feat: 新增 Grok 图像节点、前端 UI 增强、重构 nano-banana 系列
- 新增 Grok Image 节点及客户端 - 新增 save_image_format 节点 - 新增前端 JS 扩展：画笔工具、点阵网格、侧边栏隐藏、资源切换、重命名等 - 重构 nano-banana 节点，移除 pro 版本 - 移除 multi_res_preview 节点 - 新增 http_error 工具模块 - 各客户端和节点优化改进 Co-Authored-By: Claude Opus 4.6 <[email protected]>
This commit is contained in:
Jony
+11
-16
@@ -13,9 +13,10 @@ import tempfile
|
||||
|
||||
import aiohttp
|
||||
|
||||
from ..utils.config import get_api_key_or_raise, get_async_api_base_url
|
||||
from ..utils.config import get_api_key_or_raise, get_async_api_base_url, NETWORK_ROUTE_OPTIONS, get_base_url_by_route
|
||||
from ..utils.r2_uploader import upload_video, upload_image
|
||||
from ..utils.image_utils import tensor_to_pil
|
||||
from ..utils.http_error import async_request_with_retry
|
||||
|
||||
try:
|
||||
from comfy_api.latest import InputImpl
|
||||
@@ -106,6 +107,7 @@ class K3MotionControl:
|
||||
"参考图片": ("IMAGE",),
|
||||
"参考视频": ("VIDEO",),
|
||||
"提示词": ("STRING", {"multiline": True, "default": ""}),
|
||||
"网络线路": (NETWORK_ROUTE_OPTIONS, {"default": "全球加速"}),
|
||||
"模型": (["v3", "v2-6"], {"default": "v3"}),
|
||||
"模式": (["720p", "1080p"], {"default": "1080p"}),
|
||||
"时长": ([5, 10, 15, 20, 25, 30], {"default": 5}),
|
||||
@@ -123,9 +125,9 @@ class K3MotionControl:
|
||||
FUNCTION = "generate"
|
||||
CATEGORY = "comfyui_o1key/KVideo"
|
||||
|
||||
async def generate(self, 参考图片, 参考视频, 提示词, 保留原声, 角色朝向, 模式, 模型, 时长, seed, **kwargs):
|
||||
async def generate(self, 参考图片, 参考视频, 提示词, 保留原声, 角色朝向, 模式, 模型, 时长, 网络线路, seed, **kwargs):
|
||||
api_key = get_api_key_or_raise()
|
||||
base_url = get_async_api_base_url()
|
||||
base_url = get_base_url_by_route(网络线路)
|
||||
headers = {
|
||||
"Authorization": f"Bearer {api_key}",
|
||||
"Content-Type": "application/json",
|
||||
@@ -207,20 +209,13 @@ class K3MotionControl:
|
||||
# 1. 提交任务
|
||||
_stage("submitting")
|
||||
create_url = f"{base_url}{_ENDPOINT_CREATE}"
|
||||
async with session.post(
|
||||
create_url,
|
||||
resp = await async_request_with_retry(
|
||||
session, "POST", create_url,
|
||||
data=json.dumps(body, ensure_ascii=False).encode("utf-8"),
|
||||
headers=headers,
|
||||
) as resp:
|
||||
text = await resp.text()
|
||||
if resp.status != 200:
|
||||
try:
|
||||
err = json.loads(text)
|
||||
msg = err.get("message") or text
|
||||
except Exception:
|
||||
msg = text
|
||||
raise RuntimeError(f"K3 动作控制提交失败 ({resp.status}): {msg}")
|
||||
create_resp = json.loads(text)
|
||||
headers=headers, prefix="K3 动作控制提交: "
|
||||
)
|
||||
text = await resp.text()
|
||||
create_resp = json.loads(text)
|
||||
|
||||
# task_id 兼容扁平结构和 data 嵌套结构
|
||||
task_id = (
|
||||
|
||||
+10
-13
@@ -11,8 +11,9 @@ import tempfile
|
||||
|
||||
import aiohttp
|
||||
|
||||
from ..utils.config import get_api_key_or_raise, get_async_api_base_url
|
||||
from ..utils.config import get_api_key_or_raise, get_async_api_base_url, NETWORK_ROUTE_OPTIONS, get_base_url_by_route
|
||||
from ..utils.image_utils import tensor_to_pil, encode_image_to_base64
|
||||
from ..utils.http_error import async_request_with_retry
|
||||
|
||||
try:
|
||||
from comfy_api.latest import InputImpl
|
||||
@@ -113,6 +114,7 @@ class K3Video:
|
||||
"时长": ([5, 10, 15], {"default": 5}),
|
||||
"生成音频": (["关闭", "打开"], {"default": "关闭"}),
|
||||
"模式": (_MODES, {"default": "720p"}),
|
||||
"网络线路": (NETWORK_ROUTE_OPTIONS, {"default": "全球加速"}),
|
||||
"seed": ("INT", {
|
||||
"default": 0, "min": 0, "max": 2147483647,
|
||||
"tooltip": "seed 仅控制节点是否重新运行，结果本身不可复现。",
|
||||
@@ -137,9 +139,9 @@ class K3Video:
|
||||
FUNCTION = "generate"
|
||||
CATEGORY = "comfyui_o1key/KVideo"
|
||||
|
||||
async def generate(self, 多镜头, 起始帧, 提示词, 负向提示词, 时长, 生成音频, 模式, seed, **kwargs):
|
||||
async def generate(self, 多镜头, 起始帧, 提示词, 负向提示词, 时长, 生成音频, 模式, 网络线路, seed, **kwargs):
|
||||
api_key = get_api_key_or_raise()
|
||||
base_url = get_async_api_base_url()
|
||||
base_url = get_base_url_by_route(网络线路)
|
||||
headers = {
|
||||
"Authorization": f"Bearer {api_key}",
|
||||
"Content-Type": "application/json",
|
||||
@@ -246,16 +248,11 @@ class K3Video:
|
||||
# 1. 提交
|
||||
_stage("submitting")
|
||||
create_url = f"{base_url}{_ENDPOINT_CREATE}"
|
||||
async with session.post(create_url, json=body, headers=headers) as resp:
|
||||
text = await resp.text()
|
||||
if resp.status != 200:
|
||||
try:
|
||||
err = json.loads(text)
|
||||
msg = err.get("error", {}).get("message") or err.get("message") or text
|
||||
except Exception:
|
||||
msg = text
|
||||
raise RuntimeError(f"K3 提交失败 ({resp.status}): {msg}")
|
||||
create_resp = json.loads(text)
|
||||
resp = await async_request_with_retry(
|
||||
session, "POST", create_url, json=body, headers=headers, prefix="K3 提交: "
|
||||
)
|
||||
text = await resp.text()
|
||||
create_resp = json.loads(text)
|
||||
|
||||
task_id = (
|
||||
create_resp.get("task_id")
|
||||
|
||||
+10
-13
@@ -10,8 +10,9 @@ import tempfile
|
||||
|
||||
import aiohttp
|
||||
|
||||
from ..utils.config import get_api_key_or_raise, get_async_api_base_url
|
||||
from ..utils.config import get_api_key_or_raise, get_async_api_base_url, NETWORK_ROUTE_OPTIONS, get_base_url_by_route
|
||||
from ..utils.image_utils import tensor_to_pil, encode_image_to_base64
|
||||
from ..utils.http_error import async_request_with_retry
|
||||
|
||||
try:
|
||||
from comfy_api.latest import InputImpl
|
||||
@@ -94,6 +95,7 @@ class K3VideoFirstLast:
|
||||
"时长": ([5, 10, 15], {"default": 5}),
|
||||
"生成音频": (["关闭", "打开"], {"default": "关闭"}),
|
||||
"模式": (_MODES, {"default": "720p"}),
|
||||
"网络线路": (NETWORK_ROUTE_OPTIONS, {"default": "全球加速"}),
|
||||
"seed": ("INT", {
|
||||
"default": 0, "min": 0, "max": 2147483647,
|
||||
"tooltip": "seed 仅控制节点是否重新运行，结果本身不可复现。",
|
||||
@@ -109,9 +111,9 @@ class K3VideoFirstLast:
|
||||
FUNCTION = "generate"
|
||||
CATEGORY = "comfyui_o1key/KVideo"
|
||||
|
||||
async def generate(self, 起始帧, 提示词, 负向提示词, 时长, 生成音频, 模式, seed, 尾帧=None):
|
||||
async def generate(self, 起始帧, 提示词, 负向提示词, 时长, 生成音频, 模式, 网络线路, seed, 尾帧=None):
|
||||
api_key = get_api_key_or_raise()
|
||||
base_url = get_async_api_base_url()
|
||||
base_url = get_base_url_by_route(网络线路)
|
||||
headers = {
|
||||
"Authorization": f"Bearer {api_key}",
|
||||
"Content-Type": "application/json",
|
||||
@@ -185,16 +187,11 @@ class K3VideoFirstLast:
|
||||
# 1. 提交
|
||||
_stage("submitting")
|
||||
create_url = f"{base_url}{_ENDPOINT_CREATE}"
|
||||
async with session.post(create_url, json=body, headers=headers) as resp:
|
||||
text = await resp.text()
|
||||
if resp.status != 200:
|
||||
try:
|
||||
err = json.loads(text)
|
||||
msg = err.get("error", {}).get("message") or err.get("message") or text
|
||||
except Exception:
|
||||
msg = text
|
||||
raise RuntimeError(f"K3 首尾帧提交失败 ({resp.status}): {msg}")
|
||||
create_resp = json.loads(text)
|
||||
resp = await async_request_with_retry(
|
||||
session, "POST", create_url, json=body, headers=headers, prefix="K3 首尾帧提交: "
|
||||
)
|
||||
text = await resp.text()
|
||||
create_resp = json.loads(text)
|
||||
|
||||
task_id = (
|
||||
create_resp.get("task_id")
|
||||
|
||||
+10
-13
@@ -10,8 +10,9 @@ import tempfile
|
||||
|
||||
import aiohttp
|
||||
|
||||
from ..utils.config import get_api_key_or_raise, get_api_base_url
|
||||
from ..utils.config import get_api_key_or_raise, get_api_base_url, NETWORK_ROUTE_OPTIONS, get_base_url_by_route
|
||||
from ..utils.image_utils import tensor_to_pil, encode_image_to_base64
|
||||
from ..utils.http_error import async_request_with_retry
|
||||
|
||||
try:
|
||||
from comfy_api.latest import InputImpl
|
||||
@@ -55,6 +56,7 @@ class KVideoFirstLast:
|
||||
"模式": (["1080p"],),
|
||||
"时长": ([5, 10],),
|
||||
"生成音频": (["关闭", "打开"], {"default": "关闭"}),
|
||||
"网络线路": (NETWORK_ROUTE_OPTIONS, {"default": "全球加速"}),
|
||||
"seed": ("INT", {
|
||||
"default": 0, "min": 0, "max": 2147483647,
|
||||
"tooltip": "seed 仅控制节点是否重新运行，结果本身不可复现。",
|
||||
@@ -70,9 +72,9 @@ class KVideoFirstLast:
|
||||
FUNCTION = "generate"
|
||||
CATEGORY = "comfyui_o1key/KVideo"
|
||||
|
||||
async def generate(self, 起始帧, 提示词, 模式, 时长, 生成音频="关闭", 尾帧=None, seed=0):
|
||||
async def generate(self, 起始帧, 提示词, 模式, 时长, 生成音频="关闭", 网络线路="全球加速", 尾帧=None, seed=0):
|
||||
api_key = get_api_key_or_raise()
|
||||
base_url = get_api_base_url()
|
||||
base_url = get_base_url_by_route(网络线路)
|
||||
headers = {
|
||||
"Authorization": f"Bearer {api_key}",
|
||||
"Content-Type": "application/json",
|
||||
@@ -154,16 +156,11 @@ class KVideoFirstLast:
|
||||
# 1. 提交
|
||||
_stage("submitting")
|
||||
create_url = f"{base_url}{_ENDPOINT_CREATE}"
|
||||
async with session.post(create_url, json=body, headers=headers) as resp:
|
||||
text = await resp.text()
|
||||
if resp.status != 200:
|
||||
try:
|
||||
err = json.loads(text)
|
||||
msg = err.get("error", {}).get("message") or err.get("message") or text
|
||||
except Exception:
|
||||
msg = text
|
||||
raise RuntimeError(f"K26 提交失败 ({resp.status}): {msg}")
|
||||
create_resp = json.loads(text)
|
||||
resp = await async_request_with_retry(
|
||||
session, "POST", create_url, json=body, headers=headers, prefix="K26 提交: "
|
||||
)
|
||||
text = await resp.text()
|
||||
create_resp = json.loads(text)
|
||||
|
||||
task_id = (
|
||||
create_resp.get("task_id")
|
||||
|
||||
@@ -11,8 +11,9 @@ import tempfile
|
||||
|
||||
import aiohttp
|
||||
|
||||
from ..utils.config import get_api_key_or_raise, get_api_base_url
|
||||
from ..utils.config import get_api_key_or_raise, get_api_base_url, NETWORK_ROUTE_OPTIONS, get_base_url_by_route
|
||||
from ..utils.image_utils import tensor_to_pil, encode_image_to_base64
|
||||
from ..utils.http_error import async_request_with_retry
|
||||
|
||||
try:
|
||||
from comfy_api.latest import InputImpl
|
||||
@@ -56,6 +57,7 @@ class KVideoImage2Video:
|
||||
"模式": (["720p", "1080p"], {"default": "720p"}),
|
||||
"时长": ([5, 10], {"default": 5}),
|
||||
"生成音频": (["关闭", "打开"], {"default": "关闭"}),
|
||||
"网络线路": (NETWORK_ROUTE_OPTIONS, {"default": "全球加速"}),
|
||||
"seed": ("INT", {
|
||||
"default": 0, "min": 0, "max": 2147483647,
|
||||
"tooltip": "seed 仅控制节点是否重新运行，结果本身不可复现。",
|
||||
@@ -68,9 +70,9 @@ class KVideoImage2Video:
|
||||
FUNCTION = "generate"
|
||||
CATEGORY = "comfyui_o1key/KVideo"
|
||||
|
||||
async def generate(self, 起始帧, 提示词, 模式, 时长, 生成音频="关闭", seed=0):
|
||||
async def generate(self, 起始帧, 提示词, 模式, 时长, 生成音频="关闭", 网络线路="全球加速", seed=0):
|
||||
api_key = get_api_key_or_raise()
|
||||
base_url = get_api_base_url()
|
||||
base_url = get_base_url_by_route(网络线路)
|
||||
headers = {
|
||||
"Authorization": f"Bearer {api_key}",
|
||||
"Content-Type": "application/json",
|
||||
@@ -150,11 +152,10 @@ class KVideoImage2Video:
|
||||
# 1. 提交
|
||||
_stage("submitting")
|
||||
create_url = f"{base_url}{_ENDPOINT_CREATE}"
|
||||
async with session.post(create_url, json=body, headers=headers) as resp:
|
||||
if resp.status != 200:
|
||||
err_text = await resp.text()
|
||||
raise RuntimeError(f"提交失败 ({resp.status}): {err_text}")
|
||||
sr = await resp.json()
|
||||
resp = await async_request_with_retry(
|
||||
session, "POST", create_url, json=body, headers=headers, prefix="K26 图生视频提交: "
|
||||
)
|
||||
sr = await resp.json()
|
||||
|
||||
task_id = sr.get("task_id") or sr.get("id")
|
||||
if not task_id:
|
||||
|
||||
+7
-5
@@ -4,27 +4,29 @@
|
||||
"""
|
||||
|
||||
from .stream_preview import StreamPreview
|
||||
from .nano_banana_pro import NanoBananaPro
|
||||
from .batch_nano_banana_pro import BatchNanoBananaPro
|
||||
from .nano_banana import NanoBanana
|
||||
NanoBananaPro = NanoBanana
|
||||
from .batch_nano_banana import BatchNanoBananaPro
|
||||
from .google_gemini import GoogleGemini
|
||||
from .load_file import LoadFile
|
||||
from .image_stitch_pro import ImageStitchPro
|
||||
from .remove_metadata import SaveCleanImage, BatchCleanMetadata
|
||||
from .remove_metadata import BatchCleanMetadata
|
||||
from .video_preview import VideoPreview
|
||||
from .kling_video import KlingVideo, KlingFirstLastFrame, KlingMotionControlTest, AspectRatioPreset
|
||||
from .veo_video import GoogleVeo
|
||||
from .flux_edit import FluxImageEdit
|
||||
from .universal_llm import UniversalLLMChat
|
||||
from .multi_res_preview import MultiResPreview
|
||||
from .batch_images_o1key import BatchImagesO1key
|
||||
from .seedance_video import Seedance, SeedanceMultiModal
|
||||
from .nano_banana_v2 import NanoBananaV2, NanoBananaV2Batch, AsyncImageGenerator, BatchAsyncImageGenerator
|
||||
from .doubao_image import DoubaoImage
|
||||
from .gpt_image import O1keyGPTImage
|
||||
from .grok_image import O1keyGrokImage
|
||||
from .K_video_firstlast import KVideoFirstLast
|
||||
from .K_video_image2video import KVideoImage2Video
|
||||
from .K3_video import K3Video
|
||||
from .K3_video_firstlast import K3VideoFirstLast
|
||||
from .K3_motion_control import K3MotionControl, K3MotionVideoCheck
|
||||
from .save_image_format import SaveImageFormat
|
||||
|
||||
__all__ = ['NanoBananaV2', 'NanoBananaV2Batch', 'NanoBananaPro', 'BatchNanoBananaPro', 'GoogleGemini', 'LoadFile', 'ImageStitchPro', 'SaveCleanImage', 'BatchCleanMetadata', 'VideoPreview', 'KlingVideo', 'KlingFirstLastFrame', 'KlingMotionControlTest', 'AspectRatioPreset', 'GoogleVeo', 'FluxImageEdit', 'UniversalLLMChat', 'MultiResPreview', 'BatchImagesO1key', 'Seedance', 'SeedanceMultiModal', 'StreamPreview', 'DoubaoImage', 'O1keyGPTImage', 'KVideoFirstLast', 'KVideoImage2Video', 'K3Video', 'K3VideoFirstLast', 'K3MotionControl', 'K3MotionVideoCheck', 'AsyncImageGenerator', 'BatchAsyncImageGenerator']
|
||||
__all__ = ['NanoBananaV2', 'NanoBananaV2Batch', 'NanoBanana', 'BatchNanoBananaPro', 'GoogleGemini', 'LoadFile', 'ImageStitchPro', 'BatchCleanMetadata', 'VideoPreview', 'KlingVideo', 'KlingFirstLastFrame', 'KlingMotionControlTest', 'AspectRatioPreset', 'GoogleVeo', 'FluxImageEdit', 'UniversalLLMChat', 'BatchImagesO1key', 'Seedance', 'SeedanceMultiModal', 'StreamPreview', 'DoubaoImage', 'O1keyGPTImage', 'O1keyGrokImage', 'KVideoFirstLast', 'KVideoImage2Video', 'K3Video', 'K3VideoFirstLast', 'K3MotionControl', 'K3MotionVideoCheck', 'AsyncImageGenerator', 'BatchAsyncImageGenerator', 'SaveImageFormat']
|
||||
|
||||
@@ -1,11 +1,15 @@
|
||||
"""
|
||||
批量 Nano Banana Pro 节点
|
||||
批量 Nano Banana 节点
|
||||
ComfyUI 自定义节点，用于批量处理图像生成任务
|
||||
支持多文件夹加载、1:1/笛卡尔积配对、智能命名保存
|
||||
"""
|
||||
|
||||
import io as _io
|
||||
import re
|
||||
import json
|
||||
import time
|
||||
import math
|
||||
import base64
|
||||
import random
|
||||
import asyncio
|
||||
import aiohttp
|
||||
@@ -16,7 +20,7 @@ from PIL import Image
|
||||
import torch
|
||||
import numpy as np
|
||||
|
||||
from ..utils.image_utils import tensor_to_pil, pil_to_tensor, parse_batch_prompts
