APP下载

每日签到地址发布老王说明书宣传中心繁/简

老王论坛»首页 › AI专区 › AI资源工具 › [转载搬运] 剑侠AI-krea2文生图整合包v2.1，最低8G显卡 ...

[转载搬运] 剑侠AI-krea2文生图整合包v2.1，最低8G显卡，支持NSFW [1+50GB][百度盘]

查看数: 10.3W | 评论数: 262 | 收藏 2169

关灯 | 提示：支持键盘翻页<-左右->

本主题由隔壁老王于 2026-7-18 20:14 审核通过

发布时间: 2026-7-18 13:25

正文摘要:

剑侠AI· krea2文生图整合包 Lite v2.1 说明与使用指南这套整合包是基于 ComfyUI 后端引擎封装的一套 Windows 本地 AI 画图工具。主要目的是解决原版 ComfyUI 部署繁琐、全英文节点难上手的问题。界面采用了全中文可 ...

回复

静若 发表于 2026-7-26 15:24:35

问题修复了，原因是代码中写死了Lora，就算界面取消加载但是工作流里面写死都会导致生成的图片出现雪花马赛克，等下就更新

静若 发表于 2026-7-26 22:58:52

新版本上传好了，可以直接删除旧版本了！

更新日志：
【修复】
  · 修复文生图空 LoRA 仍被自动加载 / 回退模板默认的问题（含 identity_edit 误灌导致马赛克雪花图）
  · UI 选「无」时真正旁路 LoRA 节点，不再写死加载
  · 修复 UI 开启高清放大异常偏慢：默认改回 SeedVR2 3B fp8，强制单帧 batch、合理 blocks_to_swap（对齐原生高清工作流）
  · 降低启动后后台负载：缓存 nvidia-smi 轮询、减少桥接访问日志、截断过大 runtime.log
  · 内嵌窗口启动器不再弹出黑框控制台（备用启动器仍保留控制台）；关窗后结束后台进程逻辑不变

  【新增 / 优化】
  · 成品图左上角悬停显示「生成用时 X 分钟 Y 秒」，历史记录同步保留用时
  · 终端完成日志同步输出生成用时，便于对照
  · 单图编辑工作流 API 对齐最新 KREA2 单图编辑图（节点/默认参数跟工作流走；UI 有值才覆盖，不写死）
  · 单图编辑右侧生成参数新增「参考增强」（工作流浮点节点 → ref_boost，默认 4）

SOSUFO 发表于 2026-7-20 11:01:33

我的也是显示超时，但是能打开备用的，但是生成不了图片，提示：无法连接: <urlopen error [WinError 10061] 由于目标计算机积极拒绝，无法连接。大神这个要怎么处理

静若 发表于 2026-7-18 23:11:40

miyu12345 发表于 2026-7-18 22:08
大佬，有没有生视频的整合包

有了，已经做出来了，这段时间连续熬夜搞了很多款，遭不住了，明天想休息一天，缓解一下

ZERO.零ꦿృ༊ 发表于 2026-7-22 20:06:21

启动超时，问了下ai说没有安装git这个插件是怎么回事

17194851733 发表于 2026-7-20 02:12:20

大佬牛逼，希望有本地部署生成视频的整合包，生图的已经没啥新意了感觉

402315863 发表于 2026-7-19 13:45:21

我启动不了，双击启动器后等待一段时间就会显示启动超时，是不是因为我电脑配置不够啊

A1015269654 发表于 2026-8-5 10:07:45

关于单图编辑，我自己试的比较容易成功的办法，《模式切换》就选《单图编辑》，主模型选《文生模型》，loR1选文生图（身体）loR2选图片编辑（图片编辑）loR3选文生图（场景），三个选项强度0.8左右（强度大小自己试，强度越大越容易乱码），生成步数一般6-8步左右，参考强度3左右，采样器:er-sde，调度器:slmple
哪位道友有更好的设置，希望回复一下

fangsiji 发表于 2026-7-18 22:18:03

生成是模糊看不清的是为什么

老六六吗 发表于 2026-7-19 22:26:39

老六六吗发表于 2026-7-19 22:21
这个是什么情况，models到底是用电脑c盘的还是自己在这个文件下面建一个啊建一个 ...

我是sb，放错位置了

wangyoucong 发表于 2026-8-8 00:27:56

只支持n卡，可惜我是a卡

昊京 发表于 昨天 01:10

大佬牛逼

1000304222.png (1.92 MB, 下载次数: 0)

cyg773 发表于 5 天前

我是小白，我没看懂，您说的下载好的模型，在哪里？我找不到

lhp518 发表于 7 天前

单图编辑点生成后一直显示在监听进度

tcar 发表于 2026-9-13 19:28:51

静若发表于 2026-9-12 00:08
这次核心报错问题：cudaGetDeviceCount() returned cudaErrorNotSupported
原因是 PyTorch环境在调用 CUD ...

更新了驱动  现在显示这个

========================================
[launcher] 鍚姩 ComfyUI
[32m[INFO][0m setup plugin alembic.autogenerate.schemas
[32m[INFO][0m setup plugin alembic.autogenerate.tables
[32m[INFO][0m setup plugin alembic.autogenerate.types
[32m[INFO][0m setup plugin alembic.autogenerate.constraints
[32m[INFO][0m setup plugin alembic.autogenerate.defaults
[32m[INFO][0m setup plugin alembic.autogenerate.comments
[32m[INFO][0m Setting output directory to: F:\JianxiaAI\output
[START] Security scan
[DONE] Security scan
## ComfyUI-Manager: installing dependencies done.
** ComfyUI startup time: 2026-09-11 13:11:59.539
** Platform: Windows
** Python version: 3.13.11 (tags/v3.13.11:6278944, Dec  5 2025, 16:26:58) [MSC v.1944 64 bit (AMD64)]
** Python executable: F:\JianxiaAI\python\python.exe
** ComfyUI Path: F:\JianxiaAI\ComfyUI
** ComfyUI Base Folder Path: F:\JianxiaAI\ComfyUI
** User directory: F:\JianxiaAI\ComfyUI\user
** ComfyUI-Manager config path: F:\JianxiaAI\ComfyUI\user\__manager\config.ini
** Log path: F:\JianxiaAI\ComfyUI\user\comfyui.log
[32m[INFO][0m
Prestartup times for custom nodes:
[32m[INFO][0m 0.0 seconds: F:\JianxiaAI\ComfyUI\custom_nodes\rgthree-comfy
[32m[INFO][0m 0.0 seconds: F:\JianxiaAI\ComfyUI\custom_nodes\comfyui-easy-use
[32m[INFO][0m 0.0 seconds: F:\JianxiaAI\ComfyUI\custom_nodes\deno-custom-nodes
[32m[INFO][0m 3.1 seconds: F:\JianxiaAI\ComfyUI\custom_nodes\ComfyUI-Manager
[32m[INFO][0m
F:\JianxiaAI\python\Lib\site-packages\torch\cuda\__init__.py:182: UserWarning: cudaGetDeviceCount() returned cudaErrorNotSupported, likely using older driver or on CPU machine (Triggered internally at C:\actions-runner\_work\pytorch\pytorch\pytorch\c10\cuda\CUDAFunctions.cpp:88.)
  return torch._C._cuda_getDeviceCount() > 0
[32m[INFO][0m Found comfy_kitchen backend triton: {'available': False, 'disabled': True, 'unavailable_reason': 'Neither CUDA nor XPU available on this system', 'capabilities': []}
[32m[INFO][0m Found comfy_kitchen backend eager: {'available': True, 'disabled': False, 'unavailable_reason': None, 'capabilities': ['adaln', 'apply_rope', 'apply_rope1', 'apply_rope_split_half', 'apply_rope_split_half1', 'convrot_w4a4_linear', 'dequantize_convrot_w4a4_weight', 'dequantize_int8_convrot_weight', 'dequantize_int8_convrot_weight_dtype', 'dequantize_int8_simple', 'dequantize_int8_simple_dtype', 'dequantize_mxfp8', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'gemv_awq_w4a16', 'int8_linear', 'prepare_int4_weight_for_int8_linear', 'quantize_and_rotate_rowwise', 'quantize_convrot_w4a4_weight', 'quantize_int8_convrot_weight', 'quantize_int8_rowwise', 'quantize_int8_tensorwise', 'quantize_mxfp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8', 'quantize_svdquant_w4a4', 'rms_rope', 'rms_rope1', 'rms_rope_split_half', 'rms_rope_split_half1', 'scaled_mm_mxfp8', 'scaled_mm_nvfp4', 'scaled_mm_svdquant_w4a4', 'stochastic_rounding_fp8']}
[32m[INFO][0m Found comfy_kitchen backend cuda: {'available': False, 'disabled': False, 'unavailable_reason': 'CUDA not available on this system', 'capabilities': []}
[32m[INFO][0m Checkpoint files will always be loaded safely.
Windows fatal exception: access violation

Stack (most recent call first):
  File "F:\JianxiaAI\python\Lib\site-packages\torch\cuda\__init__.py", line 410 in _lazy_init
  File "F:\JianxiaAI\python\Lib\site-packages\torch\cuda\__init__.py", line 1069 in current_device
  File "F:\JianxiaAI\ComfyUI\comfy\model_management.py", line 211 in get_torch_device
  File "F:\JianxiaAI\ComfyUI\comfy\model_management.py", line 362 in <module>
  File "<frozen importlib._bootstrap>", line 488 in _call_with_frames_removed
  File "<frozen importlib._bootstrap_external>", line 1023 in exec_module
  File "<frozen importlib._bootstrap>", line 935 in _load_unlocked
  File "<frozen importlib._bootstrap>", line 1331 in _find_and_load_unlocked
  File "<frozen importlib._bootstrap>", line 1360 in _find_and_load
  File "F:\JianxiaAI\ComfyUI\execution.py", line 18 in <module>
  File "<frozen importlib._bootstrap>", line 488 in _call_with_frames_removed
  File "<frozen importlib._bootstrap_external>", line 1023 in exec_module
  File "<frozen importlib._bootstrap>", line 935 in _load_unlocked
  File "<frozen importlib._bootstrap>", line 1331 in _find_and_load_unlocked
  File "<frozen importlib._bootstrap>", line 1360 in _find_and_load
  File "F:\JianxiaAI\ComfyUI\main.py", line 227 in <module>