|
||||
from ..utils.image_utils import tensor_to_pil, pil_to_tensor, parse_batch_prompts, encode_image_to_base64, encode_image_to_base64_limited
|
||||
from ..utils.file_utils import (
|
||||
ImageInfo,
|
||||
load_images_from_folder,
|
||||
@@ -25,9 +29,10 @@ from ..utils.file_utils import (
|
||||
generate_timestamp_filename,
|
||||
save_image,
|
||||
)
|
||||
from ..utils.config import NETWORK_ROUTE_OPTIONS, get_base_url_by_route, get_api_key_or_raise
|
||||
from ..utils.http_error import RETRYABLE_STATUS_CODES, HTTP_ERROR_MESSAGES, _compute_delay, DEFAULT_MAX_RETRIES, DEFAULT_BASE_DELAY, DEFAULT_MAX_DELAY, DEFAULT_BACKOFF_FACTOR
|
||||
from ..clients.gemini_client import GeminiAPIClient
|
||||
from ..models_config import (
|
||||
get_enabled_models,
|
||||
get_model_supported_aspect_ratios, get_all_supported_aspect_ratios,
|
||||
get_model_supported_resolutions, get_all_supported_resolutions
|
||||
)
|
||||
@@ -67,7 +72,146 @@ DEBUG_LOG_ENABLED = False
|
||||
REQUEST_LOG_ENABLED = False
|
||||
# ============================================================================
|
||||
|
||||
_NODE = "Nano Banana Pro"
|
||||
_NODE = "Nano Banana"
|
||||
_ENDPOINT = "/v1/chat/completions"
|
||||
|
||||
_IMAGE_RE = re.compile(r"!\[.*?\]\(data:image/(\w+);base64,([A-Za-z0-9+/=]+)\)")
|
||||
|
||||
|
||||
def _get_headers(api_key: str) -> dict:
|
||||
return {
|
||||
"Authorization": f"Bearer {api_key}",
|
||||
"Content-Type": "application/json",
|
||||
"X-Accel-Buffering": "no",
|
||||
"Cache-Control": "no-cache, no-transform",
|
||||
}
|
||||
|
||||
|
||||
def _build_request_body(
|
||||
prompt: str,
|
||||
model: str,
|
||||
aspect_ratio: str,
|
||||
resolution: str,
|
||||
images: Optional[List[Image.Image]] = None,
|
||||
enable_grounding: bool = False,
|
||||
) -> dict:
|
||||
content_parts = [{"type": "text", "text": prompt}]
|
||||
|
||||
if images:
|
||||
for img in images:
|
||||
b64 = encode_image_to_base64_limited(img, format="PNG")
|
||||
content_parts.append({
|
||||
"type": "image_url",
|
||||
"image_url": {"url": f"data:image/png;base64,{b64}"}
|
||||
})
|
||||
|
||||
body = {
|
||||
"model": model,
|
||||
"stream": True,
|
||||
"messages": [{"role": "user", "content": content_parts}],
|
||||
}
|
||||
|
||||
google_config = {
|
||||
"image_config": {
|
||||
"image_size": resolution,
|
||||
}
|
||||
}
|
||||
if aspect_ratio and aspect_ratio != "智能":
|
||||
google_config["image_config"]["aspect_ratio"] = aspect_ratio
|
||||
body["extra_body"] = {"google": google_config}
|
||||
|
||||
if enable_grounding:
|
||||
body["extra_body"]["google_search"] = True
|
||||
|
||||
return body
|
||||
|
||||
|
||||
async def _generate_single_openai(
|
||||
session: aiohttp.ClientSession,
|
||||
base_url: str,
|
||||
api_key: str,
|
||||
prompt: str,
|
||||
model: str,
|
||||
resolution: str,
|
||||
aspect_ratio: str,
|
||||
images: Optional[List[Image.Image]] = None,
|
||||
enable_grounding: bool = False,
|
||||
) -> List[Image.Image]:
|
||||
url = f"{base_url}{_ENDPOINT}"
|
||||
headers = _get_headers(api_key)
|
||||
body = _build_request_body(
|
||||
prompt=prompt,
|
||||
model=model,
|
||||
aspect_ratio=aspect_ratio,
|
||||
resolution=resolution,
|
||||
images=images,
|
||||
enable_grounding=enable_grounding,
|
||||
)
|
||||
|
||||
if REQUEST_LOG_ENABLED:
|
||||
extra = json.dumps(body.get("extra_body", {}), ensure_ascii=False)
|
||||
print(f"[请求] POST {url} | model={model} | extra_body={extra}")
|
||||
|
||||
last_status = None
|
||||
for attempt in range(DEFAULT_MAX_RETRIES + 1):
|
||||
resp = await session.post(url, headers=headers, json=body)
|
||||
if resp.status == 200:
|
||||
break
|
||||
last_status = resp.status
|
||||
if resp.status in RETRYABLE_STATUS_CODES and attempt < DEFAULT_MAX_RETRIES:
|
||||
friendly = HTTP_ERROR_MESSAGES.get(resp.status, f"请求失败 ({resp.status})")
|
||||
delay = _compute_delay(attempt, DEFAULT_BASE_DELAY, DEFAULT_MAX_DELAY, DEFAULT_BACKOFF_FACTOR)
|
||||
resp.close()
|
||||
await asyncio.sleep(delay)
|
||||
continue
|
||||
error_text = await resp.text()
|
||||
resp.close()
|
||||
if resp.status in HTTP_ERROR_MESSAGES:
|
||||
raise RuntimeError(HTTP_ERROR_MESSAGES[resp.status])
|
||||
try:
|
||||
err_json = json.loads(error_text)
|
||||
msg = err_json.get("error", {}).get("message", error_text[:200])
|
||||
except Exception:
|
||||
msg = error_text[:200]
|
||||
raise RuntimeError(f"API 错误 ({resp.status}): {msg}")
|
||||
else:
|
||||
if last_status and last_status in HTTP_ERROR_MESSAGES:
|
||||
raise RuntimeError(HTTP_ERROR_MESSAGES[last_status])
|
||||
raise RuntimeError(f"API 错误: 重试 {DEFAULT_MAX_RETRIES} 次后仍然失败")
|
||||
|
||||
full_content = ""
|
||||
buffer = ""
|
||||
async for raw_chunk in resp.content.iter_any():
|
||||
buffer += raw_chunk.decode("utf-8")
|
||||
while "\n" in buffer:
|
||||
line_str, buffer = buffer.split("\n", 1)
|
||||
line_str = line_str.strip()
|
||||
if not line_str or not line_str.startswith("data:"):
|
||||
continue
|
||||
data_str = line_str[5:].strip()
|
||||
if data_str == "[DONE]":
|
||||
break
|
||||
try:
|
||||
chunk = json.loads(data_str)
|
||||
delta = chunk.get("choices", [{}])[0].get("delta", {})
|
||||
if "content" in delta:
|
||||
full_content += delta["content"]
|
||||
except (json.JSONDecodeError, IndexError):
|
||||
continue
|
||||
resp.close()
|
||||
|
||||
if not full_content:
|
||||
raise RuntimeError("API 未返回有效内容")
|
||||
|
||||
matches = list(_IMAGE_RE.finditer(full_content))
|
||||
if not matches:
|
||||
raise RuntimeError(f"响应中未找到图片: {full_content[:100]}")
|
||||
|
||||
last_match = matches[-1]
|
||||
img_data = base64.b64decode(last_match.group(2))
|
||||
final_image = Image.open(_io.BytesIO(img_data)).convert("RGB")
|
||||
|
||||
return [final_image]
|
||||
|
||||
|
||||
def _images_to_tensor_safe(images: List[Image.Image], node_label: str) -> torch.Tensor:
|
||||
@@ -98,7 +242,7 @@ def _images_to_tensor_safe(images: List[Image.Image], node_label: str) -> torch.
|
||||
|
||||
class BatchNanoBananaPro:
|
||||
"""
|
||||
批量 Nano Banana Pro 节点
|
||||
批量 Nano Banana 节点
|
||||
|
||||
功能：
|
||||
- 从多个文件夹加载图片
|
||||
@@ -116,26 +260,32 @@ class BatchNanoBananaPro:
|
||||
- 要添加/禁用模型，请编辑 models_config.py 文件
|
||||
"""
|
||||
|
||||
# 支持的模型列表（从配置文件动态加载）
|
||||
MODELS = None # 将在 INPUT_TYPES 中动态获取
|
||||
|
||||
# 支持的宽高比列表（全量：所有启用模型的并集，动态加载）
|
||||
# 实际渲染时通过 get_all_supported_aspect_ratios() 获取
|
||||
ASPECT_RATIOS = [
|
||||
"1:1", "4:3", "3:4", "16:9", "9:16",
|
||||
"2:3", "3:2", "4:5", "5:4", "21:9",
|
||||
"1:4", "4:1", "1:8", "8:1"
|
||||
]
|
||||
|
||||
# 支持的分辨率列表（全量兜底，实际由 get_all_supported_resolutions() 动态生成）
|
||||
RESOLUTIONS = ["512px", "1K", "2K", "4K"]
|
||||
|
||||
# 模型展示名到基础 ID 的映射
|
||||
MODEL_DISPLAY_NAMES = ["Nano Banana Pro", "Nano Banana 2", "Nano Banana"]
|
||||
MODEL_ID_MAP = {
|
||||
"Nano Banana Pro": "nano-banana-pro",
|
||||
"Nano Banana 2": "nano-banana-2",
|
||||
"Nano Banana": "nano-banana",
|
||||
}
|
||||
# 计费后缀映射
|
||||
BILLING_SUFFIX = {
|
||||
"特价": "-次卡",
|
||||
"官方": "-官方计费",
|
||||
}
|
||||
RESOLUTION_KEY_MAP = {
|
||||
"512px": "0.5k",
|
||||
"1K": "1k",
|
||||
"2K": "2k",
|
||||
"4K": "4k",
|
||||
}
|
||||
# 仅支持特价的模型
|
||||
BILLING_SPECIAL_ONLY = {"nano-banana"}
|
||||
|
||||
# 配对模式
|
||||
PAIRING_MODES = ["按相同图片命名", "1*N", "不配对"]
|
||||
|
||||
|
||||
def __init__(self):
|
||||
"""初始化节点"""
|
||||
self.client = None
|
||||
pass
|
||||
|
||||
def resize_to_megapixels(
|
||||
self,
|
||||
@@ -181,33 +331,17 @@ class BatchNanoBananaPro:
|
||||
|
||||
@classmethod
|
||||
def INPUT_TYPES(cls):
|
||||
"""
|
||||
定义输入参数
|
||||
|
||||
ComfyUI 节点规范：
|
||||
- required: 必选参数
|
||||
- optional: 可选参数
|
||||
"""
|
||||
# 从配置文件动态获取启用的模型列表
|
||||
enabled_models = get_enabled_models()
|
||||
|
||||
# 如果没有启用的模型，使用空列表（会导致节点不可用，提示用户配置）
|
||||
if not enabled_models:
|
||||
enabled_models = ["请在 models_config.py 中启用至少一个模型"]
|
||||
|
||||
# 动态获取所有启用模型支持的宽高比（去重合并）
|
||||
all_aspect_ratios = get_all_supported_aspect_ratios()
|
||||
if not all_aspect_ratios:
|
||||
all_aspect_ratios = cls.ASPECT_RATIOS
|
||||
|
||||
# 动态获取所有启用模型支持的分辨率（去重合并）
|
||||
all_aspect_ratios = ["1:1", "4:3", "3:4", "16:9", "9:16", "2:3", "3:2", "4:5", "5:4", "21:9", "1:4", "4:1", "1:8", "8:1"]
|
||||
|
||||
all_resolutions = get_all_supported_resolutions()
|
||||
if not all_resolutions:
|
||||
all_resolutions = cls.RESOLUTIONS
|
||||
all_resolutions = ["512px", "1K", "2K", "4K"]
|
||||
|
||||
# 创建9个独立的图像输入
|
||||
# 创建5个独立的图像输入
|
||||
optional_inputs = {}
|
||||
for i in range(1, 10): # 1-9
|
||||
for i in range(1, 6): # 1-5
|
||||
optional_inputs[f"参考图{i}"] = ("IMAGE",)
|
||||
|
||||
# 图片配对模式移到可选参数
|
||||
@@ -215,35 +349,29 @@ class BatchNanoBananaPro:
|
||||
"default": "不配对"
|
||||
})
|
||||
|
||||
optional_inputs["代理端口（如7897）"] = ("STRING", {
|
||||
"default": "",
|
||||
"multiline": False,
|
||||
"placeholder": "本地代理端口，如 7897（Clash Verge）或 10808（v2rayN），留空不使用"
|
||||
})
|
||||
|
||||
return {
|
||||
"required": {
|
||||
"prompt": ("STRING", {
|
||||
"default": "一个中国女子的OOTD",
|
||||
"multiline": True
|
||||
}),
|
||||
"模型": (enabled_models, {
|
||||
"default": enabled_models[0]
|
||||
"模型": (cls.MODEL_DISPLAY_NAMES, {
|
||||
"default": cls.MODEL_DISPLAY_NAMES[0]
|
||||
}),
|
||||
"宽高比": (all_aspect_ratios, {
|
||||
"default": "1:1"
|
||||
"宽高比": (["智能"] + all_aspect_ratios, {
|
||||
"default": "智能"
|
||||
}),
|
||||
"分辨率": (all_resolutions, {
|
||||
"default": "2K"
|
||||
}),
|
||||
"谷歌搜索（联网）": (["关闭", "打开"], {
|
||||
"default": "关闭"
|
||||
"图片格式": (["原始", "JPEG", "PNG", "WebP"], {
|
||||
"default": "原始"
|
||||
}),
|
||||
"图片搜索（联网）": (["关闭", "打开"], {
|
||||
"default": "关闭"
|
||||
"计费": (["特价", "官方"], {
|
||||
"default": "特价"
|
||||
}),
|
||||
"返回格式": (["url", "base64"], {
|
||||
"default": "url"
|
||||
"网络": (NETWORK_ROUTE_OPTIONS, {
|
||||
"default": "全球加速"
|
||||
}),
|
||||
"seed": ("INT", {
|
||||
"default": 0,
|
||||
@@ -270,22 +398,6 @@ class BatchNanoBananaPro:
|
||||
"default": "",
|
||||
"multiline": False
|
||||
}),
|
||||
"文件夹6": ("STRING", {
|
||||
"default": "",
|
||||
"multiline": False
|
||||
}),
|
||||
"文件夹7": ("STRING", {
|
||||
"default": "",
|
||||
"multiline": False
|
||||
}),
|
||||
"文件夹8": ("STRING", {
|
||||
"default": "",
|
||||
"multiline": False
|
||||
}),
|
||||
"文件夹9": ("STRING", {
|
||||
"default": "",
|
||||
"multiline": False
|
||||
}),
|
||||
"保存路径": ("STRING", {
|
||||
"default": "",
|
||||
"multiline": False
|
||||
@@ -403,8 +515,9 @@ class BatchNanoBananaPro:
|
||||
|
||||
async def _generate_single_task(
|
||||
self,
|
||||
client: GeminiAPIClient,
|
||||
session: aiohttp.ClientSession,
|
||||
base_url: str,
|
||||
api_key: str,
|
||||
prompt: str,
|
||||
model: str,
|
||||
resolution: str,
|
||||
@@ -412,27 +525,12 @@ class BatchNanoBananaPro:
|
||||
images: List[ImageInfo],
|
||||
output_folder: str,
|
||||
task_index: int,
|
||||
enable_grounding: bool = True,
|
||||
enable_image_search: bool = False,
|
||||
enable_grounding: bool = False,
|
||||
base_filename: str = None,
|
||||
image_format: str = "url",
|
||||
image_format: str = "原始",
|
||||
) -> dict:
|
||||
"""
|
||||
执行单个生成任务
|
||||
|
||||
Args:
|
||||
client: API 客户端
|
||||
session: aiohttp 会话
|
||||
prompt: 提示词
|
||||
model: 模型名称
|
||||
resolution: 分辨率
|
||||
aspect_ratio: 宽高比
|
||||
images: 输入图片列表
|
||||
output_folder: 输出文件夹
|
||||
task_index: 任务索引
|
||||
|
||||
Returns:
|
||||
包含结果信息的字典
|
||||
执行单个生成任务（OpenAI 兼容接口）
|
||||
"""
|
||||
result = {
|
||||
"task_index": task_index,
|
||||
@@ -440,34 +538,29 @@ class BatchNanoBananaPro:
|
||||
"success": False,
|
||||
"generated_count": 0,
|
||||
"saved_files": [],
|
||||
"output_images": [], # 无保存路径时存储内存图片
|
||||
"output_images": [],
|
||||
"error": None
|
||||
}
|
||||
|
||||
|
||||
try:
|
||||
# 准备输入图片
|
||||
input_pil_images = [info.image for info in images]
|
||||
|
||||
# 调用 API 生成图片（固定生成1次）
|
||||
|
||||
# 调用 OpenAI 兼容接口生成图片
|
||||
generated_images = []
|
||||
try:
|
||||
gen_result = await client.generate_single_async(
|
||||
gen_images = await _generate_single_openai(
|
||||
session=session,
|
||||
base_url=base_url,
|
||||
api_key=api_key,
|
||||
prompt=prompt,
|
||||
model=model,
|
||||
resolution=resolution,
|
||||
aspect_ratio=aspect_ratio,
|
||||
images=input_pil_images,
|
||||
session=session,
|
||||
debug=DEBUG_LOG_ENABLED,
|
||||
debug_request=REQUEST_LOG_ENABLED,
|
||||
images=input_pil_images if input_pil_images else None,
|
||||
enable_grounding=enable_grounding,
|
||||
enable_image_search=enable_image_search,
|
||||
image_format=image_format,
|
||||
)
|
||||
if gen_result:
|
||||
# 正确解包元组：第一个元素是图像列表，第二个是计时信息
|
||||
images_list, timing_info = gen_result
|
||||
generated_images.extend(images_list)
|
||||
generated_images.extend(gen_images)
|
||||
except Exception as e:
|
||||
import traceback
|
||||
error_msg = str(e)
|
||||
@@ -490,29 +583,54 @@ class BatchNanoBananaPro:
|
||||
|
||||
# 保存生成的图片到磁盘（始终保存）
|
||||
import os
|
||||
|
||||
# 确定保存扩展名
|
||||
_FORMAT_EXT_MAP = {"JPEG": ".jpg", "PNG": ".png", "WebP": ".webp"}
|
||||
save_ext = _FORMAT_EXT_MAP.get(image_format, ".png")
|
||||
|
||||
for i, gen_img in enumerate(generated_images):
|
||||
# 格式转换：非"原始"时检测并转换
|
||||
if image_format != "原始":
|
||||
src_format = (gen_img.format or "").upper()
|
||||
target_upper = image_format.upper()
|
||||
# JPEG 格式名在 PIL 中为 "JPEG"
|
||||
if src_format == "JPG":
|
||||
src_format = "JPEG"
|
||||
need_convert = (src_format != target_upper)
|
||||
if need_convert:
|
||||
if target_upper in ("JPEG", "WEBP") and gen_img.mode in ("RGBA", "LA", "P"):
|
||||
gen_img = gen_img.convert("RGB")
|
||||
|
||||
# 使用文件夹1图片的名称，如果重名则+1
|
||||
if base_filename:
|
||||
base_name = base_filename
|
||||
counter = 0
|
||||
while True:
|
||||
if counter == 0:
|
||||
filename = f"{base_name}.png"
|
||||
filename = f"{base_name}{save_ext}"
|
||||
else:
|
||||
filename = f"{base_name}+{counter}.png"
|
||||
filename = f"{base_name}+{counter}{save_ext}"
|
||||
output_path = os.path.join(output_folder, filename)
|
||||
if not os.path.exists(output_path):
|
||||
break
|
||||
counter += 1
|
||||
else:
|
||||
# 如果没有base_filename，使用时间戳
|
||||
output_path = generate_timestamp_filename(
|
||||
output_folder=output_folder,
|
||||
extension=".png"
|
||||
extension=save_ext
|
||||
)
|
||||
save_image(gen_img, output_path)
|
||||
|
||||
# 保存时不压缩
|
||||
if image_format == "JPEG":
|
||||
if gen_img.mode != "RGB":
|
||||
gen_img = gen_img.convert("RGB")
|
||||
gen_img.save(output_path, quality=100)
|
||||
elif image_format == "WebP":
|
||||
gen_img.save(output_path, lossless=True)
|
||||
else:
|
||||
save_image(gen_img, output_path)
|
||||
|
||||
result["saved_files"].append(output_path)
|
||||
# 立即释放内存
|
||||
gen_img = None
|
||||
|
||||
# 只有生成了图片才标记为成功
|
||||
@@ -533,38 +651,20 @@ class BatchNanoBananaPro:
|
||||
resolution: str,
|
||||
aspect_ratio: str,
|
||||
output_folder: str,
|
||||
base_url: str,
|
||||
api_key: str,
|
||||
pbar=None,
|
||||
prompts_per_task: Optional[List[str]] = None,
|
||||
enable_grounding: bool = True,
|
||||
enable_image_search: bool = False,
|
||||
image_format: str = "url",
|
||||
enable_grounding: bool = False,
|
||||
image_format: str = "原始",
|
||||
) -> List[dict]:
|
||||
"""
|
||||
异步批量处理所有任务 - 改进版：支持分批保存
|
||||
|
||||
Args:
|
||||
pairs: 配对后的图片组合
|
||||
prompt: 提示词（单提示词模式时使用）
|
||||
model: 模型名称
|
||||
resolution: 分辨率
|
||||
aspect_ratio: 宽高比
|
||||
output_folder: 输出文件夹
|
||||
pbar: ComfyUI 进度条
|
||||
prompts_per_task: 每个任务对应的提示词列表（批量提示词模式时使用）
|
||||
|
||||
Returns:
|
||||
所有任务的结果列表
|
||||
异步批量处理所有任务（OpenAI 兼容接口）
|
||||
"""
|
||||
if self.client is None:
|
||||
self.client = GeminiAPIClient()
|
||||
|
||||
total_tasks = len(pairs)
|
||||
|
||||
max_concurrent = 50
|
||||
|
||||
# 分批保存的批次大小（与并发数一致）
|
||||
save_batch_size = 10
|
||||
|
||||
print(f"BatchNanoBananaPro: 检测到 {total_tasks} 个任务")
|
||||
|
||||
all_results = []
|
||||
@@ -617,8 +717,9 @@ class BatchNanoBananaPro:
|
||||
|
||||
task = asyncio.create_task(
|
||||
self._generate_single_task(
|
||||
client=self.client,
|
||||
session=session,
|
||||
base_url=base_url,
|
||||
api_key=api_key,
|
||||
prompt=task_prompt,
|
||||
model=model,
|
||||
resolution=resolution,
|
||||
@@ -627,7 +728,6 @@ class BatchNanoBananaPro:
|
||||
output_folder=output_folder,
|
||||
task_index=start_idx + i,
|
||||
enable_grounding=enable_grounding,
|
||||
enable_image_search=enable_image_search,
|
||||
base_filename=base_filename,
|
||||
image_format=image_format,
|
||||
)
|
||||
@@ -721,15 +821,14 @@ class BatchNanoBananaPro:
|
||||
文件夹3: str,
|
||||
文件夹4: str,
|
||||
文件夹5: str,
|
||||
文件夹6: str,
|
||||
文件夹7: str,
|
||||
文件夹8: str,
|
||||
文件夹9: str,
|
||||
seed: int,
|
||||
图片配对模式: str,
|
||||
模型: str,
|
||||
计费: str,
|
||||
宽高比: str,
|
||||
分辨率: str,
|
||||
图片格式: str,
|
||||
网络: str,
|
||||
保存路径: str = "",
|
||||
**kwargs
|
||||
) -> Tuple[torch.Tensor]:
|
||||
@@ -738,14 +837,14 @@ class BatchNanoBananaPro:
|
||||
|
||||
Args:
|
||||
prompt: 提示词
|
||||
文件夹1-9: 图片文件夹路径
|
||||
文件夹1-5: 图片文件夹路径
|
||||
seed: 随机种子
|
||||
保存路径: 输出保存路径
|
||||
图片配对模式: 1:1 或 1*N
|
||||
模型: 模型名称
|
||||
宽高比: 输出宽高比
|
||||
分辨率: 输出分辨率
|
||||
**kwargs: 动态参考图输入 (参考图1-9)
|
||||
**kwargs: 动态参考图输入 (参考图1-5)
|
||||
|
||||
Returns:
|
||||
输出图像张量
|
||||
@@ -753,10 +852,27 @@ class BatchNanoBananaPro:
|
||||
start_time = time.time()
|
||||
|
||||
# 从 kwargs 提取搜索参数（界面显示为「关闭/打开」，转为 bool 供调用）
|
||||
enable_grounding: bool = (kwargs.pop("谷歌搜索（联网）", "关闭") == "打开")
|
||||
enable_image_search: bool = (kwargs.pop("图片搜索（联网）", "关闭") == "打开")
|
||||
proxy_port: str = kwargs.pop("代理端口（如7897）", "")
|
||||
image_format: str = kwargs.pop("返回格式", "url")
|
||||
enable_grounding: bool = False
|
||||
|
||||
# 拼接实际模型 ID
|
||||
base_model_id = self.MODEL_ID_MAP.get(模型, "nano-banana-pro")
|
||||
if base_model_id == "nano-banana":
|
||||
if 计费 == "官方":
|
||||
raise ValueError(f"模型 \"{模型}\" 仅支持特价计费")
|
||||
模型 = "nano-banana"
|
||||
else:
|
||||
res_key = self.RESOLUTION_KEY_MAP.get(分辨率, "2k")
|
||||
is_official = (计费 == "官方")
|
||||
if base_model_id == "nano-banana-pro" and res_key == "1k" and not is_official:
|
||||
模型 = "nano-banana-pro"
|
||||
elif base_model_id == "nano-banana-2" and res_key == "0.5k":
|
||||
if is_official:
|
||||
raise ValueError("Nano Banana 2 的 512px 分辨率仅支持特价计费")
|
||||
模型 = "nano-banana-2-0.5k"
|
||||
else:
|
||||
模型 = f"{base_model_id}-{res_key}"
|
||||
if is_official:
|
||||
模型 += "-official"
|
||||
|
||||
|
||||
try:
|
||||
@@ -767,7 +883,7 @@ class BatchNanoBananaPro:
|
||||
# 验证：至少需要填写一个文件夹路径
|
||||
has_any_folder = any(
|
||||
f and f.strip()
|
||||
for f in [文件夹1, 文件夹2, 文件夹3, 文件夹4, 文件夹5, 文件夹6, 文件夹7, 文件夹8, 文件夹9]
|
||||
for f in [文件夹1, 文件夹2, 文件夹3, 文件夹4, 文件夹5]
|
||||
)
|
||||
if not has_any_folder:
|
||||
raise ValueError("请至少填写一个文件夹路径，该节点专为批量文件夹处理设计")
|
||||
@@ -782,26 +898,16 @@ class BatchNanoBananaPro:
|
||||
|
||||
# 校验宽高比与模型的兼容性
|
||||
supported_ratios = get_model_supported_aspect_ratios(模型)
|
||||
if supported_ratios and 宽高比 not in supported_ratios:
|
||||
if 宽高比 != "智能" and supported_ratios and 宽高比 not in supported_ratios:
|
||||
raise ValueError(
|
||||
f"宽高比 \"{宽高比}\" 与模型 \"{模型}\" 不兼容！\n"
|
||||
f"该模型支持的宽高比：{', '.join(supported_ratios)}"
|
||||
)
|
||||
|
||||
# 校验图片搜索（联网）与模型的兼容性
|
||||
# 仅 nano-banana-2-限时特价 和 gemini-3.1-flash-image-preview 支持图片搜索
|
||||
IMAGE_SEARCH_UNSUPPORTED_MODELS = ["nano-banana-pro-次卡", "nano-banana-pro-官方计费", "gemini-3-pro-image-preview"]
|
||||
if enable_image_search and 模型 in IMAGE_SEARCH_UNSUPPORTED_MODELS:
|
||||
raise ValueError(
|
||||
f"模型 \"{模型}\" 不支持【图片搜索（联网）】功能！"
|
||||
f"请切换到 nano-banana-2-限时特价 或 gemini-3.1-flash-image-preview 后再使用"
|
||||
)
|
||||
|
||||
# 加载文件夹图片
|
||||
print("BatchNanoBananaPro: 开始加载图片...")
|
||||
image_lists = self._load_folders(
|
||||
文件夹1, 文件夹2, 文件夹3, 文件夹4,
|
||||
文件夹5, 文件夹6, 文件夹7, 文件夹8, 文件夹9
|
||||
文件夹1, 文件夹2, 文件夹3, 文件夹4, 文件夹5
|
||||
)
|
||||
|
||||
# 验证文件夹是否有可用图片
|
||||
@@ -811,7 +917,7 @@ class BatchNanoBananaPro:
|
||||
|
||||
# 处理独立的参考图输入
|
||||
manual_images = []
|
||||
for i in range(1, 10): # 1-9
|
||||
for i in range(1, 6): # 1-5
|
||||
key = f"参考图{i}"
|
||||
if key in kwargs and kwargs[key] is not None:
|
||||
pil_images = tensor_to_pil(kwargs[key])
|
||||
@@ -848,11 +954,8 @@ class BatchNanoBananaPro:
|
||||
total_tasks = len(pairs)
|
||||
|
||||
# 打印首行概览
|
||||
# 图片搜索（联网）开启时隐含谷歌搜索接地，与客户端请求逻辑保持一致
|
||||
grounding_str = ""
|
||||
if enable_image_search:
|
||||
grounding_str = " | 谷歌图片搜索接地"
|
||||
elif enable_grounding:
|
||||
if enable_grounding:
|
||||
grounding_str = " | 谷歌搜索接地"
|
||||
|
||||
if batch_prompts:
|
||||
@@ -890,18 +993,10 @@ class BatchNanoBananaPro:
|
||||
except Exception as e:
|
||||
raise ValueError(f"保存路径无效或无写入权限: {保存路径} - {str(e)}")
|
||||
|
||||
# 初始化 API 客户端
|
||||
if self.client is None:
|
||||
try:
|
||||
self.client = GeminiAPIClient()
|
||||
except ValueError as e:
|
||||
raise ValueError(f"初始化 API 客户端失败: {str(e)}")
|
||||
# 获取 API 密钥和基础 URL
|
||||
api_key = get_api_key_or_raise("O1KEY_API_KEY")
|
||||
base_url = get_base_url_by_route(网络)
|
||||
|
||||
# 注入代理设置（每次执行都刷新，支持用户中途修改端口）
|
||||
self.client.proxy_url = GeminiAPIClient.build_proxy_url(proxy_port)
|
||||
if self.client.proxy_url:
|
||||
print(f"BatchNanoBananaPro: 已启用代理加速 → {self.client.proxy_url}")
|
||||
|
||||
# 判断是否使用默认 output 目录
|
||||
original_save_path = kwargs.get('保存路径', '')
|
||||
user_set_save_path = bool(original_save_path and original_save_path.strip())
|
||||
@@ -920,11 +1015,12 @@ class BatchNanoBananaPro:
|
||||
resolution=分辨率,
|
||||
aspect_ratio=宽高比,
|
||||
output_folder=保存路径,
|
||||
base_url=base_url,
|
||||
api_key=api_key,
|
||||
pbar=pbar,
|
||||
prompts_per_task=prompts_per_task,
|
||||
enable_grounding=enable_grounding,
|
||||
enable_image_search=enable_image_search,
|
||||
image_format=image_format,
|
||||
image_format=图片格式,
|
||||
)
|
||||
)
|
||||
except Exception as e:
|
||||
@@ -1050,14 +1146,15 @@ class BatchNanoBananaPro:
|
||||
|
||||
finally:
|
||||
# 查询余额
|
||||
if self.client is not None:
|
||||
try:
|
||||
balance_data = self.client.query_balance_sync()
|
||||
balance_info = self.client.format_balance_info(balance_data)
|
||||
print(f"BatchNanaBananaPro: {balance_info}")
|
||||
print("=" * 60)
|
||||
except Exception:
|
||||
pass
|
||||
try:
|
||||
client = GeminiAPIClient()
|
||||
client.base_url = get_base_url_by_route(网络)
|
||||
balance_data = client.query_balance_sync()
|
||||
balance_info = client.format_balance_info(balance_data)
|
||||
print(f"BatchNanoBananaPro: {balance_info}")
|
||||
print("=" * 60)
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
# 最终内存清理
|
||||
import gc
|
||||
+19
-13
@@ -6,6 +6,7 @@ o1key GPT Image 节点
|
||||
import time
|
||||
from ..clients.gpt_image_client import GptImageClient
|
||||
from ..utils.image_utils import parse_batch_prompts
|
||||
from ..utils.config import NETWORK_ROUTE_OPTIONS, get_base_url_by_route
|
||||
|
||||
try:
|
||||
from comfy.model_management import processing_interrupted, InterruptProcessingException
|
||||
@@ -52,30 +53,33 @@ class O1keyGPTImage:
|
||||
], {
|
||||
"default": "gpt-image-2-次卡",
|
||||
})
|
||||
optional_inputs["网络"] = (NETWORK_ROUTE_OPTIONS, {
|
||||
"default": "全球加速",
|
||||
})
|
||||
optional_inputs["分辨率"] = ([
|
||||
"智能",
|
||||
# ── 1K ──
|
||||
"1024x1024（1K 正方形 1:1）",
|
||||
"1536x1024（1K 横版 3:2）",
|
||||
"1024x1536（1K 竖版 2:3）",
|
||||
"1365x1024（1K 横版 4:3）",
|
||||
"1024x1365（1K 竖版 3:4）",
|
||||
"1820x1024（1K 横版 16:9）",
|
||||
"1024x1820（1K 竖版 9:16）",
|
||||
"1360x1024（1K 横版 4:3）",
|
||||
"1024x1360（1K 竖版 3:4）",
|
||||
"1824x1024（1K 横版 16:9）",
|
||||
"1024x1824（1K 竖版 9:16）",
|
||||
# ── 2K ──
|
||||
"2048x2048（2K 正方形 1:1）",
|
||||
"3072x2048（2K 横版 3:2）",
|
||||
"2048x3072（2K 竖版 2:3）",
|
||||
"2732x2048（2K 横版 4:3）",
|
||||
"2048x2732（2K 竖版 3:4）",
|
||||
"3640x2048（2K 横版 16:9）",
|
||||
"2048x3640（2K 竖版 9:16）",
|
||||
"2736x2048（2K 横版 4:3）",
|
||||
"2048x2736（2K 竖版 3:4）",
|
||||
"3648x2048（2K 横版 16:9）",
|
||||
"2048x3648（2K 竖版 9:16）",
|
||||
# ── 4K ──
|
||||
"3840x3840（4K 正方形 1:1）",
|
||||
"3840x2560（4K 横版 3:2）",
|
||||
"2560x3840（4K 竖版 2:3）",
|
||||
"3840x2880（4K 横版 4:3）",
|
||||
"2880x3840（4K 竖版 3:4）",
|
||||
"2880x2880（4K 正方形 1:1）",
|
||||
"3504x2336（4K 横版 3:2）",
|
||||
"2336x3504（4K 竖版 2:3）",
|
||||
"3264x2448（4K 横版 4:3）",
|
||||
"2448x3264（4K 竖版 3:4）",
|
||||
"3840x2160（4K 横版 16:9）",
|
||||
"2160x3840（4K 竖版 9:16）",
|
||||
], {
|
||||
@@ -128,6 +132,7 @@ class O1keyGPTImage:
|
||||
self,
|
||||
prompt: str,
|
||||
模型: str = "gpt-image-2-次卡",
|
||||
网络: str = "全球加速",
|
||||
分辨率: str = "auto",
|
||||
质量: str = "自动",
|
||||
生图数量: int = 1,
|
||||
@@ -169,6 +174,7 @@ class O1keyGPTImage:
|
||||
# ── 3. 创建客户端 ─────────────────────────────────────────────────────
|
||||
try:
|
||||
client = GptImageClient()
|
||||
client.base_url = get_base_url_by_route(网络)
|
||||
except ValueError as e:
|
||||
if str(e) == "未授权！":
|
||||
print("[o1key GPT Image] 请联系作者授权后方可使用！")
|
||||
|
||||
@@ -0,0 +1,165 @@
|
||||
"""
|
||||
o1key Grok Image 节点
|
||||
支持 Grok Image / Grok Image Pro 模型的文生图和图生图
|
||||
"""
|
||||
|
||||
import time
|
||||
from ..clients.grok_image_client import GrokImageClient
|
||||
from ..utils.image_utils import parse_batch_prompts
|
||||
from ..utils.config import NETWORK_ROUTE_OPTIONS
|
||||
|
||||
try:
|
||||
from comfy.model_management import processing_interrupted, InterruptProcessingException
|
||||
_INTERRUPT_AVAILABLE = True
|
||||
except ImportError:
|
||||
_INTERRUPT_AVAILABLE = False
|
||||
processing_interrupted = lambda: False
|
||||
InterruptProcessingException = RuntimeError
|
||||
|
||||
_ASPECT_RATIOS = [
|
||||
"auto", "1:1", "16:9", "9:16", "4:3", "3:4",
|
||||
"3:2", "2:3", "2:1", "1:2", "19.5:9", "9:19.5", "20:9", "9:20",
|
||||
]
|
||||
|
||||
|
||||
class O1keyGrokImage:
|
||||
|
||||
@classmethod
|
||||
def INPUT_TYPES(cls):
|
||||
optional_inputs = {}
|
||||
for i in range(1, 4):
|
||||
optional_inputs[f"参考图{i}"] = ("IMAGE", {
|
||||
"tooltip": f"Optional reference image {i}",
|
||||
})
|
||||
|
||||
return {
|
||||
"required": {
|
||||
"prompt": ("STRING", {
|
||||
"default": "",
|
||||
"multiline": True,
|
||||
"tooltip": "文本提示词，用 --- 独占一行分隔批量提示词",
|
||||
}),
|
||||
},
|
||||
"optional": {
|
||||
"模型": (["Grok Image", "Grok Image Pro"], {
|
||||
"default": "Grok Image Pro",
|
||||
}),
|
||||
"宽高比": (_ASPECT_RATIOS, {
|
||||
"default": "auto",
|
||||
}),
|
||||
"分辨率": (["1k", "2k"], {
|
||||
"default": "1k",
|
||||
}),
|
||||
"生图数量": ("INT", {
|
||||
"default": 1,
|
||||
"min": 1,
|
||||
"max": 4,
|
||||
"step": 1,
|
||||
"display": "number",
|
||||
}),
|
||||
"网络线路": (NETWORK_ROUTE_OPTIONS, {
|
||||
"default": NETWORK_ROUTE_OPTIONS[0],
|
||||
}),
|
||||
"seed": ("INT", {
|
||||
"default": 0,
|
||||
"min": 0,
|
||||
"max": 2**31 - 1,
|
||||
"step": 1,
|
||||
"display": "number",
|
||||
"control_after_generate": True,
|
||||
}),
|
||||
**optional_inputs,
|
||||
},
|
||||
}
|
||||
|
||||
RETURN_TYPES = ("IMAGE",)
|
||||
RETURN_NAMES = ("IMAGE",)
|
||||
FUNCTION = "generate"
|
||||
CATEGORY = "o1key/image"
|
||||
OUTPUT_NODE = False
|
||||
|
||||
def generate(
|
||||
self,
|
||||
prompt: str,
|
||||
模型: str = "Grok Image Pro",
|
||||
宽高比: str = "auto",
|
||||
分辨率: str = "1k",
|
||||
生图数量: int = 1,
|
||||
网络线路: str = "全球加速",
|
||||
seed: int = 0,
|
||||
**kwargs,
|
||||
):
|
||||
start_time = time.time()
|
||||
|
||||
reference_tensors = []
|
||||
for i in range(1, 4):
|
||||
key = f"参考图{i}"
|
||||
if key in kwargs and kwargs[key] is not None:
|
||||
reference_tensors.append(kwargs[key])
|
||||
image_list = reference_tensors if reference_tensors else None
|
||||
|
||||
try:
|
||||
client = GrokImageClient(route=网络线路)
|
||||
except ValueError as e:
|
||||
if str(e) == "未授权！":
|
||||
print("[o1key Grok Image] 请联系作者授权后方可使用！")
|
||||
raise ValueError("未授权！") from None
|
||||
raise
|
||||
|
||||
try:
|
||||
batch_prompts = parse_batch_prompts(prompt)
|
||||
all_pil_images = []
|
||||
|
||||
if batch_prompts:
|
||||
total = len(batch_prompts)
|
||||
print(f"[o1key Grok Image] 批量模式 | {total} 条提示词 | 每条生成 {生图数量} 张")
|
||||
for idx, p in enumerate(batch_prompts, 1):
|
||||
if _INTERRUPT_AVAILABLE and processing_interrupted():
|
||||
print("[o1key Grok Image] 用户取消")
|
||||
raise InterruptProcessingException()
|
||||
try:
|
||||
pil_images = client.run_sync(
|
||||
prompt=p, model=模型, aspect_ratio=宽高比,
|
||||
resolution=分辨率, n=生图数量, image_list=image_list,
|
||||
)
|
||||
all_pil_images.extend(pil_images)
|
||||
snippet = p[:30] + ("..." if len(p) >= 30 else "")
|
||||
print(f"[o1key Grok Image] [{idx}/{total}] done: {snippet}")
|
||||
except InterruptProcessingException:
|
||||
raise
|
||||
except Exception as e:
|
||||
error_msg = str(e).split('\n')[0]
|
||||
snippet = p[:30] + ("..." if len(p) >= 30 else "")
|
||||
print(f"[o1key Grok Image] [{idx}/{total}] fail: {snippet} → {error_msg}")
|
||||
else:
|
||||
if not prompt or not prompt.strip():
|
||||
raise ValueError("提示词不能为空")
|
||||
pil_images = client.run_sync(
|
||||
prompt=prompt, model=模型, aspect_ratio=宽高比,
|
||||
resolution=分辨率, n=生图数量, image_list=image_list,
|
||||
)
|
||||
all_pil_images.extend(pil_images)
|
||||
|
||||
if not all_pil_images:
|
||||
raise RuntimeError("所有提示词均生成失败，无可用图像输出")
|
||||
|
||||
output_tensor = GrokImageClient._pil_list_to_tensor(all_pil_images)
|
||||
|
||||
elapsed = time.time() - start_time
|
||||
print(
|
||||
f"[o1key Grok Image] 完成！耗时 {elapsed:.1f}s，"
|
||||
f"输出 {output_tensor.shape[0]} 张 "
|