[release] 鍚姩澶辫触
Traceback (most recent call last):
  File "release.py", line 52, in run_release
RuntimeError: ComfyUI 鍚姩瓒呮椂锛岃鏌ョ湅 data/runtime.log

========================================
[launcher] 鍚姩 ComfyUI
[32m[INFO][0m setup plugin alembic.autogenerate.schemas
[32m[INFO][0m setup plugin alembic.autogenerate.tables
[32m[INFO][0m setup plugin alembic.autogenerate.types
[32m[INFO][0m setup plugin alembic.autogenerate.constraints
[32m[INFO][0m setup plugin alembic.autogenerate.defaults
[32m[INFO][0m setup plugin alembic.autogenerate.comments
[32m[INFO][0m Setting output directory to: F:\JianxiaAI\output
[START] Security scan
[DONE] Security scan
## ComfyUI-Manager: installing dependencies done.
** ComfyUI startup time: 2026-09-12 21:56:47.120
** Platform: Windows
** Python version: 3.13.11 (tags/v3.13.11:6278944, Dec  5 2025, 16:26:58) [MSC v.1944 64 bit (AMD64)]
** Python executable: F:\JianxiaAI\python\python.exe
** ComfyUI Path: F:\JianxiaAI\ComfyUI
** ComfyUI Base Folder Path: F:\JianxiaAI\ComfyUI
** User directory: F:\JianxiaAI\ComfyUI\user
** ComfyUI-Manager config path: F:\JianxiaAI\ComfyUI\user\__manager\config.ini
** Log path: F:\JianxiaAI\ComfyUI\user\comfyui.log
[32m[INFO][0m
Prestartup times for custom nodes:
[32m[INFO][0m 0.0 seconds: F:\JianxiaAI\ComfyUI\custom_nodes\rgthree-comfy
[32m[INFO][0m 0.0 seconds: F:\JianxiaAI\ComfyUI\custom_nodes\comfyui-easy-use
[32m[INFO][0m 0.0 seconds: F:\JianxiaAI\ComfyUI\custom_nodes\deno-custom-nodes
[32m[INFO][0m 7.8 seconds: F:\JianxiaAI\ComfyUI\custom_nodes\ComfyUI-Manager
[32m[INFO][0m
[32m[INFO][0m Found comfy_kitchen backend eager: {'available': True, 'disabled': False, 'unavailable_reason': None, 'capabilities': ['adaln', 'apply_rope', 'apply_rope1', 'apply_rope_split_half', 'apply_rope_split_half1', 'convrot_w4a4_linear', 'dequantize_convrot_w4a4_weight', 'dequantize_int8_convrot_weight', 'dequantize_int8_convrot_weight_dtype', 'dequantize_int8_simple', 'dequantize_int8_simple_dtype', 'dequantize_mxfp8', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'gemv_awq_w4a16', 'int8_linear', 'prepare_int4_weight_for_int8_linear', 'quantize_and_rotate_rowwise', 'quantize_convrot_w4a4_weight', 'quantize_int8_convrot_weight', 'quantize_int8_rowwise', 'quantize_int8_tensorwise', 'quantize_mxfp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8', 'quantize_svdquant_w4a4', 'rms_rope', 'rms_rope1', 'rms_rope_split_half', 'rms_rope_split_half1', 'scaled_mm_mxfp8', 'scaled_mm_nvfp4', 'scaled_mm_svdquant_w4a4', 'stochastic_rounding_fp8']}
[32m[INFO][0m Found comfy_kitchen backend triton: {'available': True, 'disabled': True, 'unavailable_reason': None, 'capabilities': ['adaln', 'apply_rope', 'apply_rope1', 'apply_rope_split_half', 'apply_rope_split_half1', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'int8_linear', 'quantize_and_rotate_rowwise', 'quantize_int8_rowwise', 'quantize_mxfp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8']}
[32m[INFO][0m Found comfy_kitchen backend cuda: {'available': True, 'disabled': False, 'unavailable_reason': None, 'capabilities': ['adaln', 'apply_rope', 'apply_rope1', 'apply_rope_split_half', 'apply_rope_split_half1', 'convrot_w4a4_linear', 'dequantize_convrot_w4a4_weight', 'dequantize_int8_convrot_weight', 'dequantize_int8_convrot_weight_dtype', 'dequantize_int8_simple', 'dequantize_int8_simple_dtype', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'gemv_awq_w4a16', 'int8_linear', 'prepare_int4_weight_for_int8_linear', 'quantize_and_rotate_rowwise', 'quantize_convrot_w4a4_weight', 'quantize_int8_convrot_weight', 'quantize_int8_rowwise', 'quantize_int8_tensorwise', 'quantize_mxfp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8', 'quantize_svdquant_w4a4', 'rms_rope', 'rms_rope1', 'rms_rope_split_half', 'rms_rope_split_half1', 'scaled_mm_nvfp4', 'scaled_mm_svdquant_w4a4', 'stochastic_rounding_fp8']}
[32m[INFO][0m Checkpoint files will always be loaded safely.
[32m[INFO][0m Total VRAM 8192 MB, total RAM 32578 MB
[32m[INFO][0m pytorch version: 2.9.1+cu130
[32m[INFO][0m Set vram state to: NORMAL_VRAM
[32m[INFO][0m Device: cuda:0 NVIDIA GeForce RTX 2070 SUPER : cudaMallocAsync
[32m[INFO][0m Using async weight offloading with 2 streams
[32m[INFO][0m Enabled pinned memory 13031.0
[32m[INFO][0m working around nvidia conv3d memory bug.
[32m[INFO][0m Using pytorch attention
aimdo: src-win/cuda-detour.c:38:INFO:aimdo_setup_hooks: installing 6 hooks
aimdo: src-win/cuda-detour.c:28

EBUG:install_hook_entries: hooks successfully installed
aimdo: src-win/shmem-detect.c:80:INFO:comfy-aimdo WDDM adapter match: NVIDIA GeForce RTX 2070 SUPER runtime_luid=00000000:0333c13d dxgi_luid=00000000:0333c13d
aimdo: src/control.c:248:INFO:comfy-aimdo inited for GPU: NVIDIA GeForce RTX 2070 SUPER (VRAM: 8191 MB)
[32m[INFO][0m DynamicVRAM support detected and enabled
[32m[INFO][0m Python version: 3.13.11 (tags/v3.13.11:6278944, Dec  5 2025, 16:26:58) [MSC v.1944 64 bit (AMD64)]
[32m[INFO][0m ComfyUI version: 0.26.2
[32m[INFO][0m comfy-aimdo version: 0.4.10
[32m[INFO][0m comfy-kitchen version: 0.2.21
[32m[INFO][0m comfyui-frontend-package version: 1.45.19
[32m[INFO][0m comfyui-workflow-templates version: 0.10.7
[32m[INFO][0m comfyui-embedded-docs version: 0.5.5
[32m[INFO][0m comfy-kitchen version: 0.2.21
[32m[INFO][0m comfy-aimdo version: 0.4.10
[32m[INFO][0m [Prompt Server] web root: F:\JianxiaAI\python\Lib\site-packages\comfyui_frontend_package\static
[32m[INFO][0m Asset seeder disabled
Web extensions folder found at F:\JianxiaAI\ComfyUI\web\extensions\ComfyLiterals
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1789221455.511101 15652 port.cc:153] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1789221462.113337 15652 port.cc:153] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
[34m[ComfyUI-Easy-Use] server: [0mv1.3.6 [92mLoaded[0m
[34m[ComfyUI-Easy-Use] web root: [0mF:\JianxiaAI\ComfyUI\custom_nodes\comfyui-easy-use\web_version/v2 [92mLoaded[0m
[32m[INFO][0m ComfyUI-GGUF: Allowing full torch compile
[32m[INFO][0m ### Loading: ComfyUI-Impact-Pack (V8.28.2)
[32m[INFO][0m [Impact Pack] Wildcard total size (0.00 MB) is within cache limit (50.00 MB). Using full cache mode.
[32m[INFO][0m [Impact Pack] Wildcards loading done.
[krea2edit] nodes vunknown loaded
[32m[INFO][0m ### Loading: ComfyUI-Manager (V3.39.2)
[32m[INFO][0m [ComfyUI-Manager] network_mode: public
[32m[INFO][0m [ComfyUI-Manager] ComfyUI per-queue preview override detected (PR #11261). Manager's preview method feature is disabled. Use ComfyUI's --preview-method CLI option or 'Settings > Execution > Live preview method'.
[32m[INFO][0m ### ComfyUI Revision: UNKNOWN (The currently installed ComfyUI is not a Git repository)
[32m[INFO][0m [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/alter-list.json
[32m[INFO][0m [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/model-list.json
[32m[INFO][0m [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/github-stats.json
F:\JianxiaAI\python\Lib\site-packages\timm\models\layers\__init__.py:49: FutureWarning: Importing from timm.models.layers is deprecated, please import via timm.layers
  warnings.warn(f"Importing from {__name__} is deprecated, please import via timm.layers", FutureWarning)
[34m[ComfyUI-RMBG][0m v[93m3.0.0[0m | [93m43 nodes[0m [92mLoaded[0m
(pysssss:WD14Tagger) [DEBUG] Available ORT providers: TensorrtExecutionProvider, CUDAExecutionProvider, CPUExecutionProvider
(pysssss:WD14Tagger) [DEBUG] Using ORT providers: CUDAExecutionProvider, CPUExecutionProvider
### ComfyUI-Workflow-Encrypt: Copy .js from 'F:\JianxiaAI\ComfyUI\custom_nodes\comfyui-workflow-encrypt\js\comfyui-workflow-encrypt.js' to 'F:\JianxiaAI\ComfyUI\web\extensions\comfyui-workflow-encrypt'
------------------------------------------
[34mComfyroll Studio v1.76 : [92m 175 Nodes Loaded[0m
------------------------------------------
** For changes, please see patch notes at https://github.com/Suzie1/ComfyUI_Comfyroll_CustomNodes/blob/main/Patch_Notes.md
** For help, please see the wiki at https://github.com/Suzie1/ComfyUI_Comfyroll_CustomNodes/wiki
------------------------------------------
[36;20m[F:\JianxiaAI\ComfyUI\custom_nodes\comfyui_controlnet_aux] | INFO -> Using ckpts path: F:\JianxiaAI\ComfyUI\custom_nodes\comfyui_controlnet_aux\ckpts[0m
[36;20m[F:\JianxiaAI\ComfyUI\custom_nodes\comfyui_controlnet_aux] | INFO -> Using symlinks: False[0m
[36;20m[F:\JianxiaAI\ComfyUI\custom_nodes\comfyui_controlnet_aux] | INFO -> Using ort providers: ['CUDAExecutionProvider', 'DirectMLExecutionProvider', 'OpenVINOExecutionProvider', 'ROCMExecutionProvider', 'MIGraphXExecutionProvider', 'CPUExecutionProvider', 'CoreMLExecutionProvider'][0m
DWPose: Onnxruntime with acceleration providers detected
[32m[INFO][0m [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/extension-node-map.json
[32m[INFO][0m ('Looking for cached Spacy xx_sent_ud_sm.',)
[32m[INFO][0m ('Downloading Spacy xx_sent_ud_sm.',)
Collecting xx-sent-ud-sm==3.8.0
[32m[INFO][0m [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/custom-node-list.json
  Downloading https://github.com/explosion/spacy-models/releases/download/xx_sent_ud_sm-3.8.0/xx_sent_ud_sm-3.8.0-py3-none-any.whl (4.3 MB)
FETCH ComfyRegistry Data: 5/186
FETCH ComfyRegistry Data: 10/186
FETCH ComfyRegistry Data: 15/186
FETCH ComfyRegistry Data: 20/186
FETCH ComfyRegistry Data: 25/186
FETCH ComfyRegistry Data: 30/186
FETCH ComfyRegistry Data: 35/186

[release] 鍚姩澶辫触
Traceback (most recent call last):
  File "release.py", line 52, in run_release
RuntimeError: ComfyUI 鍚姩瓒呮椂锛岃鏌ョ湅 data/runtime.log

========================================
[launcher] 鍚姩 ComfyUI
[32m[INFO][0m setup plugin alembic.autogenerate.schemas
[32m[INFO][0m setup plugin alembic.autogenerate.tables
[32m[INFO][0m setup plugin alembic.autogenerate.types
[32m[INFO][0m setup plugin alembic.autogenerate.constraints
[32m[INFO][0m setup plugin alembic.autogenerate.defaults
[32m[INFO][0m setup plugin alembic.autogenerate.comments
[32m[INFO][0m Setting output directory to: F:\JianxiaAI\output
[START] Security scan
[DONE] Security scan
## ComfyUI-Manager: installing dependencies done.
** ComfyUI startup time: 2026-09-12 22:03:20.185
** Platform: Windows
** Python version: 3.13.11 (tags/v3.13.11:6278944, Dec  5 2025, 16:26:58) [MSC v.1944 64 bit (AMD64)]
** Python executable: F:\JianxiaAI\python\python.exe
** ComfyUI Path: F:\JianxiaAI\ComfyUI
** ComfyUI Base Folder Path: F:\JianxiaAI\ComfyUI
** User directory: F:\JianxiaAI\ComfyUI\user
** ComfyUI-Manager config path: F:\JianxiaAI\ComfyUI\user\__manager\config.ini
** Log path: F:\JianxiaAI\ComfyUI\user\comfyui.log
[32m[INFO][0m
Prestartup times for custom nodes:
[32m[INFO][0m 0.0 seconds: F:\JianxiaAI\ComfyUI\custom_nodes\rgthree-comfy
[32m[INFO][0m 0.0 seconds: F:\JianxiaAI\ComfyUI\custom_nodes\comfyui-easy-use
[32m[INFO][0m 0.0 seconds: F:\JianxiaAI\ComfyUI\custom_nodes\deno-custom-nodes
[32m[INFO][0m 7.1 seconds: F:\JianxiaAI\ComfyUI\custom_nodes\ComfyUI-Manager
[32m[INFO][0m
[32m[INFO][0m Found comfy_kitchen backend triton: {'available': True, 'disabled': True, 'unavailable_reason': None, 'capabilities': ['adaln', 'apply_rope', 'apply_rope1', 'apply_rope_split_half', 'apply_rope_split_half1', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'int8_linear', 'quantize_and_rotate_rowwise', 'quantize_int8_rowwise', 'quantize_mxfp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8']}
[32m[INFO][0m Found comfy_kitchen backend cuda: {'available': True, 'disabled': False, 'unavailable_reason': None, 'capabilities': ['adaln', 'apply_rope', 'apply_rope1', 'apply_rope_split_half', 'apply_rope_split_half1', 'convrot_w4a4_linear', 'dequantize_convrot_w4a4_weight', 'dequantize_int8_convrot_weight', 'dequantize_int8_convrot_weight_dtype', 'dequantize_int8_simple', 'dequantize_int8_simple_dtype', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'gemv_awq_w4a16', 'int8_linear', 'prepare_int4_weight_for_int8_linear', 'quantize_and_rotate_rowwise', 'quantize_convrot_w4a4_weight', 'quantize_int8_convrot_weight', 'quantize_int8_rowwise', 'quantize_int8_tensorwise', 'quantize_mxfp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8', 'quantize_svdquant_w4a4', 'rms_rope', 'rms_rope1', 'rms_rope_split_half', 'rms_rope_split_half1', 'scaled_mm_nvfp4', 'scaled_mm_svdquant_w4a4', 'stochastic_rounding_fp8']}
[32m[INFO][0m Found comfy_kitchen backend eager: {'available': True, 'disabled': False, 'unavailable_reason': None, 'capabilities': ['adaln', 'apply_rope', 'apply_rope1', 'apply_rope_split_half', 'apply_rope_split_half1', 'convrot_w4a4_linear', 'dequantize_convrot_w4a4_weight', 'dequantize_int8_convrot_weight', 'dequantize_int8_convrot_weight_dtype', 'dequantize_int8_simple', 'dequantize_int8_simple_dtype', 'dequantize_mxfp8', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'gemv_awq_w4a16', 'int8_linear', 'prepare_int4_weight_for_int8_linear', 'quantize_and_rotate_rowwise', 'quantize_convrot_w4a4_weight', 'quantize_int8_convrot_weight', 'quantize_int8_rowwise', 'quantize_int8_tensorwise', 'quantize_mxfp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8', 'quantize_svdquant_w4a4', 'rms_rope', 'rms_rope1', 'rms_rope_split_half', 'rms_rope_split_half1', 'scaled_mm_mxfp8', 'scaled_mm_nvfp4', 'scaled_mm_svdquant_w4a4', 'stochastic_rounding_fp8']}
[32m[INFO][0m Checkpoint files will always be loaded safely.
[32m[INFO][0m Total VRAM 8192 MB, total RAM 32578 MB
[32m[INFO][0m pytorch version: 2.9.1+cu130
[32m[INFO][0m Set vram state to: NORMAL_VRAM
[32m[INFO][0m Device: cuda:0 NVIDIA GeForce RTX 2070 SUPER : cudaMallocAsync
[32m[INFO][0m Using async weight offloading with 2 streams
[32m[INFO][0m Enabled pinned memory 13031.0
[32m[INFO][0m working around nvidia conv3d memory bug.
[32m[INFO][0m Using pytorch attention
aimdo: src-win/cuda-detour.c:38:INFO:aimdo_setup_hooks: installing 6 hooks
aimdo: src-win/cuda-detour.c:28