||||
f"{output_tensor.shape[2]}x{output_tensor.shape[1]}"
|
||||
)
|
||||
return (output_tensor,)
|
||||
|
||||
finally:
|
||||
self._print_balance(client)
|
||||
|
||||
def _print_balance(self, client):
|
||||
try:
|
||||
balance_data = client.query_balance_sync()
|
||||
balance_info = client.format_balance_info(balance_data)
|
||||
print(f"[o1key Grok Image] {balance_info}")
|
||||
except Exception:
|
||||
pass
|
||||
@@ -8,6 +8,7 @@ import tempfile
|
||||
from ..clients.kling_client import KlingClient
|
||||
from ..clients.gemini_client import GeminiAPIClient
|
||||
from ..utils.image_utils import tensor_to_pil, encode_image_to_base64
|
||||
from ..utils.config import NETWORK_ROUTE_OPTIONS, get_base_url_by_route
|
||||
|
||||
from comfy_api.latest import InputImpl
|
||||
|
||||
@@ -121,6 +122,7 @@ class KlingVideo:
|
||||
"required": {
|
||||
"提示词": ("STRING", {"multiline": True, "default": ""}),
|
||||
"反向提示词": ("STRING", {"multiline": True, "default": ""}),
|
||||
"网络线路": (NETWORK_ROUTE_OPTIONS, {"default": "全球加速"}),
|
||||
"模型版本": (["v3", "v2-6"], {"default": "v3"}),
|
||||
"时长": ([5, 10, 15],),
|
||||
"分辨率": (["1080p", "720p"],),
|
||||
@@ -244,13 +246,15 @@ class KlingVideo:
|
||||
body["image"] = _tensor_to_base64(start_frame)
|
||||
endpoint_type = "image2video"
|
||||
else:
|
||||
body["metadata"] = {"aspect_ratio": aspect_ratio}
|
||||
if aspect_ratio and aspect_ratio != "智能":
|
||||
body["metadata"] = {"aspect_ratio": aspect_ratio}
|
||||
endpoint_type = "text2video"
|
||||
|
||||
# ── 保存路径（临时文件，避免与下游保存节点重复落盘）──────────────────
|
||||
_, save_path = tempfile.mkstemp(suffix=".mp4", prefix="kling_")
|
||||
|
||||
client = KlingClient()
|
||||
client.base_url = get_base_url_by_route(kwargs.get("网络线路", "全球加速"))
|
||||
|
||||
# ── 进度条 ────────────────────────────────────────────────────
|
||||
try:
|
||||
@@ -307,6 +311,7 @@ class KlingFirstLastFrame:
|
||||
"首帧": ("IMAGE",),
|
||||
"尾帧": ("IMAGE",),
|
||||
"提示词": ("STRING", {"multiline": True, "default": ""}),
|
||||
"网络线路": (NETWORK_ROUTE_OPTIONS, {"default": "全球加速"}),
|
||||
"模型": (["v3", "v2-6"], {"default": "v3"}),
|
||||
"分辨率": (["1080p", "720p"],),
|
||||
"时长": ([5, 10, 15],),
|
||||
@@ -391,6 +396,7 @@ class KlingFirstLastFrame:
|
||||
_, save_path = tempfile.mkstemp(suffix=".mp4", prefix="kling_")
|
||||
|
||||
client = KlingClient()
|
||||
client.base_url = get_base_url_by_route(kwargs.get("网络线路", "全球加速"))
|
||||
|
||||
# 进度条：0~100 步
|
||||
try:
|
||||
@@ -454,6 +460,7 @@ class KlingMotionControlTest:
|
||||
"提示词": ("STRING", {"multiline": True, "default": ""}),
|
||||
"参考图片": ("IMAGE",),
|
||||
"参考视频": ("VIDEO",),
|
||||
"网络线路": (NETWORK_ROUTE_OPTIONS, {"default": "全球加速"}),
|
||||
},
|
||||
"optional": {
|
||||
"模型": (["v3", "v2-6"], {"default": "v3"}),
|
||||
@@ -560,6 +567,7 @@ class KlingMotionControlTest:
|
||||
_, save_path = tempfile.mkstemp(suffix=".mp4", prefix="kling_motion_")
|
||||
|
||||
client = KlingClient()
|
||||
client.base_url = get_base_url_by_route(kwargs.get("网络线路", "全球加速"))
|
||||
|
||||
# ── 进度条 ────────────────────────────────────────────────────
|
||||
try:
|
||||
|
||||
@@ -1,165 +0,0 @@
|
||||
"""
|
||||
多分辨率图像预览节点
|
||||
ComfyUI 自定义节点，支持同时预览多张不同分辨率的图像
|
||||
|
||||
背景：
|
||||
ComfyUI 原生「预览图像」节点要求 batch 内所有图片分辨率相同（因为它们被
|
||||
stack 成一个 [B, H, W, C] tensor）。当 API 返回多张不同尺寸的图片时
|
||||
（例如 nano-banana-2 同时返回 1K + 2K），原生节点会报错。
|
||||
|
||||
解决方案：
|
||||
声明 INPUT_IS_LIST = True，ComfyUI 会将连入的所有图像作为
|
||||
Python list[Tensor] 传入，而不是强行 stack 成单个 tensor。
|
||||
节点逐张单独保存为临时 PNG，再通过 ui.images 列表返回给前端并列展示，
|
||||
完全不受分辨率一致性的限制。
|
||||
"""
|
||||
|
||||
import os
|
||||
import uuid
|
||||
import json
|
||||
import numpy as np
|
||||
from PIL import Image
|
||||
from PIL.PngImagePlugin import PngInfo
|
||||
|
||||
try:
|
||||
import folder_paths
|
||||
FOLDER_PATHS_AVAILABLE = True
|
||||
except ImportError:
|
||||
FOLDER_PATHS_AVAILABLE = False
|
||||
|
||||
|
||||
def _get_temp_dir() -> str:
|
||||
"""获取 ComfyUI temp 目录，不可用时回退到系统临时目录"""
|
||||
if FOLDER_PATHS_AVAILABLE:
|
||||
return folder_paths.get_temp_directory()
|
||||
import tempfile
|
||||
return tempfile.gettempdir()
|
||||
|
||||
|
||||
def _tensor_to_pil(tensor) -> list:
|
||||
"""
|
||||
将单个 IMAGE tensor 转换为 PIL Image 列表。
|
||||
|
||||
ComfyUI IMAGE tensor 格式：[B, H, W, C]，float32，值域 [0, 1]
|
||||
支持：
|
||||
- 单张图 tensor: shape [H, W, C] 或 [1, H, W, C]
|
||||
- batch tensor: shape [B, H, W, C]（B 张相同尺寸图）
|
||||
"""
|
||||
import torch
|
||||
if not isinstance(tensor, torch.Tensor):
|
||||
return []
|
||||
|
||||
if tensor.ndim == 3:
|
||||
tensor = tensor.unsqueeze(0)
|
||||
|
||||
results = []
|
||||
for i in range(tensor.shape[0]):
|
||||
img_np = tensor[i].cpu().numpy()
|
||||
img_np = np.clip(img_np * 255.0, 0, 255).astype(np.uint8)
|
||||
results.append(Image.fromarray(img_np))
|
||||
return results
|
||||
|
||||
|
||||
class MultiResPreview:
|
||||
"""
|
||||
多分辨率图像预览节点
|
||||
|
||||
功能：
|
||||
- 单个「图像」输入端口，支持接入批次图像
|
||||
- INPUT_IS_LIST = True：ComfyUI 将每张图作为独立 tensor 传入，
|
||||
不强制要求尺寸相同，彻底解决不同分辨率无法共存的问题
|
||||
- 每张图像独立保存为临时 PNG，在节点上并列展示所有图像
|
||||
|
||||
用法：
|
||||
将 Nano Banana 节点的输出直接连入「图像」端口即可，
|
||||
无论返回几张、分辨率是否相同，都能正确展示。
|
||||
"""
|
||||
|
||||
@classmethod
|
||||
def INPUT_TYPES(cls):
|
||||
return {
|
||||
"required": {
|
||||
"图像": ("IMAGE",),
|
||||
},
|
||||
"hidden": {
|
||||
"prompt": "PROMPT",
|
||||
"extra_pnginfo": "EXTRA_PNGINFO",
|
||||
},
|
||||
}
|
||||
|
||||
# 关键：告知 ComfyUI 以 list[Tensor] 而非 stacked Tensor 传入图像
|
||||
# 这样不同分辨率的图片可以共存于同一个输入中
|
||||
INPUT_IS_LIST = True
|
||||
|
||||
RETURN_TYPES = ()
|
||||
OUTPUT_NODE = True
|
||||
FUNCTION = "preview"
|
||||
CATEGORY = "image"
|
||||
|
||||
DESCRIPTION = (
|
||||
"多分辨率图像预览节点。\n"
|
||||
"单个图像输入端口，支持任意数量、任意分辨率的批次图像。\n"
|
||||
"解决了原生「预览图像」节点要求 batch 内图片尺寸相同的限制。\n"
|
||||
"常用场景：nano-banana-2 同时返回 1K + 2K 图时，直接连入本节点即可。"
|
||||
)
|
||||
|
||||
def preview(self, 图像, prompt=None, extra_pnginfo=None) -> dict:
|
||||
"""
|
||||
逐张将图像保存到 temp 目录，返回 ui.images 供前端展示。
|
||||
|
||||
Args:
|
||||
图像: list[Tensor]，每个元素是一张或一批图（INPUT_IS_LIST）
|
||||
prompt: ComfyUI 注入的 prompt 元数据（可选）
|
||||
extra_pnginfo: ComfyUI 注入的额外 PNG 信息（可选）
|
||||
|
||||
Returns:
|
||||
{"ui": {"images": [...]}} 格式，每项对应一张图
|
||||
"""
|
||||
temp_dir = _get_temp_dir()
|
||||
os.makedirs(temp_dir, exist_ok=True)
|
||||
|
||||
# 构建 PNG 元数据（与原生预览节点行为一致）
|
||||
metadata = PngInfo()
|
||||
# INPUT_IS_LIST 时 hidden 值也会被包装成 list，取第一个元素
|
||||
_prompt = prompt[0] if isinstance(prompt, list) else prompt
|
||||
_extra = extra_pnginfo[0] if isinstance(extra_pnginfo, list) else extra_pnginfo
|
||||
if _prompt is not None:
|
||||
try:
|
||||
metadata.add_text("prompt", json.dumps(_prompt))
|
||||
except Exception:
|
||||
pass
|
||||
if _extra is not None:
|
||||
try:
|
||||
for k, v in _extra.items():
|
||||
metadata.add_text(k, json.dumps(v))
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
saved = []
|
||||
total_input = 0
|
||||
total_saved = 0
|
||||
|
||||
# 图像 是 list[Tensor]，逐个处理（每个 Tensor 可能自身是个 batch）
|
||||
for tensor in 图像:
|
||||
pil_images = _tensor_to_pil(tensor)
|
||||
total_input += len(pil_images)
|
||||
|
||||
for pil_img in pil_images:
|
||||
try:
|
||||
filename = f"multi_res_preview_{uuid.uuid4().hex[:12]}.png"
|
||||
filepath = os.path.join(temp_dir, filename)
|
||||
pil_img.save(filepath, pnginfo=metadata, compress_level=1)
|
||||
|
||||
saved.append({
|
||||
"filename": filename,
|
||||
"subfolder": "",
|
||||
"type": "temp",
|
||||
})
|
||||
total_saved += 1
|
||||
except Exception as e:
|
||||
print(f"多分辨率预览: ⚠️ 保存图像失败 - {e}")
|
||||
|
||||
if total_input == 0:
|
||||
print("多分辨率预览: ⚠️ 没有接收到任何图像")
|
||||
|
||||
return {"ui": {"images": saved}}
|
||||
@@ -0,0 +1,636 @@
|
||||
"""
|
||||
Nano Banana 节点 (V3)
|
||||
ComfyUI 自定义节点，用于调用生图模型（OpenAI 兼容接口）
|
||||
使用 V3 DynamicCombo 实现模型-宽高比-分辨率动态联动
|
||||
"""
|
||||
|
||||
import io as _io
|
||||
import re
|
||||
import json
|
||||
import time
|
||||
import math
|
||||
import base64
|
||||
import random
|
||||
import asyncio
|
||||
import aiohttp
|
||||
from concurrent.futures import ThreadPoolExecutor
|
||||
from typing import List, Optional
|
||||
|
||||
import torch
|
||||
import numpy as np
|
||||
from PIL import Image
|
||||
|
||||
from comfy_api.latest import io
|
||||
|
||||
from ..utils.image_utils import tensor_to_pil, pil_to_tensor, parse_batch_prompts, encode_image_to_base64, encode_image_to_base64_limited
|
||||
from ..utils.config import (
|
||||
NETWORK_ROUTE_OPTIONS,
|
||||
get_base_url_by_route,
|
||||
get_api_key_or_raise,
|
||||
)
|
||||
from ..utils.http_error import RETRYABLE_STATUS_CODES, HTTP_ERROR_MESSAGES, _compute_delay, DEFAULT_MAX_RETRIES, DEFAULT_BASE_DELAY, DEFAULT_MAX_DELAY, DEFAULT_BACKOFF_FACTOR
|
||||
from ..clients.gemini_client import GeminiAPIClient
|
||||
|
||||
try:
|
||||
import folder_paths
|
||||
FOLDER_PATHS_AVAILABLE = True
|
||||
except ImportError:
|
||||
FOLDER_PATHS_AVAILABLE = False
|
||||
|
||||
try:
|
||||
from comfy.utils import ProgressBar
|
||||
PROGRESS_BAR_AVAILABLE = True
|
||||
except ImportError:
|
||||
PROGRESS_BAR_AVAILABLE = False
|
||||
|
||||
try:
|
||||
import psutil
|
||||
MEMORY_MONITOR_AVAILABLE = True
|
||||
except ImportError:
|
||||
MEMORY_MONITOR_AVAILABLE = False
|
||||
|
||||
DEBUG_LOG_ENABLED = True
|
||||
REQUEST_LOG_ENABLED = False
|
||||
|
||||
_NODE = "Nano Banana"
|
||||
_ENDPOINT = "/v1/chat/completions"
|
||||
|
||||
_client_instance = None
|
||||
|
||||
|
||||
def _get_client():
|
||||
global _client_instance
|
||||
if _client_instance is None:
|
||||
_client_instance = GeminiAPIClient()
|
||||
return _client_instance
|
||||
|
||||
|
||||
def _images_to_tensor_safe(images: List[Image.Image], node_label: str) -> torch.Tensor:
|
||||
if not images:
|
||||
placeholder = Image.new('RGB', (512, 512), color=(128, 128, 128))
|
||||
return pil_to_tensor([placeholder])
|
||||
|
||||
base_size = max(images, key=lambda img: img.size[0] * img.size[1]).size
|
||||
matched = [img for img in images if img.size == base_size]
|
||||
skipped = [img for img in images if img.size != base_size]
|
||||
|
||||
if skipped:
|
||||
sizes_str = ", ".join(f"{img.size[0]}x{img.size[1]}" for img in skipped)
|
||||
print(
|
||||
f"{node_label}: 丢弃 {len(skipped)} 张较小尺寸的图 ({sizes_str})，"
|
||||
f"仅输出最大尺寸 {base_size[0]}x{base_size[1]} 的 {len(matched)} 张"
|
||||
)
|
||||
|
||||
return pil_to_tensor(matched)
|
||||
|
||||
|
||||
MODEL_ID_MAP = {
|
||||
"Nano Banana Pro": "nano-banana-pro",
|
||||
"Nano Banana 2": "nano-banana-2",
|
||||
"Nano Banana": "nano-banana",
|
||||
}
|
||||
RESOLUTION_KEY_MAP = {
|
||||
"512px": "0.5k",
|
||||
"1K": "1k",
|
||||
"2K": "2k",
|
||||
"4K": "4k",
|
||||
}
|
||||
BILLING_SPECIAL_ONLY = {"nano-banana"}
|
||||
|
||||
|
||||
def _build_model_id(model_name: str, resolution: str, billing: str) -> str:
|
||||
base = MODEL_ID_MAP.get(model_name, "nano-banana-pro")
|
||||
|
||||
if base == "nano-banana":
|
||||
if billing == "官方":
|
||||
raise ValueError(f"模型 \"{model_name}\" 仅支持特价计费")
|
||||
return "nano-banana"
|
||||
|
||||
res_key = RESOLUTION_KEY_MAP.get(resolution, "2k")
|
||||
is_official = (billing == "官方")
|
||||
|
||||
if base == "nano-banana-pro" and res_key == "1k" and not is_official:
|
||||
return "nano-banana-pro"
|
||||
|
||||
if base == "nano-banana-2" and res_key == "0.5k":
|
||||
if is_official:
|
||||
raise ValueError("Nano Banana 2 的 512px 分辨率仅支持特价计费")
|
||||
return "nano-banana-2-0.5k"
|
||||
|
||||
model_id = f"{base}-{res_key}"
|
||||
if is_official:
|
||||
model_id += "-official"
|
||||
return model_id
|
||||
|
||||
_IMAGE_RE = re.compile(r"!\[.*?\]\(data:image/(\w+);base64,([A-Za-z0-9+/=]+)\)")
|
||||
|
||||
|
||||
def _get_headers(api_key: str) -> dict:
|
||||
return {
|
||||
"Authorization": f"Bearer {api_key}",
|
||||
"Content-Type": "application/json",
|
||||
"X-Accel-Buffering": "no",
|
||||
"Cache-Control": "no-cache, no-transform",
|
||||
}
|
||||
|
||||
|
||||
def _build_request_body(
|
||||
prompt: str,
|
||||
model: str,
|
||||
aspect_ratio: str,
|
||||
resolution: str,
|
||||
images: Optional[List[Image.Image]] = None,
|
||||
enable_grounding: bool = False,
|
||||
thinking_level: Optional[str] = None,
|
||||
) -> dict:
|
||||
content_parts = [{"type": "text", "text": prompt}]
|
||||
|
||||
if images:
|
||||
for img in images:
|
||||
b64 = encode_image_to_base64_limited(img, format="PNG")
|
||||
content_parts.append({
|
||||
"type": "image_url",
|
||||
"image_url": {"url": f"data:image/png;base64,{b64}"}
|
||||
})
|
||||
|
||||
body = {
|
||||
"model": model,
|
||||
"stream": True,
|
||||
"messages": [{"role": "user", "content": content_parts}],
|
||||
}
|
||||
|
||||
google_config = {
|
||||
"image_config": {
|
||||
"image_size": resolution,
|
||||
}
|
||||
}
|
||||
if aspect_ratio and aspect_ratio != "智能":
|
||||
google_config["image_config"]["aspect_ratio"] = aspect_ratio
|
||||
if thinking_level:
|
||||
google_config["thinking_config"] = {
|
||||
"thinking_level": thinking_level.lower(),
|
||||
"include_thoughts": True,
|
||||
}
|
||||
body["extra_body"] = {"google": google_config}
|
||||
|
||||
if enable_grounding:
|
||||
body["extra_body"]["google_search"] = True
|
||||
|
||||
return body
|
||||
|
||||
|
||||
async def _generate_single(
|
||||
session: aiohttp.ClientSession,
|
||||
base_url: str,
|
||||
api_key: str,
|
||||
prompt: str,
|
||||
model: str,
|
||||
resolution: str,
|
||||
aspect_ratio: str,
|
||||
images: Optional[List[Image.Image]] = None,
|
||||
enable_grounding: bool = False,
|
||||
thinking_level: Optional[str] = None,
|
||||
) -> List[Image.Image]:
|
||||
url = f"{base_url}{_ENDPOINT}"
|
||||
headers = _get_headers(api_key)
|
||||
body = _build_request_body(
|
||||
prompt=prompt,
|
||||
model=model,
|
||||
aspect_ratio=aspect_ratio,
|
||||
resolution=resolution,
|
||||
images=images,
|
||||
enable_grounding=enable_grounding,
|
||||
thinking_level=thinking_level,
|
||||
)
|
||||
|
||||
if REQUEST_LOG_ENABLED:
|
||||
extra = json.dumps(body.get("extra_body", {}), ensure_ascii=False)
|
||||
print(f"[请求] POST {url} | model={model} | extra_body={extra}")
|
||||
|
||||
last_status = None
|
||||
for attempt in range(DEFAULT_MAX_RETRIES + 1):
|
||||
resp = await session.post(url, headers=headers, json=body)
|
||||
if resp.status == 200:
|
||||
break
|
||||
last_status = resp.status
|
||||
if resp.status in RETRYABLE_STATUS_CODES and attempt < DEFAULT_MAX_RETRIES:
|
||||
friendly = HTTP_ERROR_MESSAGES.get(resp.status, f"请求失败 ({resp.status})")
|
||||
delay = _compute_delay(attempt, DEFAULT_BASE_DELAY, DEFAULT_MAX_DELAY, DEFAULT_BACKOFF_FACTOR)
|
||||
print(f"Nano Banana: {friendly} {delay:.1f}s 后重试 ({attempt+1}/{DEFAULT_MAX_RETRIES})...")
|
||||
resp.close()
|
||||
await asyncio.sleep(delay)
|
||||
continue
|
||||
error_text = await resp.text()
|
||||
resp.close()
|
||||
if resp.status in HTTP_ERROR_MESSAGES:
|
||||
raise RuntimeError(HTTP_ERROR_MESSAGES[resp.status])
|
||||
try:
|
||||
err_json = json.loads(error_text)
|
||||
msg = err_json.get("error", {}).get("message", error_text[:200])
|
||||
except Exception:
|
||||
msg = error_text[:200]
|
||||
raise RuntimeError(f"API 错误 ({resp.status}): {msg}")
|
||||
else:
|
||||
if last_status and last_status in HTTP_ERROR_MESSAGES:
|
||||
raise RuntimeError(HTTP_ERROR_MESSAGES[last_status])
|
||||
raise RuntimeError(f"API 错误: 重试 {DEFAULT_MAX_RETRIES} 次后仍然失败")
|
||||
|
||||
full_content = ""
|
||||
buffer = ""
|
||||
t_request = time.time()
|
||||
t_first_token = None
|
||||
async for raw_chunk in resp.content.iter_any():
|
||||
if t_first_token is None:
|
||||
t_first_token = time.time()
|
||||
buffer += raw_chunk.decode("utf-8")
|
||||
while "\n" in buffer:
|
||||
line_str, buffer = buffer.split("\n", 1)
|
||||
line_str = line_str.strip()
|
||||
if not line_str or not line_str.startswith("data:"):
|
||||
continue
|
||||
data_str = line_str[5:].strip()
|
||||
if data_str == "[DONE]":
|
||||
break
|
||||
try:
|
||||
chunk = json.loads(data_str)
|
||||
delta = chunk.get("choices", [{}])[0].get("delta", {})
|
||||
if "content" in delta:
|
||||
full_content += delta["content"]
|
||||
except (json.JSONDecodeError, IndexError):
|
||||
continue
|
||||
t_done = time.time()
|
||||
resp.close()
|
||||
|
||||
if not full_content:
|
||||
raise RuntimeError("API 未返回有效内容")
|
||||
|
||||
# 思考模型可能输出多张临时图片，最终图片始终是最后一张
|
||||
matches = list(_IMAGE_RE.finditer(full_content))
|
||||
if not matches:
|
||||
raise RuntimeError(f"响应中未找到图片: {full_content[:100]}")
|
||||
|
||||
last_match = matches[-1]
|
||||
img_data = base64.b64decode(last_match.group(2))
|
||||
final_image = Image.open(_io.BytesIO(img_data)).convert("RGB")
|
||||
|
||||
first_token_ms = (t_first_token - t_request) * 1000 if t_first_token else 0
|
||||
download_ms = (t_done - t_first_token) * 1000 if t_first_token else 0
|
||||
|
||||
return [final_image], first_token_ms, download_ms
|
||||
|
||||
|
||||
async def _generate_single_task(
|
||||
session: aiohttp.ClientSession,
|
||||
base_url: str,
|
||||
api_key: str,
|
||||
prompt: str,
|
||||
model: str,
|
||||
resolution: str,
|
||||
aspect_ratio: str,
|
||||
images: Optional[List[Image.Image]],
|
||||
global_task_index: int,
|
||||
enable_grounding: bool = False,
|
||||
thinking_level: Optional[str] = None,
|
||||
) -> dict:
|
||||
result = {
|
||||
"global_task_index": global_task_index,
|
||||
"prompt": prompt,
|
||||
"success": False,
|
||||
"generated_count": 0,
|
||||
"output_images": [],
|
||||
"error": None,
|
||||
}
|
||||
try:
|
||||
gen_images, first_token_ms, download_ms = await _generate_single(
|
||||
session=session,
|
||||
base_url=base_url,
|
||||
api_key=api_key,
|
||||
prompt=prompt,
|
||||
model=model,
|
||||
resolution=resolution,
|
||||
aspect_ratio=aspect_ratio,
|
||||
images=images if images else None,
|
||||
enable_grounding=enable_grounding,
|
||||
thinking_level=thinking_level,
|
||||
)
|
||||
result["output_images"] = gen_images
|
||||
result["success"] = True
|
||||
result["generated_count"] = len(gen_images)
|
||||
except Exception as e:
|
||||
result["error"] = str(e)
|
||||
return result
|
||||
|
||||
|
||||
async def _process_batch_async(
|
||||
base_url: str,
|
||||
api_key: str,
|
||||
prompts: List[str],
|
||||
model: str,
|
||||
resolution: str,
|
||||
aspect_ratio: str,
|
||||
images_per_prompt: int,
|
||||
input_images: Optional[List[Image.Image]],
|
||||
pbar=None,
|
||||
enable_grounding: bool = False,
|
||||
thinking_level: Optional[str] = None,
|
||||
) -> List[dict]:
|
||||
tasks_def = []
|
||||
for p_idx, prompt in enumerate(prompts):
|
||||
for sub_idx in range(images_per_prompt):
|
||||
tasks_def.append((p_idx, sub_idx, prompt))
|
||||
|
||||
total_tasks = len(tasks_def)
|
||||
max_concurrent = 50
|
||||
num_batches = math.ceil(total_tasks / max_concurrent)
|
||||
|
||||
all_results = []
|
||||
completed = 0
|
||||
success_count = 0
|
||||
fail_count = 0
|
||||
|
||||
connector = aiohttp.TCPConnector(ssl=False, limit=0, limit_per_host=0)
|
||||
|
||||
async with aiohttp.ClientSession(connector=connector) as session:
|
||||
for batch_idx in range(num_batches):
|
||||
start_idx = batch_idx * max_concurrent
|
||||
end_idx = min(start_idx + max_concurrent, total_tasks)
|
||||
|
||||
tasks = []
|
||||
for i in range(start_idx, end_idx):
|
||||
_, _, prompt = tasks_def[i]
|
||||
task = asyncio.create_task(
|
||||
_generate_single_task(
|
||||
session=session,
|
||||
base_url=base_url,
|
||||
api_key=api_key,
|
||||
prompt=prompt,
|
||||
model=model,
|
||||
resolution=resolution,
|
||||
aspect_ratio=aspect_ratio,
|
||||
images=input_images,
|
||||
global_task_index=i,
|
||||
enable_grounding=enable_grounding,
|
||||
thinking_level=thinking_level,
|
||||
)
|
||||
)
|
||||
tasks.append(task)
|
||||
|
||||
batch_results = []
|
||||
for coro in asyncio.as_completed(tasks):
|
||||
result_data = None
|
||||
try:
|
||||
result = await coro
|
||||
if isinstance(result, Exception):
|
||||
result_data = {"success": False, "error": str(result), "generated_count": 0, "output_images": [], "prompt": ""}
|
||||
else:
|
||||
result_data = result
|
||||
except Exception as e:
|
||||
result_data = {"success": False, "error": str(e), "generated_count": 0, "output_images": [], "prompt": ""}
|
||||
|
||||
batch_results.append(result_data)
|
||||
completed += 1
|
||||
prompt_snippet = (result_data.get("prompt", "") or "")[:30]
|
||||
|
||||
if result_data and result_data.get("success", False):
|
||||
success_count += 1
|
||||
count = result_data.get("generated_count", 1)
|
||||
print(f"Nano Banana: [{completed}/{total_tasks}] {prompt_snippet}{'...' if len(prompt_snippet) >= 30 else ''} → ✓成功({count}张)")
|
||||
else:
|
||||
fail_count += 1
|
||||
error_msg = result_data.get("error", "未知错误") if result_data else "未知错误"
|
||||
print(f"Nano Banana: [{completed}/{total_tasks}] {prompt_snippet}{'...' if len(prompt_snippet) >= 30 else ''} → ✗失败: {error_msg}")
|
||||
|
||||
if pbar is not None:
|
||||
pbar.update(1)
|
||||
|
||||
all_results.extend(batch_results)
|
||||
import gc; gc.collect()
|
||||
await asyncio.sleep(0.1)
|
||||
|
||||
return all_results
|
||||
|
||||
|
||||
class NanoBanana(io.ComfyNode):
|
||||
|
||||
@classmethod
|
||||
def define_schema(cls):
|
||||
return io.Schema(
|
||||
node_id="NanoBanana",
|
||||
display_name="Nano Banana",
|
||||
category="image/generation",
|
||||
inputs=[
|
||||
io.String.Input(
|
||||
"prompt",
|
||||
default="一个中国女子的OOTD",
|
||||
multiline=True,
|
||||
),
|
||||
io.DynamicCombo.Input("模型", options=[
|
||||
io.DynamicCombo.Option("Nano Banana Pro", [
|
||||
io.Combo.Input("宽高比", options=[
|
||||
"智能", "1:1", "2:3", "3:2", "3:4", "4:3",
|
||||
"4:5", "5:4", "9:16", "16:9", "21:9",
|
||||
], default="智能"),
|
||||
io.Combo.Input("分辨率", options=["1K", "2K", "4K"], default="2K"),
|
||||
]),
|
||||
io.DynamicCombo.Option("Nano Banana 2", [
|
||||
io.Combo.Input("宽高比", options=[
|
||||
"智能", "1:1", "1:4", "1:8", "2:3", "3:2", "3:4",
|
||||
"4:1", "4:3", "4:5", "5:4", "8:1",
|
||||
"9:16", "16:9", "21:9",
|
||||
], default="智能"),
|
||||
io.Combo.Input("分辨率", options=["512px", "1K", "2K", "4K"], default="2K"),
|
||||
io.Combo.Input("思考深度", options=["高", "低"], default="高"),
|
||||
]),
|
||||
io.DynamicCombo.Option("Nano Banana", [
|
||||
io.Combo.Input("宽高比", options=[
|
||||
"智能", "1:1", "2:3", "3:2", "3:4", "4:3",
|
||||
"4:5", "5:4", "9:16", "16:9", "21:9",
|
||||
], default="智能"),
|
||||
io.Combo.Input("分辨率", options=["1K"], default="1K"),
|
||||
]),
|
||||
]),
|
||||
io.Int.Input("生图数量", default=1, min=1, max=1000, step=1),
|
||||
io.Combo.Input("网络", options=NETWORK_ROUTE_OPTIONS, default="全球加速"),
|
||||
io.Combo.Input("计费", options=["特价", "官方"], default="特价"),
|
||||
io.Combo.Input("谷歌搜索", options=["关闭", "打开"], default="关闭"),
|
||||
io.Int.Input("seed", default=0, min=0, max=0xFFFFFFFFFFFFFFFF),
|
||||
io.Image.Input("参考图1", optional=True),
|
||||
io.Image.Input("参考图2", optional=True),
|
||||
io.Image.Input("参考图3", optional=True),
|
||||
io.Image.Input("参考图4", optional=True),
|
||||
io.Image.Input("参考图5", optional=True),
|
||||
io.Image.Input("参考图6", optional=True),
|
||||
io.Image.Input("参考图7", optional=True),
|
||||
io.Image.Input("参考图8", optional=True),
|
||||
io.Image.Input("参考图9", optional=True),
|
||||
],
|
||||
outputs=[
|
||||
io.Image.Output(display_name="输出图像"),
|
||||
],
|
||||
)
|
||||
|
||||
@classmethod
|
||||
def execute(cls, prompt, 模型, 生图数量, 计费, 网络, 谷歌搜索, seed, **kwargs) -> io.NodeOutput:
|
||||
start_time = time.time()
|
||||
|
||||
model_name = 模型["模型"]
|
||||
宽高比 = 模型["宽高比"]
|
||||
分辨率 = 模型["分辨率"]
|
||||
思考深度 = 模型.get("思考深度")
|
||||
|
||||
enable_grounding = (谷歌搜索 == "打开")
|
||||
|
||||
thinking_level = None
|
||||
if model_name == "Nano Banana 2" and 思考深度:
|
||||
thinking_level = "High" if 思考深度 == "高" else "Low"
|
||||
|
||||
actual_model = _build_model_id(model_name, 分辨率, 计费)
|
||||
|
||||
api_key = get_api_key_or_raise("O1KEY_API_KEY")
|
||||
base_url = get_base_url_by_route(网络)
|
||||
|
||||
pbar = ProgressBar(生图数量) if PROGRESS_BAR_AVAILABLE else None
|
||||
|
||||
try:
|
||||
random.seed(seed)
|
||||
np.random.seed(seed % (2**32))
|
||||
|
||||
input_images = []
|
||||
for i in range(1, 10):
|
||||
key = f"参考图{i}"
|
||||
if key in kwargs and kwargs[key] is not None:
|
||||
pil_imgs = tensor_to_pil(kwargs[key])
|
||||
input_images.extend(pil_imgs)
|
||||
|
||||
if input_images and len(input_images) > 14:
|
||||
raise ValueError(f"输入图像数量 {len(input_images)} 超过限制 14 张")
|
||||
|
||||
batch_prompts = parse_batch_prompts(prompt)
|
||||
|
||||
grounding_str = " | 谷歌搜索接地" if enable_grounding else ""
|
||||
thinking_str = f" | 思考:{thinking_level}" if thinking_level else ""
|
||||
if batch_prompts:
|
||||
num_prompts = len(batch_prompts)
|
||||
total_images = num_prompts * 生图数量
|
||||
mode_str = f"批量提示词模式 ({num_prompts}个提示词)"
|
||||
if input_images:
|
||||
mode_str += f" (输入{len(input_images)}张)"
|
||||
print(f"Nano Banana: {mode_str} | {分辨率} {宽高比} | 共{total_images}张{grounding_str}{thinking_str}")
|
||||
else:
|
||||
mode_str = f"图生图模式 (输入{len(input_images)}张)" if input_images else "文生图模式"
|
||||
print(f"Nano Banana: {mode_str} | {分辨率} {宽高比} | {生图数量}张{grounding_str}{thinking_str}")
|
||||
|
||||
if batch_prompts or 生图数量 > 1:
|
||||
prompts = batch_prompts if batch_prompts else [prompt]
|
||||
images_per_prompt = 生图数量
|
||||
total_tasks = len(prompts) * images_per_prompt
|
||||
|
||||
if pbar is not None:
|
||||
pbar = ProgressBar(total_tasks)
|
||||
|
||||
def run_async_in_thread():
|
||||
loop = asyncio.new_event_loop()
|
||||
asyncio.set_event_loop(loop)
|
||||
try:
|
||||
return loop.run_until_complete(
|
||||
_process_batch_async(
|
||||
base_url=base_url,
|
||||
api_key=api_key,
|
||||
prompts=prompts,
|
||||
model=actual_model,
|
||||
resolution=分辨率,
|
||||
aspect_ratio=宽高比,
|
||||
images_per_prompt=images_per_prompt,
|
||||
input_images=input_images,
|
||||
pbar=pbar,
|
||||
enable_grounding=enable_grounding,
|
||||
thinking_level=thinking_level,
|
||||
)
|
||||
)
|
||||
finally:
|
||||
loop.close()
|
||||
|
||||
with ThreadPoolExecutor(max_workers=1) as executor:
|
||||
future = executor.submit(run_async_in_thread)
|
||||
try:
|
||||
results = future.result(timeout=900)
|
||||
except TimeoutError:
|
||||
raise RuntimeError("任务执行超时（900秒）")
|
||||
|
||||
success_count = sum(1 for r in results if r.get("success", False))
|
||||
fail_count = len(results) - success_count
|
||||
elapsed = time.time() - start_time
|
||||
time_str = f"{elapsed:.3f}s" if elapsed < 1 else f"{elapsed:.2f}s"
|
||||
print(f"完成！总耗时 {time_str} | 成功: {success_count}/{total_tasks} | 失败: {fail_count}")
|
||||
|
||||
output_images = []
|
||||
for r in results:
|
||||
output_images.extend(r.get("output_images", []))
|
||||
if not output_images:
|
||||
placeholder = Image.new('RGB', (512, 512), color=(128, 128, 128))
|
||||
output_images = [placeholder]
|
||||
|
||||
output_tensor = _images_to_tensor_safe(output_images, _NODE)
|
||||
import gc; gc.collect()
|
||||
return io.NodeOutput(output_tensor)
|
||||
|
||||
else:
|
||||
def run_single():
|
||||
loop = asyncio.new_event_loop()
|
||||
asyncio.set_event_loop(loop)
|
||||
try:
|
||||
async def _do():
|
||||
connector = aiohttp.TCPConnector(ssl=False)
|
||||
async with aiohttp.ClientSession(connector=connector) as session:
|
||||
return await _generate_single(
|
||||
session=session,
|
||||
base_url=base_url,
|
||||
api_key=api_key,
|
||||
prompt=prompt,
|
||||
model=actual_model,
|
||||
resolution=分辨率,
|
||||
aspect_ratio=宽高比,
|
||||
images=input_images if input_images else None,
|
||||
enable_grounding=enable_grounding,
|
||||
thinking_level=thinking_level,
|
||||
)
|
||||
return loop.run_until_complete(_do())
|
||||
finally:
|
||||
loop.close()
|
||||
|
||||
with ThreadPoolExecutor(max_workers=1) as executor:
|
||||
future = executor.submit(run_single)
|
||||
generated_images, first_token_ms, download_ms = future.result(timeout=900)
|
||||
|
||||
if pbar is not None:
|
||||
pbar.update(1)
|
||||
|
||||
output_tensor = _images_to_tensor_safe(generated_images, _NODE)
|
||||
elapsed = time.time() - start_time
|
||||
time_str = f"{elapsed:.3f}s" if elapsed < 1 else f"{elapsed:.2f}s"
|
||||
ft_str = f"{first_token_ms/1000:.2f}s"
|
||||
dl_str = f"{download_ms/1000:.2f}s"
|
||||
print(f"完成！总耗时 {time_str} | 首字 {ft_str} | 下载 {dl_str} | 成功 {len(generated_images)}张")
|
||||
|
||||
import gc; gc.collect()