EBUG:install_hook_entries: hooks successfully installed
aimdo: src-win/shmem-detect.c:80:INFO:comfy-aimdo WDDM adapter match: NVIDIA GeForce RTX 2070 SUPER runtime_luid=00000000:0000cc28 dxgi_luid=00000000:0000cc28
aimdo: src/control.c:248:INFO:comfy-aimdo inited for GPU: NVIDIA GeForce RTX 2070 SUPER (VRAM: 8191 MB)
[32m[INFO][0m DynamicVRAM support detected and enabled
[32m[INFO][0m Python version: 3.13.11 (tags/v3.13.11:6278944, Dec  5 2025, 16:26:58) [MSC v.1944 64 bit (AMD64)]
[32m[INFO][0m ComfyUI version: 0.26.2
[32m[INFO][0m comfy-aimdo version: 0.4.10
[32m[INFO][0m comfy-kitchen version: 0.2.21
[32m[INFO][0m comfyui-frontend-package version: 1.45.19
[32m[INFO][0m comfyui-workflow-templates version: 0.10.7
[32m[INFO][0m comfyui-embedded-docs version: 0.5.5
[32m[INFO][0m comfy-kitchen version: 0.2.21
[32m[INFO][0m comfy-aimdo version: 0.4.10
[32m[INFO][0m [Prompt Server] web root: F:\JianxiaAI\python\Lib\site-packages\comfyui_frontend_package\static
[32m[INFO][0m Asset seeder disabled
Web extensions folder found at F:\JianxiaAI\ComfyUI\web\extensions\ComfyLiterals
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1789221847.026051 8776 port.cc:153] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1789221853.750008 8776 port.cc:153] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
[34m[ComfyUI-Easy-Use] server: [0mv1.3.6 [92mLoaded[0m
[34m[ComfyUI-Easy-Use] web root: [0mF:\JianxiaAI\ComfyUI\custom_nodes\comfyui-easy-use\web_version/v2 [92mLoaded[0m
[32m[INFO][0m ComfyUI-GGUF: Allowing full torch compile
[32m[INFO][0m ### Loading: ComfyUI-Impact-Pack (V8.28.2)
[32m[INFO][0m [Impact Pack] Wildcard total size (0.00 MB) is within cache limit (50.00 MB). Using full cache mode.
[32m[INFO][0m [Impact Pack] Wildcards loading done.
[krea2edit] nodes vunknown loaded
[32m[INFO][0m ### Loading: ComfyUI-Manager (V3.39.2)
[32m[INFO][0m [ComfyUI-Manager] network_mode: public
[32m[INFO][0m [ComfyUI-Manager] ComfyUI per-queue preview override detected (PR #11261). Manager's preview method feature is disabled. Use ComfyUI's --preview-method CLI option or 'Settings > Execution > Live preview method'.
[32m[INFO][0m ### ComfyUI Revision: UNKNOWN (The currently installed ComfyUI is not a Git repository)
[32m[INFO][0m [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/model-list.json
[32m[INFO][0m [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/alter-list.json
F:\JianxiaAI\python\Lib\site-packages\timm\models\layers\__init__.py:49: FutureWarning: Importing from timm.models.layers is deprecated, please import via timm.layers
  warnings.warn(f"Importing from {__name__} is deprecated, please import via timm.layers", FutureWarning)
[34m[ComfyUI-RMBG][0m v[93m3.0.0[0m | [93m43 nodes[0m [92mLoaded[0m
[32m[INFO][0m [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/github-stats.json
(pysssss:WD14Tagger) [DEBUG] Available ORT providers: TensorrtExecutionProvider, CUDAExecutionProvider, CPUExecutionProvider
(pysssss:WD14Tagger) [DEBUG] Using ORT providers: CUDAExecutionProvider, CPUExecutionProvider
### ComfyUI-Workflow-Encrypt: Copy .js from 'F:\JianxiaAI\ComfyUI\custom_nodes\comfyui-workflow-encrypt\js\comfyui-workflow-encrypt.js' to 'F:\JianxiaAI\ComfyUI\web\extensions\comfyui-workflow-encrypt'
------------------------------------------
[34mComfyroll Studio v1.76 : [92m 175 Nodes Loaded[0m
------------------------------------------
** For changes, please see patch notes at https://github.com/Suzie1/ComfyUI_Comfyroll_CustomNodes/blob/main/Patch_Notes.md
** For help, please see the wiki at https://github.com/Suzie1/ComfyUI_Comfyroll_CustomNodes/wiki
------------------------------------------
[36;20m[F:\JianxiaAI\ComfyUI\custom_nodes\comfyui_controlnet_aux] | INFO -> Using ckpts path: F:\JianxiaAI\ComfyUI\custom_nodes\comfyui_controlnet_aux\ckpts[0m
[36;20m[F:\JianxiaAI\ComfyUI\custom_nodes\comfyui_controlnet_aux] | INFO -> Using symlinks: False[0m
[36;20m[F:\JianxiaAI\ComfyUI\custom_nodes\comfyui_controlnet_aux] | INFO -> Using ort providers: ['CUDAExecutionProvider', 'DirectMLExecutionProvider', 'OpenVINOExecutionProvider', 'ROCMExecutionProvider', 'MIGraphXExecutionProvider', 'CPUExecutionProvider', 'CoreMLExecutionProvider'][0m
DWPose: Onnxruntime with acceleration providers detected
[32m[INFO][0m [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/extension-node-map.json
[32m[INFO][0m ('Looking for cached Spacy xx_sent_ud_sm.',)
[32m[INFO][0m ('Downloading Spacy xx_sent_ud_sm.',)
Collecting xx-sent-ud-sm==3.8.0
  Downloading https://github.com/explosion/spacy-models/releases/download/xx_sent_ud_sm-3.8.0/xx_sent_ud_sm-3.8.0-py3-none-any.whl (4.3 MB)
[32m[INFO][0m [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/custom-node-list.json
FETCH ComfyRegistry Data: 5/186
FETCH ComfyRegistry Data: 10/186
FETCH ComfyRegistry Data: 15/186
FETCH ComfyRegistry Data: 20/186
FETCH ComfyRegistry Data: 25/186
FETCH ComfyRegistry Data: 30/186
FETCH ComfyRegistry Data: 35/186
FETCH ComfyRegistry Data: 40/186
FETCH ComfyRegistry Data: 45/186
FETCH ComfyRegistry Data: 50/186
FETCH ComfyRegistry Data: 55/186
FETCH ComfyRegistry Data: 60/186
   ---------------------------------------- 4.3/4.3 MB 30.4 kB/s  0:02:37

[notice] A new release of pip is available: 25.3 -> 26.2.1
[notice] To update, run: python.exe -m pip install --upgrade pip
[38;5;2m鉁 Download and installation successful[0m
You can now load the package via spacy.load('xx_sent_ud_sm')
[32m[INFO][0m ('Spacy xx_sent_ud_sm successfully cached.',)
[1;35m
### [START] ComfyUI AlekPet Nodes [1;34mv1.0.92[0m[1;35m ###[0m
[92mNode -> ArgosTranslateNode: [93mArgosTranslateCLIPTextEncodeNode, ArgosTranslateTextNode[0m [92m[92m[Loading][0m[0m
[92mNode -> ChatGLMNode[92m[92m[Loading][0m[0m
[92mNode -> DeepTranslatorNode: [93mDeepTranslatorCLIPTextEncodeNode, DeepTranslatorTextNode[0m [92m[92m[Loading][0m[0m
[92mNode -> ExtrasNode: [93mPreviewTextNode, HexToHueNode, ColorsCorrectNode[0m [92m[92m[Loading][0m[0m
[92mNode -> GoogleTranslateNode: [93mGoogleTranslateCLIPTextEncodeNode, GoogleTranslateTextNode[0m [92m[92m[Loading][0m[0m
[92mNode -> IDENode: [93mIDENode[0m [92m[92m[Loading][0m[0m
[92mNode -> PainterNode: [93mPainterNode[0m [92m[92m[Loading][0m[0m
[92mNode -> PoseNode: [93mPoseNode[0m [92m[92m[Loading][0m[0m
[1;35m### [END] ComfyUI AlekPet Nodes ###[0m
# 馃樅dzNodes: LayerStyle -> [1;33mCannot import name 'guidedFilter' from 'cv2.ximgproc'
A few nodes cannot works properly, while most nodes are not affected. Please REINSTALL package 'opencv-contrib-python'.
For detail refer to [4mhttps://github.com/chflame163/ComfyUI_LayerStyle/issues/5[0m[m

[92m[rgthree-comfy] Loaded 48 epic nodes. 馃帀[0m

[33m[rgthree-comfy] ComfyUI's new Node 2.0 rendering may be incompatible with some rgthree-comfy nodes and features, breaking some rendering as well as losing the ability to access a node's properties (a vital part of many nodes). It also appears to run MUCH more slowly spiking CPU usage and causing jankiness and unresponsiveness, especially with large workflows. Personally I am not planning to use the new Nodes 2.0 and, unfortunately, am not able to invest the time to investigate and overhaul rgthree-comfy where needed. If you have issues when Nodes 2.0 is enabled, I'd urge you to switch it off as well and join me in hoping ComfyUI is not planning to deprecate the existing, stable canvas rendering all together.
[0m
鈿 SeedVR2 optimizations check: SageAttention 鉁 | Flash Attention 鉂 | Triton 鉁
馃挕 Optional: pip install flash-attn
馃敡 Conv3d workaround active: PyTorch 2.9.1, cuDNN 91200 (fixing VAE 3x memory bug)
馃搳 Initial CUDA memory: 6.91GB free / 8.00GB total
FETCH ComfyRegistry Data: 65/186
[34mWAS Node Suite: [0mOpenCV Python FFMPEG support is enabled[0m
[34mWAS Node Suite [93mWarning: [0m`ffmpeg_bin_path` is not set in `F:\JianxiaAI\ComfyUI\custom_nodes\was-ns\was_suite_config.json` config file. Will attempt to use system ffmpeg binaries if available.[0m
[34mWAS Node Suite: [0mFinished.[0m [32mLoaded[0m [0m220[0m [32mnodes successfully.[0m

[3m[93m"Art is the most powerful tool we have to connect with the world and express our individuality."[0m[3m - Unknown[0m

[32m[INFO][0m
Import times for custom nodes:
[32m[INFO][0m 0.0 seconds: F:\JianxiaAI\ComfyUI\custom_nodes\websocket_image_save.py
[32m[INFO][0m 0.0 seconds: F:\JianxiaAI\ComfyUI\custom_nodes\image-size-tools
[32m[INFO][0m 0.0 seconds: F:\JianxiaAI\ComfyUI\custom_nodes\comfyui-splitstring
[32m[INFO][0m 0.0 seconds: F:\JianxiaAI\ComfyUI\custom_nodes\ComfyUI_zip
[32m[INFO][0m 0.0 seconds: F:\JianxiaAI\ComfyUI\custom_nodes\qweneditutils
[32m[INFO][0m 0.0 seconds: F:\JianxiaAI\ComfyUI\custom_nodes\ComfyUI-DD-Translation
[32m[INFO][0m 0.0 seconds: F:\JianxiaAI\ComfyUI\custom_nodes\ComfyUI-Krea2-Projector-Tuner-2.2.0
[32m[INFO][0m 0.0 seconds: F:\JianxiaAI\ComfyUI\custom_nodes\ComfyUI-Krea2-Ostris-Edit
[32m[INFO][0m 0.0 seconds: F:\JianxiaAI\ComfyUI\custom_nodes\ComfyUI-ZImage-Caption-Tuner
[32m[INFO][0m 0.0 seconds: F:\JianxiaAI\ComfyUI\custom_nodes\erosdiffusion-eulerflowmatchingdiscretescheduler
[32m[INFO][0m 0.0 seconds: F:\JianxiaAI\ComfyUI\custom_nodes\comfyui-krea2edit
[32m[INFO][0m 0.0 seconds: F:\JianxiaAI\ComfyUI\custom_nodes\ComfyUI-GGUF
[32m[INFO][0m 0.0 seconds: F:\JianxiaAI\ComfyUI\custom_nodes\gguf
[32m[INFO][0m 0.0 seconds: F:\JianxiaAI\ComfyUI\custom_nodes\ComfyUI_IPAdapter_plus
[32m[INFO][0m 0.0 seconds: F:\JianxiaAI\ComfyUI\custom_nodes\ComfyUI_UltimateSDUpscale
[32m[INFO][0m 0.0 seconds: F:\JianxiaAI\ComfyUI\custom_nodes\comfyui-wd14-tagger
[32m[INFO][0m 0.0 seconds: F:\JianxiaAI\ComfyUI\custom_nodes\ComfyUI-Conditioning-Rebalance
[32m[INFO][0m 0.0 seconds: F:\JianxiaAI\ComfyUI\custom_nodes\flashvsr_ultra_fast
[32m[INFO][0m 0.1 seconds: F:\JianxiaAI\ComfyUI\custom_nodes\rgthree-comfy
[32m[INFO][0m 0.1 seconds: F:\JianxiaAI\ComfyUI\custom_nodes\comfyui-custom-scripts
[32m[INFO][0m 0.1 seconds: F:\JianxiaAI\ComfyUI\custom_nodes\comfyui_essentials
[32m[INFO][0m 0.1 seconds: F:\JianxiaAI\ComfyUI\custom_nodes\ComfyLiterals
[32m[INFO][0m 0.1 seconds: F:\JianxiaAI\ComfyUI\custom_nodes\comfyui-workflow-encrypt
[32m[INFO][0m 0.1 seconds: F:\JianxiaAI\ComfyUI\custom_nodes\ComfyUI_Qwen3-VL-Instruct
[32m[INFO][0m 0.1 seconds: F:\JianxiaAI\ComfyUI\custom_nodes\deno-custom-nodes
[32m[INFO][0m 0.2 seconds: F:\JianxiaAI\ComfyUI\custom_nodes\comfyui-kjnodes
[32m[INFO][0m 0.2 seconds: F:\JianxiaAI\ComfyUI\custom_nodes\comfyui_controlnet_aux
[32m[INFO][0m 0.2 seconds: F:\JianxiaAI\ComfyUI\custom_nodes\ComfyUI_Comfyroll_CustomNodes
[32m[INFO][0m 0.2 seconds: F:\JianxiaAI\ComfyUI\custom_nodes\ComfyUI-Manager
[32m[INFO][0m 0.4 seconds: F:\JianxiaAI\ComfyUI\custom_nodes\ComfyUI-LTXVideo
[32m[INFO][0m 0.5 seconds: F:\JianxiaAI\ComfyUI\custom_nodes\ComfyUI-VideoHelperSuite
[32m[INFO][0m 0.7 seconds: F:\JianxiaAI\ComfyUI\custom_nodes\ComfyUI_LayerStyle
[32m[INFO][0m 0.8 seconds: F:\JianxiaAI\ComfyUI\custom_nodes\seedvr2_videoupscaler
[32m[INFO][0m 1.0 seconds: F:\JianxiaAI\ComfyUI\custom_nodes\ComfyUI-Impact-Pack
[32m[INFO][0m 1.3 seconds: F:\JianxiaAI\ComfyUI\custom_nodes\ComfyUI-WanVideoWrapper
[32m[INFO][0m 2.9 seconds: F:\JianxiaAI\ComfyUI\custom_nodes\was-ns
[32m[INFO][0m 3.6 seconds: F:\JianxiaAI\ComfyUI\custom_nodes\ComfyUI-RMBG
[32m[INFO][0m 22.9 seconds: F:\JianxiaAI\ComfyUI\custom_nodes\comfyui-easy-use
[32m[INFO][0m  168.3 seconds: F:\JianxiaAI\ComfyUI\custom_nodes\ComfyUI_Custom_Nodes_AlekPet
[32m[INFO][0m
[32m[INFO][0m Context impl SQLiteImpl.
[32m[INFO][0m Will assume non-transactional DDL.
[32m[INFO][0m Using RAM pressure cache.
[32m[INFO][0m Starting server

[32m[INFO][0m To see the GUI go to: http://127.0.0.1:8188
FETCH ComfyRegistry Data: 70/186
FETCH ComfyRegistry Data: 75/186
FETCH ComfyRegistry Data: 80/186
FETCH ComfyRegistry Data: 85/186
FETCH ComfyRegistry Data: 90/186
FETCH ComfyRegistry Data: 95/186
FETCH ComfyRegistry Data: 100/186
FETCH ComfyRegistry Data: 105/186
FETCH ComfyRegistry Data: 110/186
FETCH ComfyRegistry Data: 115/186
FETCH ComfyRegistry Data: 120/186
FETCH ComfyRegistry Data: 125/186

lsms0977 发表于 2026-9-12 18:46:22

不能用参考图换脸吗？反正我没有成功过

静若 发表于 2026-9-12 00:08:41

tcar 发表于 2026-9-11 13:16
我把原来的日志删了重新生成了一个
========================================
[launcher] 启动 Comfy ...

这次核心报错问题：cudaGetDeviceCount() returned cudaErrorNotSupported
原因是 PyTorch环境在调用 CUDA 接口返回不支持，两种最常见情况：显卡驱动版本过低 / 显卡硬件 / 驱动异常，PyTorch 无法识别 GPU。
解决方法优先更新显卡驱动：CUDA必须不能低于13.3

tcar 发表于 2026-9-11 13:16:16

静若发表于 2026-9-11 01:43
路径不要用中文，这是中文路径导致的报错，请把路径重命名为简短纯英文路径
...

我把原来的日志删了重新生成了一个
========================================
[launcher] 启动 ComfyUI
[32m[INFO][0m setup plugin alembic.autogenerate.schemas
[32m[INFO][0m setup plugin alembic.autogenerate.tables
[32m[INFO][0m setup plugin alembic.autogenerate.types
[32m[INFO][0m setup plugin alembic.autogenerate.constraints
[32m[INFO][0m setup plugin alembic.autogenerate.defaults
[32m[INFO][0m setup plugin alembic.autogenerate.comments
[32m[INFO][0m Setting output directory to: F:\JianxiaAI\output
[START] Security scan
[DONE] Security scan
## ComfyUI-Manager: installing dependencies done.
** ComfyUI startup time: 2026-09-11 13:11:59.539
** Platform: Windows
** Python version: 3.13.11 (tags/v3.13.11:6278944, Dec  5 2025, 16:26:58) [MSC v.1944 64 bit (AMD64)]
** Python executable: F:\JianxiaAI\python\python.exe
** ComfyUI Path: F:\JianxiaAI\ComfyUI
** ComfyUI Base Folder Path: F:\JianxiaAI\ComfyUI
** User directory: F:\JianxiaAI\ComfyUI\user
** ComfyUI-Manager config path: F:\JianxiaAI\ComfyUI\user\__manager\config.ini
** Log path: F:\JianxiaAI\ComfyUI\user\comfyui.log
[32m[INFO][0m
Prestartup times for custom nodes:
[32m[INFO][0m 0.0 seconds: F:\JianxiaAI\ComfyUI\custom_nodes\rgthree-comfy
[32m[INFO][0m 0.0 seconds: F:\JianxiaAI\ComfyUI\custom_nodes\comfyui-easy-use
[32m[INFO][0m 0.0 seconds: F:\JianxiaAI\ComfyUI\custom_nodes\deno-custom-nodes
[32m[INFO][0m 3.1 seconds: F:\JianxiaAI\ComfyUI\custom_nodes\ComfyUI-Manager
[32m[INFO][0m
F:\JianxiaAI\python\Lib\site-packages\torch\cuda\__init__.py:182: UserWarning: cudaGetDeviceCount() returned cudaErrorNotSupported, likely using older driver or on CPU machine (Triggered internally at C:\actions-runner\_work\pytorch\pytorch\pytorch\c10\cuda\CUDAFunctions.cpp:88.)
  return torch._C._cuda_getDeviceCount() > 0
[32m[INFO][0m Found comfy_kitchen backend triton: {'available': False, 'disabled': True, 'unavailable_reason': 'Neither CUDA nor XPU available on this system', 'capabilities': []}
[32m[INFO][0m Found comfy_kitchen backend eager: {'available': True, 'disabled': False, 'unavailable_reason': None, 'capabilities': ['adaln', 'apply_rope', 'apply_rope1', 'apply_rope_split_half', 'apply_rope_split_half1', 'convrot_w4a4_linear', 'dequantize_convrot_w4a4_weight', 'dequantize_int8_convrot_weight', 'dequantize_int8_convrot_weight_dtype', 'dequantize_int8_simple', 'dequantize_int8_simple_dtype', 'dequantize_mxfp8', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'gemv_awq_w4a16', 'int8_linear', 'prepare_int4_weight_for_int8_linear', 'quantize_and_rotate_rowwise', 'quantize_convrot_w4a4_weight', 'quantize_int8_convrot_weight', 'quantize_int8_rowwise', 'quantize_int8_tensorwise', 'quantize_mxfp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8', 'quantize_svdquant_w4a4', 'rms_rope', 'rms_rope1', 'rms_rope_split_half', 'rms_rope_split_half1', 'scaled_mm_mxfp8', 'scaled_mm_nvfp4', 'scaled_mm_svdquant_w4a4', 'stochastic_rounding_fp8']}
[32m[INFO][0m Found comfy_kitchen backend cuda: {'available': False, 'disabled': False, 'unavailable_reason': 'CUDA not available on this system', 'capabilities': []}
[32m[INFO][0m Checkpoint files will always be loaded safely.
Windows fatal exception: access violation

Stack (most recent call first):
  File "F:\JianxiaAI\python\Lib\site-packages\torch\cuda\__init__.py", line 410 in _lazy_init
  File "F:\JianxiaAI\python\Lib\site-packages\torch\cuda\__init__.py", line 1069 in current_device
  File "F:\JianxiaAI\ComfyUI\comfy\model_management.py", line 211 in get_torch_device
  File "F:\JianxiaAI\ComfyUI\comfy\model_management.py", line 362 in <module>
  File "<frozen importlib._bootstrap>", line 488 in _call_with_frames_removed
  File "<frozen importlib._bootstrap_external>", line 1023 in exec_module
  File "<frozen importlib._bootstrap>", line 935 in _load_unlocked
  File "<frozen importlib._bootstrap>", line 1331 in _find_and_load_unlocked
  File "<frozen importlib._bootstrap>", line 1360 in _find_and_load
  File "F:\JianxiaAI\ComfyUI\execution.py", line 18 in <module>
  File "<frozen importlib._bootstrap>", line 488 in _call_with_frames_removed
  File "<frozen importlib._bootstrap_external>", line 1023 in exec_module
  File "<frozen importlib._bootstrap>", line 935 in _load_unlocked
  File "<frozen importlib._bootstrap>", line 1331 in _find_and_load_unlocked
  File "<frozen importlib._bootstrap>", line 1360 in _find_and_load
  File "F:\JianxiaAI\ComfyUI\main.py", line 227 in <module>

[release] 启动失败
Traceback (most recent call last):
  File "release.py", line 52, in run_release
RuntimeError: ComfyUI 启动超时，请查看 data/runtime.log

tcar 发表于 2026-9-11 12:50:25

静若发表于 2026-9-11 01:43
路径不要用中文，这是中文路径导致的报错，请把路径重命名为简短纯英文路径
...