|
||||
return io.NodeOutput(output_tensor)
|
||||
|
||||
except ValueError as e:
|
||||
if str(e) == "未授权！":
|
||||
print("请联系作者授权后方可使用！")
|
||||
raise ValueError("未授权！") from None
|
||||
raise ValueError(str(e)) from None
|
||||
except RuntimeError as e:
|
||||
raise RuntimeError(str(e)) from None
|
||||
except Exception as e:
|
||||
raise type(e)(str(e)) from None
|
||||
finally:
|
||||
try:
|
||||
client = _get_client()
|
||||
client.base_url = base_url
|
||||
balance_data = client.query_balance_sync()
|
||||
balance_info = client.format_balance_info(balance_data)
|
||||
print(f"Nano Banana: {balance_info}")
|
||||
except Exception:
|
||||
pass
|
||||
import gc; gc.collect()
|
||||
@@ -1,831 +0,0 @@
|
||||
"""
|
||||
Nano Banana Pro 节点
|
||||
ComfyUI 自定义节点，用于调用 Gemini 模型生成图像
|
||||
"""
|
||||
|
||||
import time
|
||||
import math
|
||||
import random
|
||||
import asyncio
|
||||
import aiohttp
|
||||
from concurrent.futures import ThreadPoolExecutor
|
||||
from typing import Optional, Tuple, List
|
||||
|
||||
import torch
|
||||
import numpy as np
|
||||
from PIL import Image
|
||||
|
||||
from ..utils.image_utils import tensor_to_pil, pil_to_tensor, parse_batch_prompts
|
||||
from ..utils.file_utils import ImageInfo, generate_timestamp_filename, save_image
|
||||
from ..clients.gemini_client import GeminiAPIClient
|
||||
from ..models_config import (
|
||||
get_enabled_models, get_model_description,
|
||||
get_model_supported_aspect_ratios, get_all_supported_aspect_ratios,
|
||||
get_model_supported_resolutions, get_all_supported_resolutions
|
||||
)
|
||||
|
||||
# 检查 folder_paths 是否可用
|
||||
try:
|
||||
import folder_paths
|
||||
FOLDER_PATHS_AVAILABLE = True
|
||||
except ImportError:
|
||||
FOLDER_PATHS_AVAILABLE = False
|
||||
|
||||
# 导入 ComfyUI 原生进度条
|
||||
try:
|
||||
from comfy.utils import ProgressBar
|
||||
PROGRESS_BAR_AVAILABLE = True
|
||||
except ImportError:
|
||||
PROGRESS_BAR_AVAILABLE = False
|
||||
print("⚠️ NanoBananaPro: comfy.utils.ProgressBar 不可用，将只使用终端进度显示")
|
||||
|
||||
# 内存监控（可选）
|
||||
try:
|
||||
import psutil
|
||||
MEMORY_MONITOR_AVAILABLE = True
|
||||
except ImportError:
|
||||
MEMORY_MONITOR_AVAILABLE = False
|
||||
print("⚠️ NanoBananaPro: psutil 不可用，内存监控功能禁用")
|
||||
|
||||
# ============================================================================
|
||||
# 调试日志配置
|
||||
# ============================================================================
|
||||
# 是否启用调试日志（打印完整的 API 响应内容）
|
||||
# 设置为 True 以启用调试日志，False 以禁用
|
||||
DEBUG_LOG_ENABLED = True
|
||||
# 是否启用请求体日志（打印发送给 API 的请求体，base64 图片数据将自动截断）
|
||||
# 设置为 True 以启用请求体日志，False 以禁用
|
||||
REQUEST_LOG_ENABLED = True
|
||||
# ============================================================================
|
||||
|
||||
_NODE = "Nano Banana Pro"
|
||||
|
||||
|
||||
def _images_to_tensor_safe(images: List[Image.Image], node_label: str) -> torch.Tensor:
|
||||
"""
|
||||
将 PIL Image 列表转换为 ComfyUI tensor，安全处理多张不同尺寸的情况。
|
||||
|
||||
策略：
|
||||
- 以像素数最大的图尺寸为基准
|
||||
- 只输出与最大尺寸相同的图，其余较小的图丢弃
|
||||
"""
|
||||
if not images:
|
||||
placeholder = Image.new('RGB', (512, 512), color=(128, 128, 128))
|
||||
return pil_to_tensor([placeholder])
|
||||
|
||||
base_size = max(images, key=lambda img: img.size[0] * img.size[1]).size
|
||||
matched = [img for img in images if img.size == base_size]
|
||||
skipped = [img for img in images if img.size != base_size]
|
||||
|
||||
if skipped:
|
||||
sizes_str = ", ".join(f"{img.size[0]}×{img.size[1]}" for img in skipped)
|
||||
print(
|
||||
f"{node_label}: 丢弃 {len(skipped)} 张较小尺寸的图 ({sizes_str})，"
|
||||
f"仅输出最大尺寸 {base_size[0]}×{base_size[1]} 的 {len(matched)} 张"
|
||||
)
|
||||
|
||||
return pil_to_tensor(matched)
|
||||
|
||||
|
||||
class NanoBananaPro:
|
||||
"""
|
||||
Nano Banana Pro 节点
|
||||
|
||||
功能：
|
||||
- 文生图：基于提示词生成图像
|
||||
- 图生图：基于输入图像和提示词生成新图像
|
||||
- 批量生成：支持并发生成多张图像
|
||||
|
||||
注意：
|
||||
- 支持的模型列表从 models_config.py 动态加载
|
||||
- 要添加/禁用模型，请编辑 models_config.py 文件
|
||||
"""
|
||||
|
||||
# 支持的模型列表（从配置文件动态加载）
|
||||
MODELS = None # 将在 INPUT_TYPES 中动态获取
|
||||
|
||||
# 支持的宽高比列表（全量：所有启用模型的并集，动态加载）
|
||||
# 实际渲染时通过 get_all_supported_aspect_ratios() 获取
|
||||
ASPECT_RATIOS = [
|
||||
"1:1", "4:3", "3:4", "16:9", "9:16",
|
||||
"2:3", "3:2", "4:5", "5:4", "21:9",
|
||||
"1:4", "4:1", "1:8", "8:1"
|
||||
]
|
||||
|
||||
# 支持的分辨率列表（全量兜底，实际由 get_all_supported_resolutions() 动态生成）
|
||||
RESOLUTIONS = ["512px", "1K", "2K", "4K"]
|
||||
|
||||
def __init__(self):
|
||||
"""初始化节点"""
|
||||
self.client = None
|
||||
|
||||
@classmethod
|
||||
def INPUT_TYPES(cls):
|
||||
"""
|
||||
定义输入参数
|
||||
|
||||
ComfyUI 节点规范：
|
||||
- required: 必选参数
|
||||
- optional: 可选参数
|
||||
"""
|
||||
# 从配置文件动态获取启用的模型列表
|
||||
enabled_models = get_enabled_models()
|
||||
|
||||
# 如果没有启用的模型，使用空列表（会导致节点不可用，提示用户配置）
|
||||
if not enabled_models:
|
||||
enabled_models = ["请在 models_config.py 中启用至少一个模型"]
|
||||
|
||||
# 动态获取所有启用模型支持的宽高比（去重合并）
|
||||
all_aspect_ratios = get_all_supported_aspect_ratios()
|
||||
if not all_aspect_ratios:
|
||||
all_aspect_ratios = cls.ASPECT_RATIOS
|
||||
|
||||
# 动态获取所有启用模型支持的分辨率（去重合并）
|
||||
all_resolutions = get_all_supported_resolutions()
|
||||
if not all_resolutions:
|
||||
all_resolutions = cls.RESOLUTIONS
|
||||
|
||||
# 创建9个独立的图像输入
|
||||
optional_inputs = {}
|
||||
for i in range(1, 10): # 1-9
|
||||
optional_inputs[f"参考图{i}"] = ("IMAGE",)
|
||||
|
||||
optional_inputs["代理端口（如7897）"] = ("STRING", {
|
||||
"default": "",
|
||||
"multiline": False,
|
||||
"placeholder": "本地代理端口，如 7897（Clash Verge）或 10808（v2rayN），留空不使用"
|
||||
})
|
||||
|
||||
return {
|
||||
"required": {
|
||||
"prompt": ("STRING", {
|
||||
"default": "一个中国女子的OOTD",
|
||||
"multiline": True
|
||||
}),
|
||||
"模型": (enabled_models, {
|
||||
"default": enabled_models[0]
|
||||
}),
|
||||
"宽高比": (all_aspect_ratios, {
|
||||
"default": "1:1"
|
||||
}),
|
||||
"分辨率": (all_resolutions, {
|
||||
"default": "2K"
|
||||
}),
|
||||
"生图数量": ("INT", {
|
||||
"default": 1,
|
||||
"min": 1,
|
||||
"max": 1000,
|
||||
"step": 1
|
||||
}),
|
||||
"谷歌搜索（联网）": (["关闭", "打开"], {
|
||||
"default": "关闭"
|
||||
}),
|
||||
"图片搜索（联网）": (["关闭", "打开"], {
|
||||
"default": "关闭"
|
||||
}),
|
||||
"返回格式": (["url", "base64"], {
|
||||
"default": "url"
|
||||
}),
|
||||
"seed": ("INT", {
|
||||
"default": 0,
|
||||
"min": 0,
|
||||
"max": 0xffffffffffffffff
|
||||
})
|
||||
},
|
||||
"optional": optional_inputs
|
||||
}
|
||||
|
||||
# 返回值类型
|
||||
RETURN_TYPES = ("IMAGE",)
|
||||
RETURN_NAMES = ("输出图像",)
|
||||
|
||||
# 导入 ComfyUI 的文件夹路径管理
|
||||
try:
|
||||
import folder_paths
|
||||
FOLDER_PATHS_AVAILABLE = True
|
||||
except ImportError:
|
||||
FOLDER_PATHS_AVAILABLE = False
|
||||
|
||||
# 执行函数名
|
||||
FUNCTION = "generate"
|
||||
|
||||
# 节点分类
|
||||
CATEGORY = "image/generation"
|
||||
|
||||
def resize_to_megapixels(
|
||||
self,
|
||||
image: Image.Image,
|
||||
target_megapixels: float
|
||||
) -> Image.Image:
|
||||
"""
|
||||
将图像缩放到指定的总像素数，保持纵横比
|
||||
|
||||
Args:
|
||||
image: PIL Image 对象
|
||||
target_megapixels: 目标像素数（百万像素）
|
||||
|
||||
Returns:
|
||||
缩放后的 PIL Image
|
||||
|
||||
Example:
|
||||
>>> resized = self.resize_to_megapixels(img, 2.0) # 缩放到2百万像素
|
||||
"""
|
||||
# 计算当前像素数
|
||||
current_pixels = image.width * image.height
|
||||
target_pixels = int(target_megapixels * 1_000_000)
|
||||
|
||||
# 如果当前像素数已经接近目标，则不缩放
|
||||
if abs(current_pixels - target_pixels) / target_pixels < 0.05:
|
||||
return image
|
||||
|
||||
# 计算缩放比例
|
||||
scale = (target_pixels / current_pixels) ** 0.5
|
||||
|
||||
# 计算新尺寸
|
||||
new_width = int(image.width * scale)
|
||||
new_height = int(image.height * scale)
|
||||
|
||||
# 确保至少为1像素
|
||||
new_width = max(1, new_width)
|
||||
new_height = max(1, new_height)
|
||||
|
||||
# 使用 Lanczos 重采样
|
||||
resized_image = image.resize((new_width, new_height), Image.Resampling.LANCZOS)
|
||||
|
||||
return resized_image
|
||||
|
||||
def validate_inputs(
|
||||
self,
|
||||
images: Optional[torch.Tensor],
|
||||
batch_size: int
|
||||
) -> None:
|
||||
"""
|
||||
验证输入参数
|
||||
|
||||
Args:
|
||||
images: 输入图像张量（可选）
|
||||
batch_size: 批次大小
|
||||
|
||||
Raises:
|
||||
ValueError: 如果输入参数不合法
|
||||
"""
|
||||
# 检查图像数量
|
||||
if images is not None:
|
||||
num_images = images.shape[0]
|
||||
if num_images > 14:
|
||||
raise ValueError(
|
||||
f"输入图像数量 {num_images} 超过限制 14 张，请减少输入图像数量"
|
||||
)
|
||||
|
||||
# 检查批次大小
|
||||
if batch_size < 1 or batch_size > 1000:
|
||||
raise ValueError(
|
||||
f"批次大小 {batch_size} 超出范围 [1, 1000]"
|
||||
)
|
||||
|
||||
async def _generate_single_task(
|
||||
self,
|
||||
session: aiohttp.ClientSession,
|
||||
prompt: str,
|
||||
model: str,
|
||||
resolution: str,
|
||||
aspect_ratio: str,
|
||||
images: List[Image.Image],
|
||||
output_folder: str,
|
||||
global_task_index: int,
|
||||
enable_grounding: bool = False,
|
||||
enable_image_search: bool = False,
|
||||
save_to_disk: bool = True,
|
||||
image_format: str = "url",
|
||||
) -> dict:
|
||||
"""执行单个生成任务"""
|
||||
result = {
|
||||
"global_task_index": global_task_index,
|
||||
"prompt": prompt,
|
||||
"success": False,
|
||||
"generated_count": 0,
|
||||
"saved_files": [],
|
||||
"output_images": [],
|
||||
"error": None
|
||||
}
|
||||
|
||||
try:
|
||||
gen_result = await self.client.generate_single_async(
|
||||
prompt=prompt,
|
||||
model=model,
|
||||
resolution=resolution,
|
||||
aspect_ratio=aspect_ratio,
|
||||
images=images if images else None,
|
||||
session=session,
|
||||
debug=DEBUG_LOG_ENABLED,
|
||||
debug_request=REQUEST_LOG_ENABLED,
|
||||
enable_grounding=enable_grounding,
|
||||
enable_image_search=enable_image_search,
|
||||
image_format=image_format,
|
||||
)
|
||||
if gen_result:
|
||||
images_list, _ = gen_result
|
||||
if save_to_disk:
|
||||
for gen_img in images_list:
|
||||
output_path = generate_timestamp_filename(
|
||||
output_folder=output_folder,
|
||||
extension=".png"
|
||||
)
|
||||
save_image(gen_img, output_path)
|
||||
result["saved_files"].append(output_path)
|
||||
gen_img = None
|
||||
else:
|
||||
result["output_images"] = images_list
|
||||
|
||||
result["success"] = True
|
||||
result["generated_count"] = len(images_list)
|
||||
except Exception as e:
|
||||
result["error"] = str(e)
|
||||
|
||||
return result
|
||||
|
||||
async def _process_batch_async(
|
||||
self,
|
||||
prompts: List[str],
|
||||
model: str,
|
||||
resolution: str,
|
||||
aspect_ratio: str,
|
||||
images_per_prompt: int,
|
||||
input_images: List[Image.Image],
|
||||
output_folder: str,
|
||||
pbar=None,
|
||||
enable_grounding: bool = False,
|
||||
enable_image_search: bool = False,
|
||||
save_to_disk: bool = True,
|
||||
image_format: str = "url",
|
||||
) -> List[dict]:
|
||||
"""异步批量处理：每个提示词独立调用 API"""
|
||||
# 构建任务列表：(prompt, sub_index) 用于 images_per_prompt > 1 的情况
|
||||
tasks_def = []
|
||||
for p_idx, prompt in enumerate(prompts):
|
||||
for sub_idx in range(images_per_prompt):
|
||||
tasks_def.append((p_idx, sub_idx, prompt))
|
||||
|
||||
total_tasks = len(tasks_def)
|
||||
num_prompts = len(prompts)
|
||||
|
||||
max_concurrent = 50
|
||||
num_batches = math.ceil(total_tasks / max_concurrent)
|
||||
|
||||
all_results = []
|
||||
completed = 0
|
||||
success_count = 0
|
||||
fail_count = 0
|
||||
|
||||
connector = aiohttp.TCPConnector(ssl=False, limit=0, limit_per_host=0)
|
||||
|
||||
async with aiohttp.ClientSession(connector=connector) as session:
|
||||
for batch_idx in range(num_batches):
|
||||
start_idx = batch_idx * max_concurrent
|
||||
end_idx = min(start_idx + max_concurrent, total_tasks)
|
||||
|
||||
tasks = []
|
||||
for i in range(start_idx, end_idx):
|
||||
_, _, prompt = tasks_def[i]
|
||||
task = asyncio.create_task(
|
||||
self._generate_single_task(
|
||||
session=session,
|
||||
prompt=prompt,
|
||||
model=model,
|
||||
resolution=resolution,
|
||||
aspect_ratio=aspect_ratio,
|
||||
images=input_images,
|
||||
output_folder=output_folder,
|
||||
global_task_index=i,
|
||||
enable_grounding=enable_grounding,
|
||||
enable_image_search=enable_image_search,
|
||||
save_to_disk=save_to_disk,
|
||||
image_format=image_format,
|
||||
)
|
||||
)
|
||||
tasks.append(task)
|
||||
|
||||
batch_results = []
|
||||
for coro in asyncio.as_completed(tasks):
|
||||
result_data = None
|
||||
try:
|
||||
result = await coro
|
||||
if isinstance(result, Exception):
|
||||
result_data = {"success": False, "error": str(result), "generated_count": 0, "saved_files": [], "prompt": ""}
|
||||
else:
|
||||
result_data = result
|
||||
batch_results.append(result_data)
|
||||
except Exception as e:
|
||||
result_data = {"success": False, "error": str(e), "generated_count": 0, "saved_files": [], "prompt": ""}
|
||||
batch_results.append(result_data)
|
||||
|
||||
completed += 1
|
||||
prompt_snippet = (result_data.get("prompt", "") or "")[:30]
|
||||
|
||||
if result_data and result_data.get("success", False):
|
||||
success_count += 1
|
||||
count = result_data.get("generated_count", 1)
|
||||
print(f"Nano Banana Pro: [{completed}/{total_tasks}] {prompt_snippet}{'...' if len(prompt_snippet) >= 30 else ''} → ✓成功({count}张)")
|
||||
else:
|
||||
fail_count += 1
|
||||
error_msg = result_data.get("error", "未知错误") if result_data else "未知错误"
|
||||
print(f"Nano Banana Pro: [{completed}/{total_tasks}] {prompt_snippet}{'...' if len(prompt_snippet) >= 30 else ''} → ✗失败: {error_msg}")
|
||||
|
||||
if pbar is not None:
|
||||
pbar.update(1)
|
||||
|
||||
all_results.extend(batch_results)
|
||||
|
||||
import gc
|
||||
gc.collect()
|
||||
|
||||
await asyncio.sleep(0.1)
|
||||
|
||||
return all_results
|
||||
|
||||
def generate(
|
||||
self,
|
||||
prompt: str,