我可能没说明白第一次再中文路径进不去我就试过把路径换成英文的结果还是超时最后才把这个发上来。。。后面已经换成纯英文路径了还是超时

静若 发表于 2026-9-11 01:43:44

tcar 发表于 2026-9-10 18:37
打开显示超时这是为啥
========================================
[launcher] 鍚姩 ComfyUI

路径不要用中文，这是中文路径导致的报错，请把路径重命名为简短纯英文路径

sabermine1993 发表于 2026-9-11 01:14:20

单图修改没有变化啊，感觉就是放大了

tcar 发表于 2026-9-10 18:37:43

打开显示超时  这是为啥
========================================
[launcher] 鍚姩 ComfyUI
[32m[INFO][0m setup plugin alembic.autogenerate.schemas
[32m[INFO][0m setup plugin alembic.autogenerate.tables
[32m[INFO][0m setup plugin alembic.autogenerate.types
[32m[INFO][0m setup plugin alembic.autogenerate.constraints
[32m[INFO][0m setup plugin alembic.autogenerate.defaults
[32m[INFO][0m setup plugin alembic.autogenerate.comments
[32m[INFO][0m Setting output directory to: F:\ai绘画\JianxiaAI-CreativePack-v2.2\output
[START] Security scan
[DONE] Security scan
## ComfyUI-Manager: installing dependencies done.
** ComfyUI startup time: 2026-09-10 12:49:41.501
** Platform: Windows
** Python version: 3.13.11 (tags/v3.13.11:6278944, Dec  5 2025, 16:26:58) [MSC v.1944 64 bit (AMD64)]
** Python executable: F:\ai缁樼敾\JianxiaAI-CreativePack-v2.2\python\python.exe
** ComfyUI Path: F:\ai缁樼敾\JianxiaAI-CreativePack-v2.2\ComfyUI
** ComfyUI Base Folder Path: F:\ai缁樼敾\JianxiaAI-CreativePack-v2.2\ComfyUI
** User directory: F:\ai缁樼敾\JianxiaAI-CreativePack-v2.2\ComfyUI\user
** ComfyUI-Manager config path: F:\ai缁樼敾\JianxiaAI-CreativePack-v2.2\ComfyUI\user\__manager\config.ini
** Log path: F:\ai缁樼敾\JianxiaAI-CreativePack-v2.2\ComfyUI\user\comfyui.log
[32m[INFO][0m
Prestartup times for custom nodes:
[32m[INFO][0m 0.0 seconds: F:\ai绘画\JianxiaAI-CreativePack-v2.2\ComfyUI\custom_nodes\rgthree-comfy
[32m[INFO][0m 0.0 seconds: F:\ai绘画\JianxiaAI-CreativePack-v2.2\ComfyUI\custom_nodes\deno-custom-nodes
[32m[INFO][0m 0.0 seconds: F:\ai绘画\JianxiaAI-CreativePack-v2.2\ComfyUI\custom_nodes\comfyui-easy-use
[32m[INFO][0m 4.4 seconds: F:\ai绘画\JianxiaAI-CreativePack-v2.2\ComfyUI\custom_nodes\ComfyUI-Manager
[32m[INFO][0m
F:\ai缁樼敾\JianxiaAI-CreativePack-v2.2\python\Lib\site-packages\torch\cuda\__init__.py:182: UserWarning: cudaGetDeviceCount() returned cudaErrorNotSupported, likely using older driver or on CPU machine (Triggered internally at C:\actions-runner\_work\pytorch\pytorch\pytorch\c10\cuda\CUDAFunctions.cpp:88.)
  return torch._C._cuda_getDeviceCount() > 0
[32m[INFO][0m Found comfy_kitchen backend eager: {'available': True, 'disabled': False, 'unavailable_reason': None, 'capabilities': ['adaln', 'apply_rope', 'apply_rope1', 'apply_rope_split_half', 'apply_rope_split_half1', 'convrot_w4a4_linear', 'dequantize_convrot_w4a4_weight', 'dequantize_int8_convrot_weight', 'dequantize_int8_convrot_weight_dtype', 'dequantize_int8_simple', 'dequantize_int8_simple_dtype', 'dequantize_mxfp8', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'gemv_awq_w4a16', 'int8_linear', 'prepare_int4_weight_for_int8_linear', 'quantize_and_rotate_rowwise', 'quantize_convrot_w4a4_weight', 'quantize_int8_convrot_weight', 'quantize_int8_rowwise', 'quantize_int8_tensorwise', 'quantize_mxfp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8', 'quantize_svdquant_w4a4', 'rms_rope', 'rms_rope1', 'rms_rope_split_half', 'rms_rope_split_half1', 'scaled_mm_mxfp8', 'scaled_mm_nvfp4', 'scaled_mm_svdquant_w4a4', 'stochastic_rounding_fp8']}
[32m[INFO][0m Found comfy_kitchen backend cuda: {'available': False, 'disabled': False, 'unavailable_reason': 'CUDA not available on this system', 'capabilities': []}
[32m[INFO][0m Found comfy_kitchen backend triton: {'available': False, 'disabled': True, 'unavailable_reason': 'Neither CUDA nor XPU available on this system', 'capabilities': []}
[32m[INFO][0m Checkpoint files will always be loaded safely.
Windows fatal exception: access violation

Stack (most recent call first):
  File "F:\ai\u7ed8\u753b\JianxiaAI-CreativePack-v2.2\python\Lib\site-packages\torch\cuda\__init__.py", line 410 in _lazy_init
  File "F:\ai\u7ed8\u753b\JianxiaAI-CreativePack-v2.2\python\Lib\site-packages\torch\cuda\__init__.py", line 1069 in current_device
  File "F:\ai\u7ed8\u753b\JianxiaAI-CreativePack-v2.2\ComfyUI\comfy\model_management.py", line 211 in get_torch_device
  File "F:\ai\u7ed8\u753b\JianxiaAI-CreativePack-v2.2\ComfyUI\comfy\model_management.py", line 362 in <module>
  File "<frozen importlib._bootstrap>", line 488 in _call_with_frames_removed
  File "<frozen importlib._bootstrap_external>", line 1023 in exec_module
  File "<frozen importlib._bootstrap>", line 935 in _load_unlocked
  File "<frozen importlib._bootstrap>", line 1331 in _find_and_load_unlocked
  File "<frozen importlib._bootstrap>", line 1360 in _find_and_load
  File "F:\ai\u7ed8\u753b\JianxiaAI-CreativePack-v2.2\ComfyUI\execution.py", line 18 in <module>
  File "<frozen importlib._bootstrap>", line 488 in _call_with_frames_removed
  File "<frozen importlib._bootstrap_external>", line 1023 in exec_module
  File "<frozen importlib._bootstrap>", line 935 in _load_unlocked
  File "<frozen importlib._bootstrap>", line 1331 in _find_and_load_unlocked
  File "<frozen importlib._bootstrap>", line 1360 in _find_and_load
  File "F:\ai\u7ed8\u753b\JianxiaAI-CreativePack-v2.2\ComfyUI\main.py", line 227 in <module>

[release] 鍚姩澶辫触
Traceback (most recent call last):
  File "release.py", line 52, in run_release
RuntimeError: ComfyUI 鍚姩瓒呮椂锛岃鏌ョ湅 data/runtime.log

========================================
[launcher] 鍚姩 ComfyUI
[32m[INFO][0m setup plugin alembic.autogenerate.schemas
[32m[INFO][0m setup plugin alembic.autogenerate.tables
[32m[INFO][0m setup plugin alembic.autogenerate.types
[32m[INFO][0m setup plugin alembic.autogenerate.constraints
[32m[INFO][0m setup plugin alembic.autogenerate.defaults
[32m[INFO][0m setup plugin alembic.autogenerate.comments
[32m[INFO][0m Setting output directory to: F:\ai绘画\JianxiaAI-CreativePack-v2.2\output
[START] Security scan
[DONE] Security scan
## ComfyUI-Manager: installing dependencies done.
** ComfyUI startup time: 2026-09-10 12:53:51.049
** Platform: Windows
** Python version: 3.13.11 (tags/v3.13.11:6278944, Dec  5 2025, 16:26:58) [MSC v.1944 64 bit (AMD64)]
** Python executable: F:\ai缁樼敾\JianxiaAI-CreativePack-v2.2\python\python.exe
** ComfyUI Path: F:\ai缁樼敾\JianxiaAI-CreativePack-v2.2\ComfyUI
** ComfyUI Base Folder Path: F:\ai缁樼敾\JianxiaAI-CreativePack-v2.2\ComfyUI
** User directory: F:\ai缁樼敾\JianxiaAI-CreativePack-v2.2\ComfyUI\user
** ComfyUI-Manager config path: F:\ai缁樼敾\JianxiaAI-CreativePack-v2.2\ComfyUI\user\__manager\config.ini
** Log path: F:\ai缁樼敾\JianxiaAI-CreativePack-v2.2\ComfyUI\user\comfyui.log
[32m[INFO][0m
Prestartup times for custom nodes:
[32m[INFO][0m 0.0 seconds: F:\ai绘画\JianxiaAI-CreativePack-v2.2\ComfyUI\custom_nodes\rgthree-comfy
[32m[INFO][0m 0.0 seconds: F:\ai绘画\JianxiaAI-CreativePack-v2.2\ComfyUI\custom_nodes\comfyui-easy-use
[32m[INFO][0m 0.0 seconds: F:\ai绘画\JianxiaAI-CreativePack-v2.2\ComfyUI\custom_nodes\deno-custom-nodes
[32m[INFO][0m 3.1 seconds: F:\ai绘画\JianxiaAI-CreativePack-v2.2\ComfyUI\custom_nodes\ComfyUI-Manager
[32m[INFO][0m
F:\ai缁樼敾\JianxiaAI-CreativePack-v2.2\python\Lib\site-packages\torch\cuda\__init__.py:182: UserWarning: cudaGetDeviceCount() returned cudaErrorNotSupported, likely using older driver or on CPU machine (Triggered internally at C:\actions-runner\_work\pytorch\pytorch\pytorch\c10\cuda\CUDAFunctions.cpp:88.)
  return torch._C._cuda_getDeviceCount() > 0
[32m[INFO][0m Found comfy_kitchen backend eager: {'available': True, 'disabled': False, 'unavailable_reason': None, 'capabilities': ['adaln', 'apply_rope', 'apply_rope1', 'apply_rope_split_half', 'apply_rope_split_half1', 'convrot_w4a4_linear', 'dequantize_convrot_w4a4_weight', 'dequantize_int8_convrot_weight', 'dequantize_int8_convrot_weight_dtype', 'dequantize_int8_simple', 'dequantize_int8_simple_dtype', 'dequantize_mxfp8', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'gemv_awq_w4a16', 'int8_linear', 'prepare_int4_weight_for_int8_linear', 'quantize_and_rotate_rowwise', 'quantize_convrot_w4a4_weight', 'quantize_int8_convrot_weight', 'quantize_int8_rowwise', 'quantize_int8_tensorwise', 'quantize_mxfp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8', 'quantize_svdquant_w4a4', 'rms_rope', 'rms_rope1', 'rms_rope_split_half', 'rms_rope_split_half1', 'scaled_mm_mxfp8', 'scaled_mm_nvfp4', 'scaled_mm_svdquant_w4a4', 'stochastic_rounding_fp8']}
[32m[INFO][0m Found comfy_kitchen backend triton: {'available': False, 'disabled': True, 'unavailable_reason': 'Neither CUDA nor XPU available on this system', 'capabilities': []}
[32m[INFO][0m Found comfy_kitchen backend cuda: {'available': False, 'disabled': False, 'unavailable_reason': 'CUDA not available on this system', 'capabilities': []}
[32m[INFO][0m Checkpoint files will always be loaded safely.
Windows fatal exception: access violation

Stack (most recent call first):
  File "F:\ai\u7ed8\u753b\JianxiaAI-CreativePack-v2.2\python\Lib\site-packages\torch\cuda\__init__.py", line 410 in _lazy_init
  File "F:\ai\u7ed8\u753b\JianxiaAI-CreativePack-v2.2\python\Lib\site-packages\torch\cuda\__init__.py", line 1069 in current_device
  File "F:\ai\u7ed8\u753b\JianxiaAI-CreativePack-v2.2\ComfyUI\comfy\model_management.py", line 211 in get_torch_device
  File "F:\ai\u7ed8\u753b\JianxiaAI-CreativePack-v2.2\ComfyUI\comfy\model_management.py", line 362 in <module>
  File "<frozen importlib._bootstrap>", line 488 in _call_with_frames_removed
  File "<frozen importlib._bootstrap_external>", line 1023 in exec_module
  File "<frozen importlib._bootstrap>", line 935 in _load_unlocked
  File "<frozen importlib._bootstrap>", line 1331 in _find_and_load_unlocked
  File "<frozen importlib._bootstrap>", line 1360 in _find_and_load
  File "F:\ai\u7ed8\u753b\JianxiaAI-CreativePack-v2.2\ComfyUI\execution.py", line 18 in <module>
  File "<frozen importlib._bootstrap>", line 488 in _call_with_frames_removed
  File "<frozen importlib._bootstrap_external>", line 1023 in exec_module
  File "<frozen importlib._bootstrap>", line 935 in _load_unlocked
  File "<frozen importlib._bootstrap>", line 1331 in _find_and_load_unlocked
  File "<frozen importlib._bootstrap>", line 1360 in _find_and_load
  File "F:\ai\u7ed8\u753b\JianxiaAI-CreativePack-v2.2\ComfyUI\main.py", line 227 in <module>

[release] 鍚姩澶辫触
Traceback (most recent call last):
  File "release.py", line 52, in run_release
RuntimeError: ComfyUI 鍚姩瓒呮椂锛岃鏌ョ湅 data/runtime.log

========================================
[browser-backup] 鍚姩 ComfyUI
[32m[INFO][0m setup plugin alembic.autogenerate.schemas
[32m[INFO][0m setup plugin alembic.autogenerate.tables
[32m[INFO][0m setup plugin alembic.autogenerate.types
[32m[INFO][0m setup plugin alembic.autogenerate.constraints
[32m[INFO][0m setup plugin alembic.autogenerate.defaults
[32m[INFO][0m setup plugin alembic.autogenerate.comments
[32m[INFO][0m Setting output directory to: F:\ai绘画\JianxiaAI-CreativePack-v2.2\output
[START] Security scan
[DONE] Security scan
## ComfyUI-Manager: installing dependencies done.
** ComfyUI startup time: 2026-09-10 12:57:25.463
** Platform: Windows
** Python version: 3.13.11 (tags/v3.13.11:6278944, Dec  5 2025, 16:26:58) [MSC v.1944 64 bit (AMD64)]
** Python executable: F:\ai缁樼敾\JianxiaAI-CreativePack-v2.2\python\python.exe
** ComfyUI Path: F:\ai缁樼敾\JianxiaAI-CreativePack-v2.2\ComfyUI
** ComfyUI Base Folder Path: F:\ai缁樼敾\JianxiaAI-CreativePack-v2.2\ComfyUI
** User directory: F:\ai缁樼敾\JianxiaAI-CreativePack-v2.2\ComfyUI\user
** ComfyUI-Manager config path: F:\ai缁樼敾\JianxiaAI-CreativePack-v2.2\ComfyUI\user\__manager\config.ini
** Log path: F:\ai缁樼敾\JianxiaAI-CreativePack-v2.2\ComfyUI\user\comfyui.log
[32m[INFO][0m
Prestartup times for custom nodes:
[32m[INFO][0m 0.0 seconds: F:\ai绘画\JianxiaAI-CreativePack-v2.2\ComfyUI\custom_nodes\rgthree-comfy
[32m[INFO][0m 0.0 seconds: F:\ai绘画\JianxiaAI-CreativePack-v2.2\ComfyUI\custom_nodes\comfyui-easy-use
[32m[INFO][0m 0.0 seconds: F:\ai绘画\JianxiaAI-CreativePack-v2.2\ComfyUI\custom_nodes\deno-custom-nodes
[32m[INFO][0m 3.2 seconds: F:\ai绘画\JianxiaAI-CreativePack-v2.2\ComfyUI\custom_nodes\ComfyUI-Manager
[32m[INFO][0m
F:\ai缁樼敾\JianxiaAI-CreativePack-v2.2\python\Lib\site-packages\torch\cuda\__init__.py:182: UserWarning: cudaGetDeviceCount() returned cudaErrorNotSupported, likely using older driver or on CPU machine (Triggered internally at C:\actions-runner\_work\pytorch\pytorch\pytorch\c10\cuda\CUDAFunctions.cpp:88.)
  return torch._C._cuda_getDeviceCount() > 0
[32m[INFO][0m Found comfy_kitchen backend cuda: {'available': False, 'disabled': False, 'unavailable_reason': 'CUDA not available on this system', 'capabilities': []}
[32m[INFO][0m Found comfy_kitchen backend triton: {'available': False, 'disabled': True, 'unavailable_reason': 'Neither CUDA nor XPU available on this system', 'capabilities': []}
[32m[INFO][0m Found comfy_kitchen backend eager: {'available': True, 'disabled': False, 'unavailable_reason': None, 'capabilities': ['adaln', 'apply_rope', 'apply_rope1', 'apply_rope_split_half', 'apply_rope_split_half1', 'convrot_w4a4_linear', 'dequantize_convrot_w4a4_weight', 'dequantize_int8_convrot_weight', 'dequantize_int8_convrot_weight_dtype', 'dequantize_int8_simple', 'dequantize_int8_simple_dtype', 'dequantize_mxfp8', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'gemv_awq_w4a16', 'int8_linear', 'prepare_int4_weight_for_int8_linear', 'quantize_and_rotate_rowwise', 'quantize_convrot_w4a4_weight', 'quantize_int8_convrot_weight', 'quantize_int8_rowwise', 'quantize_int8_tensorwise', 'quantize_mxfp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8', 'quantize_svdquant_w4a4', 'rms_rope', 'rms_rope1', 'rms_rope_split_half', 'rms_rope_split_half1', 'scaled_mm_mxfp8', 'scaled_mm_nvfp4', 'scaled_mm_svdquant_w4a4', 'stochastic_rounding_fp8']}
[32m[INFO][0m Checkpoint files will always be loaded safely.
Windows fatal exception: access violation

Stack (most recent call first):
  File "F:\ai\u7ed8\u753b\JianxiaAI-CreativePack-v2.2\python\Lib\site-packages\torch\cuda\__init__.py", line 410 in _lazy_init
  File "F:\ai\u7ed8\u753b\JianxiaAI-CreativePack-v2.2\python\Lib\site-packages\torch\cuda\__init__.py", line 1069 in current_device
  File "F:\ai\u7ed8\u753b\JianxiaAI-CreativePack-v2.2\ComfyUI\comfy\model_management.py", line 211 in get_torch_device
  File "F:\ai\u7ed8\u753b\JianxiaAI-CreativePack-v2.2\ComfyUI\comfy\model_management.py", line 362 in <module>
  File "<frozen importlib._bootstrap>", line 488 in _call_with_frames_removed
  File "<frozen importlib._bootstrap_external>", line 1023 in exec_module
  File "<frozen importlib._bootstrap>", line 935 in _load_unlocked
  File "<frozen importlib._bootstrap>", line 1331 in _find_and_load_unlocked
  File "<frozen importlib._bootstrap>", line 1360 in _find_and_load
  File "F:\ai\u7ed8\u753b\JianxiaAI-CreativePack-v2.2\ComfyUI\execution.py", line 18 in <module>
  File "<frozen importlib._bootstrap>", line 488 in _call_with_frames_removed
  File "<frozen importlib._bootstrap_external>", line 1023 in exec_module
  File "<frozen importlib._bootstrap>", line 935 in _load_unlocked
  File "<frozen importlib._bootstrap>", line 1331 in _find_and_load_unlocked
  File "<frozen importlib._bootstrap>", line 1360 in _find_and_load
  File "F:\ai\u7ed8\u753b\JianxiaAI-CreativePack-v2.2\ComfyUI\main.py", line 227 in <module>

========================================
[browser-backup] 鍚姩 Bridge: F:\ai缁樼敾\JianxiaAI-CreativePack-v2.2\python\python.exe F:\ai缁樼敾\JianxiaAI-CreativePack-v2.2\krea-bridge\main.py