|
||||
模型: str,
|
||||
宽高比: str,
|
||||
分辨率: str,
|
||||
生图数量: int,
|
||||
seed: int,
|
||||
**kwargs
|
||||
) -> Tuple[torch.Tensor]:
|
||||
"""
|
||||
生成图像
|
||||
|
||||
Args:
|
||||
prompt: 提示词
|
||||
模型: 模型名称
|
||||
宽高比: 宽高比
|
||||
分辨率: 分辨率
|
||||
生图数量: 批次大小
|
||||
seed: 随机种子
|
||||
**kwargs: 搜索开关（谷歌搜索（联网）/ 图片搜索（联网））及动态参考图输入 (参考图1-9)
|
||||
注：两个搜索参数名含全角括号，不能作为 Python 形参，从 kwargs 中提取
|
||||
|
||||
注意：
|
||||
调试日志功能已移至文件顶部配置，通过修改 DEBUG_LOG_ENABLED 常量控制
|
||||
|
||||
Returns:
|
||||
生成的图像张量 (IMAGE,)
|
||||
"""
|
||||
start_time = time.time()
|
||||
|
||||
# 从 kwargs 提取搜索参数（界面显示为「关闭/打开」，转为 bool 供调用）
|
||||
enable_grounding: bool = (kwargs.pop("谷歌搜索（联网）", "关闭") == "打开")
|
||||
enable_image_search: bool = (kwargs.pop("图片搜索（联网）", "关闭") == "打开")
|
||||
proxy_port: str = kwargs.pop("代理端口（如7897）", "")
|
||||
image_format: str = kwargs.pop("返回格式", "url")
|
||||
|
||||
# 创建 ComfyUI 原生进度条
|
||||
pbar = None
|
||||
if PROGRESS_BAR_AVAILABLE:
|
||||
pbar = ProgressBar(生图数量)
|
||||
|
||||
try:
|
||||
# 设置随机种子（用于本地随机操作）
|
||||
random.seed(seed)
|
||||
np.random.seed(seed % (2**32))
|
||||
|
||||
# 内存监控初始化
|
||||
if MEMORY_MONITOR_AVAILABLE and 生图数量 > 50:
|
||||
import psutil
|
||||
process = psutil.Process()
|
||||
initial_memory = process.memory_info().rss / 1024 / 1024
|
||||
print(f"Nano Banana Pro: 初始内存使用: {initial_memory:.1f} MB")
|
||||
|
||||
# 初始化 API 客户端
|
||||
if self.client is None:
|
||||
try:
|
||||
self.client = GeminiAPIClient()
|
||||
except ValueError as e:
|
||||
raise ValueError(f"初始化失败: {str(e)}")
|
||||
|
||||
# 注入代理设置（每次执行都刷新，支持用户中途修改端口）
|
||||
self.client.proxy_url = GeminiAPIClient.build_proxy_url(proxy_port)
|
||||
if self.client.proxy_url:
|
||||
print(f"Nano Banana Pro: 已启用代理加速 → {self.client.proxy_url}")
|
||||
|
||||
# 校验分辨率与模型的兼容性
|
||||
supported_resolutions = get_model_supported_resolutions(模型)
|
||||
if supported_resolutions and 分辨率 not in supported_resolutions:
|
||||
raise ValueError(
|
||||
f"分辨率 \"{分辨率}\" 与模型 \"{模型}\" 不兼容！\n"
|
||||
f"该模型支持的分辨率：{', '.join(supported_resolutions)}"
|
||||
)
|
||||
|
||||
# 校验宽高比与模型的兼容性
|
||||
supported_ratios = get_model_supported_aspect_ratios(模型)
|
||||
if supported_ratios and 宽高比 not in supported_ratios:
|
||||
raise ValueError(
|
||||
f"宽高比 \"{宽高比}\" 与模型 \"{模型}\" 不兼容！\n"
|
||||
f"该模型支持的宽高比：{', '.join(supported_ratios)}"
|
||||
)
|
||||
|
||||
# 校验图片搜索（联网）与模型的兼容性
|
||||
# 仅 nano-banana-2-限时特价 和 gemini-3.1-flash-image-preview 支持图片搜索
|
||||
IMAGE_SEARCH_UNSUPPORTED_MODELS = ["nano-banana-pro-次卡", "nano-banana-pro-官方计费", "gemini-3-pro-image-preview"]
|
||||
if enable_image_search and 模型 in IMAGE_SEARCH_UNSUPPORTED_MODELS:
|
||||
raise ValueError(
|
||||
f"模型 \"{模型}\" 不支持【图片搜索（联网）】功能！"
|
||||
f"请切换到 nano-banana-2-限时特价 或 gemini-3.1-flash-image-preview 后再使用"
|
||||
)
|
||||
|
||||
# 收集独立输入的参考图
|
||||
input_images = []
|
||||
for i in range(1, 10): # 1-9
|
||||
key = f"参考图{i}"
|
||||
if key in kwargs and kwargs[key] is not None:
|
||||
pil_imgs = tensor_to_pil(kwargs[key])
|
||||
input_images.extend(pil_imgs)
|
||||
|
||||
# 验证输入图像数量
|
||||
if input_images:
|
||||
if len(input_images) > 14:
|
||||
raise ValueError(
|
||||
f"输入图像数量 {len(input_images)} 超过限制 14 张，请减少输入图像数量"
|
||||
)
|
||||
|
||||
# 解析批量提示词
|
||||
batch_prompts = parse_batch_prompts(prompt)
|
||||
|
||||
# 打印首行概览
|
||||
# 图片搜索（联网）开启时隐含谷歌搜索接地，与客户端请求逻辑保持一致
|
||||
grounding_str = ""
|
||||
if enable_image_search:
|
||||
grounding_str = " | 谷歌图片搜索接地"
|
||||
elif enable_grounding:
|
||||
grounding_str = " | 谷歌搜索接地"
|
||||
|
||||
if batch_prompts:
|
||||
# 批量提示词模式
|
||||
num_prompts = len(batch_prompts)
|
||||
total_images = num_prompts * 生图数量
|
||||
mode_str = f"批量提示词模式 ({num_prompts}个提示词)"
|
||||
if input_images:
|
||||
mode_str += f" (输入{len(input_images)}张)"
|
||||
print(f"Nano Banana Pro: {mode_str} | {分辨率} {宽高比} | 共{total_images}张{grounding_str}")
|
||||
|
||||
# 大批量警告
|
||||
if total_images > 100:
|
||||
print(f"⚠️ Nano Banana Pro: 警告！批量生成 {total_images} 张图片，内存占用可能较高")
|
||||
print(f"⚠️ 建议：分批执行或减少生图数量")
|
||||
else:
|
||||
# 单提示词模式
|
||||
mode_str = f"图生图模式 (输入{len(input_images)}张)" if input_images else "文生图模式"
|
||||
print(f"Nano Banana Pro: {mode_str} | {分辨率} {宽高比} | {生图数量}张{grounding_str}")
|
||||
|
||||
# 大批量警告
|
||||
if 生图数量 > 100:
|
||||
print(f"⚠️ Nano Banana Pro: 警告！批量生成 {生图数量} 张图片，内存占用可能较高")
|
||||
print(f"⚠️ 建议：分批执行或减少生图数量")
|
||||
|
||||
# 统计变量
|
||||
success_count = 0
|
||||
fail_count = 0
|
||||
|
||||
# 进度回调 - 打印错误信息并更新进度条，添加内存监控
|
||||
def progress_callback(current, total, success, error_msg=None):
|
||||
nonlocal success_count, fail_count
|
||||
if success:
|
||||
success_count += 1
|
||||
else:
|
||||
fail_count += 1
|
||||
|
||||
# 更新 ComfyUI 原生进度条
|
||||
if pbar is not None:
|
||||
pbar.update(1)
|
||||
|
||||
# 内存监控（每完成10个任务检查一次）
|
||||
if MEMORY_MONITOR_AVAILABLE and total > 50 and current % 10 == 0:
|
||||
import gc
|
||||
gc.collect() # 强制垃圾回收
|
||||
current_memory = process.memory_info().rss / 1024 / 1024
|
||||
memory_increase = current_memory - initial_memory
|
||||
print(f"Nano Banana Pro: 内存使用: {current_memory:.1f} MB (+{memory_increase:.1f} MB)")
|
||||
|
||||
# 内存警告阈值（2GB）
|
||||
if current_memory > 2000:
|
||||
print(f"⚠️ Nano Banana Pro: 内存使用过高！建议减少生图数量或分批执行")
|
||||
|
||||
# 根据是否有批量提示词选择生成模式
|
||||
if batch_prompts:
|
||||
num_prompts = len(batch_prompts)
|
||||
total_images = num_prompts * 生图数量
|
||||
|
||||
# ===== 批量提示词模式：异步并发，内存输出 =====
|
||||
if pbar is not None:
|
||||
pbar = ProgressBar(total_images)
|
||||
|
||||
def run_async_in_thread():
|
||||
loop = asyncio.new_event_loop()
|
||||
asyncio.set_event_loop(loop)
|
||||
try:
|
||||
return loop.run_until_complete(
|
||||
self._process_batch_async(
|
||||
prompts=batch_prompts,
|
||||
model=模型,
|
||||
resolution=分辨率,
|
||||
aspect_ratio=宽高比,
|
||||
images_per_prompt=生图数量,
|
||||
input_images=input_images,
|
||||
output_folder="",
|
||||
pbar=pbar,
|
||||
enable_grounding=enable_grounding,
|
||||
enable_image_search=enable_image_search,
|
||||
save_to_disk=False,
|
||||
image_format=image_format,
|
||||
)
|
||||
)
|
||||
finally:
|
||||
loop.close()
|
||||
|
||||
with ThreadPoolExecutor(max_workers=1) as executor:
|
||||
future = executor.submit(run_async_in_thread)
|
||||
try:
|
||||
results = future.result(timeout=900)
|
||||
except TimeoutError:
|
||||
raise RuntimeError("任务执行超时（900秒），请减少提示词数量或检查网络连接")
|
||||
|
||||
# 统计结果
|
||||
success_count = sum(1 for r in results if r.get("success", False))
|
||||
fail_count = len(results) - success_count
|
||||
total_generated = sum(r.get("generated_count", 0) for r in results)
|
||||
|
||||
elapsed = time.time() - start_time
|
||||
time_str = f"{elapsed:.3f}s" if elapsed < 1 else f"{elapsed:.2f}s"
|
||||
|
||||
print(f"完成！总耗时 {time_str} | 成功: {success_count}/{total_images} | 失败: {fail_count}")
|
||||
|
||||
# 失败详情
|
||||
failed_results = [r for r in results if not r.get("success", False)]
|
||||
if failed_results:
|
||||
for fr in failed_results:
|
||||
idx = fr.get("global_task_index", -1) + 1
|
||||
prompt_snippet = (fr.get("prompt", "") or "")[:30]
|
||||
error_msg = fr.get("error", "未知错误")
|
||||
print(f" 失败 #{idx}: {prompt_snippet}{'...' if len(prompt_snippet) >= 30 else ''} → {error_msg}")
|
||||
|
||||
# 收集内存中的图像
|
||||
output_images = []
|
||||
for r in results:
|
||||
output_images.extend(r.get("output_images", []))
|
||||
|
||||
if not output_images:
|
||||
placeholder = Image.new('RGB', (512, 512), color=(128, 128, 128))
|
||||
output_images = [placeholder]
|
||||
|
||||
output_tensor = _images_to_tensor_safe(output_images, _NODE)
|
||||
|
||||
import gc
|
||||
gc.collect()
|
||||
return (output_tensor,)
|
||||
else:
|
||||
# 单提示词模式
|
||||
if 生图数量 == 1:
|
||||
# 单张：同步生成
|
||||
generated_images = self.client.generate_sync(
|
||||
prompt=prompt,
|
||||
model=模型,
|
||||
resolution=分辨率,
|
||||
aspect_ratio=宽高比,
|
||||
batch_size=1,
|
||||
images=input_images,
|
||||
progress_callback=progress_callback,
|
||||
debug=DEBUG_LOG_ENABLED,
|
||||
debug_request=REQUEST_LOG_ENABLED,
|
||||
enable_grounding=enable_grounding,
|
||||
enable_image_search=enable_image_search,
|
||||
image_format=image_format,
|
||||
)
|
||||
else:
|
||||
# 多张：异步并发，内存输出
|
||||
|
||||
if pbar is not None:
|
||||
pbar = ProgressBar(生图数量)
|
||||
|
||||
def run_async_in_thread():
|
||||
loop = asyncio.new_event_loop()
|
||||
asyncio.set_event_loop(loop)
|
||||
try:
|
||||
return loop.run_until_complete(
|
||||
self._process_batch_async(
|
||||
prompts=[prompt],
|
||||
model=模型,
|
||||
resolution=分辨率,
|
||||
aspect_ratio=宽高比,
|
||||
images_per_prompt=生图数量,
|
||||
input_images=input_images,
|
||||
output_folder="",
|
||||
pbar=pbar,
|
||||
enable_grounding=enable_grounding,
|
||||
enable_image_search=enable_image_search,
|
||||
save_to_disk=False,
|
||||
image_format=image_format,
|
||||
)
|
||||
)
|
||||
finally:
|
||||
loop.close()
|
||||
|
||||
with ThreadPoolExecutor(max_workers=1) as executor:
|
||||
future = executor.submit(run_async_in_thread)
|
||||
try:
|
||||
results = future.result(timeout=900)
|
||||
except TimeoutError:
|
||||
raise RuntimeError("任务执行超时（900秒），请减少生图数量或检查网络连接")
|
||||
|
||||
success_count = sum(1 for r in results if r.get("success", False))
|
||||
fail_count = len(results) - success_count
|
||||
total_generated = sum(r.get("generated_count", 0) for r in results)
|
||||
|
||||
elapsed = time.time() - start_time
|
||||
time_str = f"{elapsed:.3f}s" if elapsed < 1 else f"{elapsed:.2f}s"
|
||||
print(f"完成！总耗时 {time_str} | 成功: {success_count}/{生图数量} | 失败: {fail_count}")
|
||||
|
||||
# 失败详情
|
||||
failed_results = [r for r in results if not r.get("success", False)]
|
||||
if failed_results:
|
||||
for fr in failed_results:
|
||||
idx = fr.get("global_task_index", -1) + 1
|
||||
error_msg = fr.get("error", "未知错误")
|
||||
print(f" 失败 #{idx}: {prompt[:30]}{'...' if len(prompt) >= 30 else ''} → {error_msg}")
|
||||
|
||||
# 收集内存中的图像
|
||||
output_images = []
|
||||
for r in results:
|
||||
output_images.extend(r.get("output_images", []))
|
||||
|
||||
if not output_images:
|
||||
placeholder = Image.new('RGB', (512, 512), color=(128, 128, 128))
|
||||
output_images = [placeholder]
|
||||
|
||||
output_tensor = _images_to_tensor_safe(output_images, _NODE)
|
||||
|
||||
import gc
|
||||
gc.collect()
|
||||
return (output_tensor,)
|
||||
|
||||
|
||||
# 优化：限制输出图片数量，避免内存爆炸
|
||||
max_output_images = 20 # 最多输出20张图片到ComfyUI
|
||||
|
||||
if len(generated_images) > max_output_images:
|
||||
print(f"Nano Banana Pro: 生成 {len(generated_images)} 张图片，限制输出前 {max_output_images} 张到ComfyUI")
|
||||
output_images = generated_images[:max_output_images]
|
||||
else:
|
||||
output_images = generated_images
|
||||
|
||||
# 转换输出图像
|
||||
output_tensor = _images_to_tensor_safe(output_images, _NODE)
|
||||
|
||||
# 计算耗时并打印最终统计
|
||||
elapsed = time.time() - start_time
|
||||
if elapsed < 1:
|
||||
time_str = f"{elapsed:.3f}s"
|
||||
else:
|
||||
time_str = f"{elapsed:.2f}s"
|
||||
|
||||
# 打印最终汇总
|
||||
if fail_count > 0:
|
||||
print(f"完成！总耗时 {time_str} | 成功 {success_count}张 | 失败 {fail_count}张")
|
||||
else:
|
||||
print(f"完成！总耗时 {time_str} | 成功 {len(generated_images)}张")
|
||||
|
||||
# 最终内存清理
|
||||
import gc
|
||||
gc.collect()
|
||||
if MEMORY_MONITOR_AVAILABLE and 生图数量 > 50:
|
||||
final_memory = process.memory_info().rss / 1024 / 1024
|
||||
print(f"Nano Banana Pro: 最终内存使用: {final_memory:.1f} MB")
|
||||
|
||||
return (output_tensor,)
|
||||
|
||||
except ValueError as e:
|
||||
# 检测是否为授权错误
|
||||
if str(e) == "未授权！":
|
||||
print("请联系作者授权后方可使用！")
|
||||
raise ValueError("未授权！") from None
|
||||
raise ValueError(str(e)) from None
|
||||
|
||||
except RuntimeError as e:
|
||||
raise RuntimeError(str(e)) from None
|
||||
|
||||
except Exception as e:
|
||||
raise type(e)(str(e)) from None
|
||||
|
||||
finally:
|
||||
# 查询余额
|
||||
if self.client is not None:
|
||||
try:
|
||||
balance_data = self.client.query_balance_sync()
|
||||
balance_info = self.client.format_balance_info(balance_data)
|
||||
print(f"Nano Banana Pro: {balance_info}")
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
# 最终内存清理
|
||||
import gc
|
||||
gc.collect()
|
||||
+15
-11
@@ -30,7 +30,8 @@ from PIL import Image
|
||||
|
||||
from ..utils.image_utils import tensor_to_pil, pil_to_tensor, parse_batch_prompts
|
||||
from ..utils.file_utils import load_images_from_folder, pair_images_by_name, pair_images_cartesian
|
||||
from ..utils.config import get_api_key_or_raise
|
||||
from ..utils.config import get_api_key_or_raise, NETWORK_ROUTE_OPTIONS, get_base_url_by_route
|
||||
from ..utils.http_error import async_request_with_retry
|
||||
from ..models_config import (
|
||||
get_enabled_async_models,
|
||||
get_model_provider,
|
||||
@@ -169,15 +170,16 @@ class NanoBananaV2:
|
||||
"default": "一个中国女子的OOTD",
|
||||
"multiline": True
|
||||
}),
|
||||
"网络线路": (NETWORK_ROUTE_OPTIONS, {"default": "全球加速"}),
|
||||
"模型": (models, {"default": models[0]}),
|
||||
"宽高比": (all_aspect_ratios, {"default": "1:1"}),
|
||||
"宽高比": (["智能"] + all_aspect_ratios, {"default": "智能"}),
|
||||
"分辨率": (all_resolutions, {"default": "2K"}),
|
||||
"生图数量": ("INT", {
|
||||
"default": 1,
|
||||
"min": 1,
|
||||
"max": 9,
|
||||
"step": 1
|
||||
})
|
||||
}),
|
||||
},
|
||||
"optional": optional
|
||||
}
|
||||
@@ -299,13 +301,11 @@ class NanoBananaV2:
|
||||
print(f"[异步提交] URL: {url}")
|
||||
print(f"[异步提交] 请求体: {json.dumps(_log_body, ensure_ascii=False)[:500]}")
|
||||
|
||||
async with session.post(url, json=request_body, headers=headers, proxy=provider.proxy_url) as response:
|
||||
if response.status != 200:
|
||||
error_text = await response.text()
|
||||
if not error_text.strip():
|
||||
error_text = "(服务器未返回错误详情)"
|
||||
raise RuntimeError(f"提交任务失败 ({response.status}): {error_text}")
|
||||
data = await response.json()
|
||||
resp = await async_request_with_retry(
|
||||
session, "POST", url, json=request_body, headers=headers,
|
||||
proxy=provider.proxy_url, prefix="异步提交: "
|
||||
)
|
||||
data = await resp.json()
|
||||
|
||||
if DEBUG_LOG_ENABLED:
|
||||
import json
|
||||
@@ -541,6 +541,7 @@ class NanoBananaV2:
|
||||
宽高比: str,
|
||||
分辨率: str,
|
||||
生图数量: int,
|
||||
网络线路: str = "全球加速",
|
||||
**kwargs
|
||||
) -> Tuple[torch.Tensor]:
|
||||
"""生成图像（异步模式）"""
|
||||
@@ -557,6 +558,7 @@ class NanoBananaV2:
|
||||
proxy_url = BaseAsyncImageProvider.build_proxy_url(proxy_port)
|
||||
provider = self._get_provider(模型, proxy_url=proxy_url, api_key_override=api_key_override)
|
||||
provider.image_compression = "webp" if 图片质量 == "日常" else None
|
||||
provider._route_base_url = get_base_url_by_route(网络线路)
|
||||
|
||||
if proxy_url:
|
||||
print(f"{self.NODE_LABEL}: 已启用代理加速 -> {proxy_url}")
|
||||
@@ -590,7 +592,7 @@ class NanoBananaV2:
|
||||
|
||||
# 运行时验证宽高比
|
||||
supported_ratios = provider.get_model_aspect_ratios(模型)
|
||||
if supported_ratios and 宽高比 not in supported_ratios:
|
||||
if 宽高比 != "智能" and supported_ratios and 宽高比 not in supported_ratios:
|
||||
raise ValueError(
|
||||
f"宽高比 \"{宽高比}\" 与模型 \"{模型}\" 不兼容！\n"
|
||||
f"该模型支持的宽高比：{', '.join(supported_ratios)}"
|
||||
@@ -977,6 +979,7 @@ class NanoBananaV2Batch(NanoBananaV2):
|
||||
宽高比: str,
|
||||
分辨率: str,
|
||||
生图数量: int = 1,
|
||||
网络线路: str = "全球加速",
|
||||
**kwargs
|
||||
) -> Tuple[torch.Tensor]:
|
||||
"""生成图像（异步模式 - 批量版：全并发 + 即时落盘）"""
|
||||
@@ -997,6 +1000,7 @@ class NanoBananaV2Batch(NanoBananaV2):
|
||||
proxy_url = BaseAsyncImageProvider.build_proxy_url(proxy_port)
|
||||
provider = self._get_provider(模型, proxy_url=proxy_url, api_key_override=api_key_override)
|
||||
provider.image_compression = "webp" if 图片质量 == "日常" else None
|
||||
provider._route_base_url = get_base_url_by_route(网络线路)
|
||||
|
||||
if proxy_url:
|
||||
print(f"{self.NODE_LABEL}: 已启用代理加速 -> {proxy_url}")
|
||||
|
||||
+2
-185
@@ -1,79 +1,18 @@
|
||||
"""
|
||||
图像元数据去除节点
|
||||
替代 ComfyUI 原生"保存图像"节点，保存时不写入提示词、工作流等 AI 元数据
|
||||
|
||||
提供两种节点：
|
||||
1. SaveCleanImage - 接收 IMAGE 张量，去除元数据后直接保存到 output 目录
|
||||
2. BatchCleanMetadata - 指定文件夹路径，批量去除已有图片中的元数据
|
||||
提供批量去除已有图片中元数据的功能
|
||||
"""
|
||||
|
||||
import os
|
||||
from datetime import datetime
|
||||
import random
|
||||
from typing import List
|
||||
|
||||
import numpy as np
|
||||
import torch
|
||||
from PIL import Image
|
||||
from PIL.PngImagePlugin import PngInfo
|
||||
|
||||
from ..utils.image_utils import tensor_to_pil
|
||||
from ..utils.file_utils import _get_port_suffix
|
||||
|
||||
# 尝试导入 ComfyUI 的 folder_paths
|
||||
try:
|
||||
import folder_paths
|
||||
FOLDER_PATHS_AVAILABLE = True
|
||||
except ImportError:
|
||||
FOLDER_PATHS_AVAILABLE = False
|
||||
|
||||
# 支持的图片格式
|
||||
SUPPORTED_EXTENSIONS = {'.png', '.jpg', '.jpeg', '.webp', '.bmp', '.tiff', '.tif'}
|
||||
|
||||
|
||||
def _get_output_dir() -> str:
|
||||
"""
|
||||
获取 ComfyUI output 目录
|
||||
|
||||
Returns:
|
||||
output 目录的绝对路径
|
||||
"""
|
||||
if FOLDER_PATHS_AVAILABLE:
|
||||
return folder_paths.get_output_directory()
|
||||
# fallback: 相对于插件目录推断
|
||||
plugin_dir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
|
||||
return os.path.join(os.path.dirname(os.path.dirname(plugin_dir)), "output")
|
||||
|
||||
|
||||
def _get_next_counter(directory: str, prefix: str) -> int:
|
||||
"""
|
||||
扫描目录，获取下一个可用的文件计数器
|
||||
|
||||
Args:
|
||||
directory: 目标目录
|
||||
prefix: 文件名前缀
|
||||
|
||||
Returns:
|
||||
下一个计数器值
|
||||
"""
|
||||
if not os.path.exists(directory):
|
||||
return 1
|
||||
|
||||
if prefix:
|
||||
pattern = re.compile(rf'^{re.escape(prefix)}_(\d+)')
|
||||
else:
|
||||
pattern = re.compile(rf'^(\d+)\.')
|
||||
max_counter = 0
|
||||
|
||||
for f in os.listdir(directory):
|
||||
m = pattern.match(f)
|
||||
if m:
|
||||
counter = int(m.group(1))
|
||||
max_counter = max(max_counter, counter)
|
||||
|
||||
return max_counter + 1
|
||||
|
||||
|
||||
def _save_image_clean(image: Image.Image, path: str, fmt: str = None, quality: int = 95) -> None:
|
||||
"""
|
||||
保存图像，不包含任何元数据
|
||||
@@ -127,129 +66,7 @@ def _save_image_clean(image: Image.Image, path: str, fmt: str = None, quality: i
|
||||
|
||||
|
||||
# ============================================================================
|
||||
# 节点 1：保存干净图像
|
||||
# ============================================================================
|
||||
|
||||
class SaveCleanImage:
|
||||
"""
|
||||
保存干净图像节点（不含元数据）
|
||||
|
||||
功能：
|
||||
- 接收 IMAGE 张量（支持单图和批次）
|
||||
- 去除所有元数据后保存到 ComfyUI/output 目录
|
||||
- 文件名自动添加 nometa 标识，方便辨认
|
||||
- 支持 PNG/JPEG/WEBP 格式
|
||||
- 作为终端节点，替代 ComfyUI 原生"保存图像"节点
|
||||
|
||||
使用场景：
|
||||
- 生图完成后，直接保存不含 AI 元数据的干净图像
|
||||
- 分享图像时不暴露提示词和工作流
|
||||
"""
|
||||
|
||||
SAVE_FORMATS = ["PNG", "JPEG", "WEBP"]
|
||||
|
||||
@classmethod
|
||||
def INPUT_TYPES(cls):
|
||||
"""
|
||||
定义输入参数
|
||||
|
||||
Returns:
|
||||
输入参数配置字典
|
||||
"""
|
||||
return {
|
||||
"required": {
|
||||
"图像": ("IMAGE",),
|
||||
"文件名前缀": ("STRING", {"default": "ComfyUI_nometa"}),
|
||||
"保存格式": (cls.SAVE_FORMATS, {"default": "PNG"}),
|
||||
},
|
||||
"optional": {
|
||||
"JPEG/WEBP质量": ("INT", {
|
||||
"default": 95,
|
||||
"min": 1,
|
||||
"max": 100,
|
||||
"step": 1
|
||||
}),
|
||||
}
|
||||
}
|
||||
|
||||
RETURN_TYPES = ()
|
||||
OUTPUT_NODE = True
|
||||
FUNCTION = "save_clean"
|
||||
CATEGORY = "image"
|
||||
|
||||
DESCRIPTION = (
|
||||
"保存干净图像（不含元数据）。\n"
|
||||
"替代 ComfyUI 原生'保存图像'节点，保存时不写入提示词、工作流等 AI 元数据。\n"
|
||||
"文件保存到 ComfyUI/output 目录。"
|
||||
)
|
||||
|
||||
def save_clean(
|
||||
self,
|
||||
图像: torch.Tensor,
|
||||
文件名前缀: str = "ComfyUI_nometa",
|
||||
保存格式: str = "PNG",
|
||||
**kwargs
|
||||
) -> dict:
|
||||
"""
|
||||
去除元数据并保存图像
|
||||
|
||||
Args:
|
||||
图像: ComfyUI 图像张量 [B, H, W, C]
|
||||
文件名前缀: 保存文件名前缀
|
||||
保存格式: 图像格式（PNG/JPEG/WEBP）
|
||||
**kwargs: 可选参数（JPEG/WEBP质量）
|
||||
|
||||
Returns:
|
||||
UI 结果字典，包含保存的图像信息用于前端预览
|
||||
"""
|
||||
quality = kwargs.get("JPEG/WEBP质量", 95)
|
||||
|
||||
output_dir = _get_output_dir()
|
||||
port_suffix = _get_port_suffix()
|
||||
os.makedirs(output_dir, exist_ok=True)
|
||||
|
||||
# 格式与扩展名映射
|
||||
ext_map = {"PNG": ".png", "JPEG": ".jpg", "WEBP": ".webp"}
|
||||
ext = ext_map.get(保存格式, ".png")
|
||||
|
||||
# 转换为 PIL 图像
|
||||
pil_images = tensor_to_pil(图像)
|
||||
|
||||
results = []
|
||||
saved_paths = []
|
||||
for img in pil_images:
|
||||
ts = datetime.now().strftime("%Y%m%d_%H%M%S")
|
||||
ms = random.randint(0, 999)
|
||||
|
||||
while True:
|
||||
if 文件名前缀:
|
||||
filename = f"{文件名前缀}_{ts}_{ms:03d}{port_suffix}{ext}"
|
||||
else:
|
||||
filename = f"{ts}_{ms:03d}{port_suffix}{ext}"
|
||||
filepath = os.path.join(output_dir, filename)
|
||||
if not os.path.exists(filepath):
|
||||
break
|
||||
ms = (ms + 1) % 1000
|
||||
|
||||
_save_image_clean(img, filepath, fmt=保存格式, quality=quality)
|
||||
|
||||
results.append({
|
||||
"filename": filename,
|
||||
"subfolder": "",
|
||||
"type": "output"
|
||||
})
|
||||
saved_paths.append(filepath)
|
||||
|
||||
# 打印详细日志，方便用户定位保存的文件
|
||||
print(f"保存干净图像: 已保存 {len(pil_images)} 张无元数据图像 (格式: {保存格式})")
|
||||
for p in saved_paths:
|
||||
print(f" → {p}")
|
||||
|
||||
return {"ui": {"images": results}}
|
||||
|
||||
|
||||
# ============================================================================
|
||||
# 节点 2：批量去除元数据
|
||||
# 批量去除元数据
|
||||
# ============================================================================
|
||||
|
||||
class BatchCleanMetadata:
|
||||
|
||||
@@ -0,0 +1,91 @@
|
||||
"""保存图像节点 - 支持 PNG/JPEG/WebP 格式输出"""
|
||||
|
||||
import os
|
||||
import json
|
||||
import numpy as np
|
||||
from PIL import Image
|
||||
from PIL.PngImagePlugin import PngInfo
|
||||
|
||||
import folder_paths
|
||||
from comfy.cli_args import args
|
||||
|
||||
|
||||
class SaveImageFormat:
|
||||
"""保存图像，支持 PNG / JPEG / WebP 三种格式"""
|
||||
|
||||
FORMATS = ["PNG", "JPEG", "WebP"]
|
||||
|
||||
def __init__(self):
|
||||
self.output_dir = folder_paths.get_output_directory()
|
||||
self.type = "output"
|
||||
self.compress_level = 4
|
||||
|
||||
@classmethod
|
||||
def INPUT_TYPES(cls):
|
||||
return {
|
||||
"required": {
|
||||
"images": ("IMAGE",),
|
||||
"filename_prefix": ("STRING", {"default": "ComfyUI"}),
|
||||
"format": (cls.FORMATS, {"default": "PNG"}),
|
||||
},
|
||||
"optional": {},
|
||||
"hidden": {
|
||||
"prompt": "PROMPT",
|
||||
"extra_pnginfo": "EXTRA_PNGINFO",
|
||||
},
|
||||
}
|
||||
|
||||
RETURN_TYPES = ()
|
||||
FUNCTION = "save_images"
|
||||
OUTPUT_NODE = True
|
||||
CATEGORY = "image"
|
||||
DESCRIPTION = "保存图像，支持 PNG / JPEG / WebP 格式输出。"
|
||||
|
||||
_EXT_MAP = {"PNG": ".png", "JPEG": ".jpg", "WebP": ".webp"}
|
||||
|
||||
def save_images(self, images, filename_prefix="ComfyUI", format="PNG",
|
||||
prompt=None, extra_pnginfo=None):
|
||||
full_output_folder, filename, counter, subfolder, filename_prefix = \
|
||||
folder_paths.get_save_image_path(
|
||||
filename_prefix, self.output_dir,
|
||||
images[0].shape[1], images[0].shape[0]
|
||||
)
|
||||
|
||||
ext = self._EXT_MAP.get(format, ".png")
|
||||
results = []
|
||||
|
||||
for batch_number, image in enumerate(images):
|
||||
i = 255.0 * image.cpu().numpy()
|
||||
img = Image.fromarray(np.clip(i, 0, 255).astype(np.uint8))
|
||||
|
||||
filename_with_batch_num = filename.replace("%batch_num%", str(batch_number))
|
||||
file = f"{filename_with_batch_num}_{counter:05}_{ext}"
|
||||
|
||||
filepath = os.path.join(full_output_folder, file)
|
||||
|
||||
if format == "PNG":
|
||||
metadata = None
|
||||
if not args.disable_metadata:
|
||||
metadata = PngInfo()
|
||||
if prompt is not None:
|
||||
metadata.add_text("prompt", json.dumps(prompt))
|
||||
if extra_pnginfo is not None:
|
||||
for x in extra_pnginfo:
|
||||
metadata.add_text(x, json.dumps(extra_pnginfo[x]))
|
||||
img.save(filepath, pnginfo=metadata,
|
||||
compress_level=self.compress_level)
|
||||
elif format == "JPEG":
|
||||
if img.mode == "RGBA":
|
||||
img = img.convert("RGB")
|
||||
img.save(filepath, quality=100, optimize=True)
|
||||
elif format == "WebP":
|
||||
img.save(filepath, lossless=True)
|
||||
|
||||
results.append({
|
||||
"filename": file,
|
||||
"subfolder": subfolder,
|
||||
"type": self.type,
|
||||
})
|
||||
counter += 1
|
||||
|
||||
return {"ui": {"images": results}}
|
||||
@@ -15,6 +15,7 @@ from ..clients.seedance_client import SeedanceClient
|
||||
from ..clients.gemini_client import GeminiAPIClient
|
||||
from ..utils.image_utils import tensor_to_pil, encode_image_to_base64, pil_to_tensor
|
||||
from ..utils.r2_uploader import upload_video, upload_audio
|
||||
from ..utils.config import NETWORK_ROUTE_OPTIONS, get_base_url_by_route
|
||||
|
||||
from comfy_api.latest import InputImpl
|
||||
|
||||
@@ -116,6 +117,7 @@ class Seedance:
|
||||
return {
|
||||
"required": {
|
||||
"提示词": ("STRING", {"multiline": True, "default": ""}),
|
||||
"网络线路": (NETWORK_ROUTE_OPTIONS, {"default": "全球加速"}),
|
||||
"模型": (_MODELS, {"default": "doubao-seedance-2-0-260128"}),
|
||||
"分辨率": (_RESOLUTIONS, {"default": "720p"}),
|
||||
"宽高比": (["16:9", "adaptive", "9:16", "1:1", "4:3", "3:4", "21:9"],
|
||||
@@ -242,6 +244,7 @@ class Seedance:
|
||||
_, save_path = tempfile.mkstemp(suffix=".mp4", prefix=f"{file_prefix}_")
|
||||
|
||||
client = SeedanceClient()
|
||||
client.base_url = get_base_url_by_route(kwargs.get("网络线路", "全球加速"))
|
||||
pbar = _make_pbar()
|
||||
on_stage, on_prog = _make_callbacks(tag, pbar)
|
||||
|
||||
@@ -268,6 +271,7 @@ class SeedanceMultiModal:
|
||||
return {
|
||||
"required": {
|
||||
"提示词": ("STRING", {"multiline": True, "default": ""}),
|
||||
"网络线路": (NETWORK_ROUTE_OPTIONS, {"default": "全球加速"}),
|
||||
"模型": (_MODELS, {"default": "doubao-seedance-2-0-260128"}),
|
||||
"分辨率": (_RESOLUTIONS, {"default": "720p"}),
|
||||
"宽高比": (["adaptive", "16:9", "9:16", "1:1", "4:3", "3:4", "21:9"],
|
||||
@@ -414,6 +418,7 @@ class SeedanceMultiModal:
|
||||
_, save_path = tempfile.mkstemp(suffix=".mp4", prefix="seedance_mm_")
|
||||
|
||||
client = SeedanceClient()
|
||||
client.base_url = get_base_url_by_route(kwargs.get("网络线路", "全球加速"))
|
||||
pbar = _make_pbar()
|
||||
on_stage, on_prog = _make_callbacks("Seedance多模态", pbar)
|
||||
|
||||
|
||||
@@ -17,7 +17,7 @@ import torch
|
||||
from PIL import Image
|
||||
|
||||
from ..utils.image_utils import tensor_to_pil
|
||||
from ..utils.config import get_api_key_or_raise, get_api_base_url
|
||||
from ..utils.config import get_api_key_or_raise, get_api_base_url, NETWORK_ROUTE_OPTIONS, get_base_url_by_route
|
||||
from ..utils.file_types import FileList
|
||||
|
||||
# ============================================================================
|
||||
@@ -66,6 +66,9 @@ class UniversalLLMChat:
|
||||
def INPUT_TYPES(cls):
|
||||
return {
|
||||
"required": {
|
||||
"网络线路": (NETWORK_ROUTE_OPTIONS, {
|
||||
"default": "全球加速"
|
||||
}),
|
||||
"模型": (SUPPORTED_MODELS, {
|
||||
"default": SUPPORTED_MODELS[0]
|
||||
}),
|
||||
@@ -370,6 +373,7 @@ class UniversalLLMChat:
|
||||
self,
|
||||
模型: str,
|
||||
提示词: str,
|
||||
网络线路: str = "全球加速",
|
||||
图片: Optional[torch.Tensor] = None,
|
||||
视频=None,
|
||||
文件: Optional[FileList] = None,
|
||||
@@ -380,6 +384,7 @@ class UniversalLLMChat:
|
||||
|
||||
try:
|
||||
self._ensure_config()
|
||||
self._base_url = get_base_url_by_route(网络线路)
|
||||
|
||||
# 如果用户传入了自定义令牌，则覆盖默认 API Key
|
||||
effective_api_key = 令牌.strip() if 令牌 and 令牌.strip() else self._api_key
|
||||
|
||||
Reference in New Issue
Block a user