========================================
[launcher] 鍚姩 ComfyUI
[32m[INFO][0m setup plugin alembic.autogenerate.schemas
[32m[INFO][0m setup plugin alembic.autogenerate.tables
[32m[INFO][0m setup plugin alembic.autogenerate.types
[32m[INFO][0m setup plugin alembic.autogenerate.constraints
[32m[INFO][0m setup plugin alembic.autogenerate.defaults
[32m[INFO][0m setup plugin alembic.autogenerate.comments
[32m[INFO][0m Setting output directory to: F:\ai绘画\JianxiaAI-CreativePack-v2.2\output
[START] Security scan
[DONE] Security scan
## ComfyUI-Manager: installing dependencies done.
** ComfyUI startup time: 2026-09-10 14:19:54.465
** Platform: Windows
** Python version: 3.13.11 (tags/v3.13.11:6278944, Dec  5 2025, 16:26:58) [MSC v.1944 64 bit (AMD64)]
** Python executable: F:\ai缁樼敾\JianxiaAI-CreativePack-v2.2\python\python.exe
** ComfyUI Path: F:\ai缁樼敾\JianxiaAI-CreativePack-v2.2\ComfyUI
** ComfyUI Base Folder Path: F:\ai缁樼敾\JianxiaAI-CreativePack-v2.2\ComfyUI
** User directory: F:\ai缁樼敾\JianxiaAI-CreativePack-v2.2\ComfyUI\user
** ComfyUI-Manager config path: F:\ai缁樼敾\JianxiaAI-CreativePack-v2.2\ComfyUI\user\__manager\config.ini
** Log path: F:\ai缁樼敾\JianxiaAI-CreativePack-v2.2\ComfyUI\user\comfyui.log
[32m[INFO][0m
Prestartup times for custom nodes:
[32m[INFO][0m 0.0 seconds: F:\ai绘画\JianxiaAI-CreativePack-v2.2\ComfyUI\custom_nodes\rgthree-comfy
[32m[INFO][0m 0.0 seconds: F:\ai绘画\JianxiaAI-CreativePack-v2.2\ComfyUI\custom_nodes\deno-custom-nodes
[32m[INFO][0m 0.0 seconds: F:\ai绘画\JianxiaAI-CreativePack-v2.2\ComfyUI\custom_nodes\comfyui-easy-use
[32m[INFO][0m 7.8 seconds: F:\ai绘画\JianxiaAI-CreativePack-v2.2\ComfyUI\custom_nodes\ComfyUI-Manager
[32m[INFO][0m
F:\ai缁樼敾\JianxiaAI-CreativePack-v2.2\python\Lib\site-packages\torch\cuda\__init__.py:182: UserWarning: cudaGetDeviceCount() returned cudaErrorNotSupported, likely using older driver or on CPU machine (Triggered internally at C:\actions-runner\_work\pytorch\pytorch\pytorch\c10\cuda\CUDAFunctions.cpp:88.)
  return torch._C._cuda_getDeviceCount() > 0
[32m[INFO][0m Found comfy_kitchen backend cuda: {'available': False, 'disabled': False, 'unavailable_reason': 'CUDA not available on this system', 'capabilities': []}
[32m[INFO][0m Found comfy_kitchen backend triton: {'available': False, 'disabled': True, 'unavailable_reason': 'Neither CUDA nor XPU available on this system', 'capabilities': []}
[32m[INFO][0m Found comfy_kitchen backend eager: {'available': True, 'disabled': False, 'unavailable_reason': None, 'capabilities': ['adaln', 'apply_rope', 'apply_rope1', 'apply_rope_split_half', 'apply_rope_split_half1', 'convrot_w4a4_linear', 'dequantize_convrot_w4a4_weight', 'dequantize_int8_convrot_weight', 'dequantize_int8_convrot_weight_dtype', 'dequantize_int8_simple', 'dequantize_int8_simple_dtype', 'dequantize_mxfp8', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'gemv_awq_w4a16', 'int8_linear', 'prepare_int4_weight_for_int8_linear', 'quantize_and_rotate_rowwise', 'quantize_convrot_w4a4_weight', 'quantize_int8_convrot_weight', 'quantize_int8_rowwise', 'quantize_int8_tensorwise', 'quantize_mxfp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8', 'quantize_svdquant_w4a4', 'rms_rope', 'rms_rope1', 'rms_rope_split_half', 'rms_rope_split_half1', 'scaled_mm_mxfp8', 'scaled_mm_nvfp4', 'scaled_mm_svdquant_w4a4', 'stochastic_rounding_fp8']}
[32m[INFO][0m Checkpoint files will always be loaded safely.
Windows fatal exception: access violation

Stack (most recent call first):
  File "F:\ai\u7ed8\u753b\JianxiaAI-CreativePack-v2.2\python\Lib\site-packages\torch\cuda\__init__.py", line 410 in _lazy_init
  File "F:\ai\u7ed8\u753b\JianxiaAI-CreativePack-v2.2\python\Lib\site-packages\torch\cuda\__init__.py", line 1069 in current_device
  File "F:\ai\u7ed8\u753b\JianxiaAI-CreativePack-v2.2\ComfyUI\comfy\model_management.py", line 211 in get_torch_device
  File "F:\ai\u7ed8\u753b\JianxiaAI-CreativePack-v2.2\ComfyUI\comfy\model_management.py", line 362 in <module>
  File "<frozen importlib._bootstrap>", line 488 in _call_with_frames_removed
  File "<frozen importlib._bootstrap_external>", line 1023 in exec_module
  File "<frozen importlib._bootstrap>", line 935 in _load_unlocked
  File "<frozen importlib._bootstrap>", line 1331 in _find_and_load_unlocked
  File "<frozen importlib._bootstrap>", line 1360 in _find_and_load
  File "F:\ai\u7ed8\u753b\JianxiaAI-CreativePack-v2.2\ComfyUI\execution.py", line 18 in <module>
  File "<frozen importlib._bootstrap>", line 488 in _call_with_frames_removed
  File "<frozen importlib._bootstrap_external>", line 1023 in exec_module
  File "<frozen importlib._bootstrap>", line 935 in _load_unlocked
  File "<frozen importlib._bootstrap>", line 1331 in _find_and_load_unlocked
  File "<frozen importlib._bootstrap>", line 1360 in _find_and_load
  File "F:\ai\u7ed8\u753b\JianxiaAI-CreativePack-v2.2\ComfyUI\main.py", line 227 in <module>

[release] 鍚姩澶辫触
Traceback (most recent call last):
  File "release.py", line 52, in run_release
RuntimeError: ComfyUI 鍚姩瓒呮椂锛岃鏌ョ湅 data/runtime.log

========================================
[launcher] 鍚姩 ComfyUI
[32m[INFO][0m setup plugin alembic.autogenerate.schemas
[32m[INFO][0m setup plugin alembic.autogenerate.tables
[32m[INFO][0m setup plugin alembic.autogenerate.types
[32m[INFO][0m setup plugin alembic.autogenerate.constraints
[32m[INFO][0m setup plugin alembic.autogenerate.defaults
[32m[INFO][0m setup plugin alembic.autogenerate.comments
[32m[INFO][0m Setting output directory to: F:\ai绘画\JianxiaAI-CreativePack-v2.2\output
[START] Security scan
[DONE] Security scan
## ComfyUI-Manager: installing dependencies done.
** ComfyUI startup time: 2026-09-10 14:33:14.249
** Platform: Windows
** Python version: 3.13.11 (tags/v3.13.11:6278944, Dec  5 2025, 16:26:58) [MSC v.1944 64 bit (AMD64)]
** Python executable: F:\ai缁樼敾\JianxiaAI-CreativePack-v2.2\python\python.exe
** ComfyUI Path: F:\ai缁樼敾\JianxiaAI-CreativePack-v2.2\ComfyUI
** ComfyUI Base Folder Path: F:\ai缁樼敾\JianxiaAI-CreativePack-v2.2\ComfyUI
** User directory: F:\ai缁樼敾\JianxiaAI-CreativePack-v2.2\ComfyUI\user
** ComfyUI-Manager config path: F:\ai缁樼敾\JianxiaAI-CreativePack-v2.2\ComfyUI\user\__manager\config.ini
** Log path: F:\ai缁樼敾\JianxiaAI-CreativePack-v2.2\ComfyUI\user\comfyui.log
[32m[INFO][0m
Prestartup times for custom nodes:
[32m[INFO][0m 0.0 seconds: F:\ai绘画\JianxiaAI-CreativePack-v2.2\ComfyUI\custom_nodes\rgthree-comfy
[32m[INFO][0m 0.0 seconds: F:\ai绘画\JianxiaAI-CreativePack-v2.2\ComfyUI\custom_nodes\comfyui-easy-use
[32m[INFO][0m 0.0 seconds: F:\ai绘画\JianxiaAI-CreativePack-v2.2\ComfyUI\custom_nodes\deno-custom-nodes
[32m[INFO][0m 2.9 seconds: F:\ai绘画\JianxiaAI-CreativePack-v2.2\ComfyUI\custom_nodes\ComfyUI-Manager
[32m[INFO][0m
F:\ai缁樼敾\JianxiaAI-CreativePack-v2.2\python\Lib\site-packages\torch\cuda\__init__.py:182: UserWarning: cudaGetDeviceCount() returned cudaErrorNotSupported, likely using older driver or on CPU machine (Triggered internally at C:\actions-runner\_work\pytorch\pytorch\pytorch\c10\cuda\CUDAFunctions.cpp:88.)
  return torch._C._cuda_getDeviceCount() > 0
[32m[INFO][0m Found comfy_kitchen backend eager: {'available': True, 'disabled': False, 'unavailable_reason': None, 'capabilities': ['adaln', 'apply_rope', 'apply_rope1', 'apply_rope_split_half', 'apply_rope_split_half1', 'convrot_w4a4_linear', 'dequantize_convrot_w4a4_weight', 'dequantize_int8_convrot_weight', 'dequantize_int8_convrot_weight_dtype', 'dequantize_int8_simple', 'dequantize_int8_simple_dtype', 'dequantize_mxfp8', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'gemv_awq_w4a16', 'int8_linear', 'prepare_int4_weight_for_int8_linear', 'quantize_and_rotate_rowwise', 'quantize_convrot_w4a4_weight', 'quantize_int8_convrot_weight', 'quantize_int8_rowwise', 'quantize_int8_tensorwise', 'quantize_mxfp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8', 'quantize_svdquant_w4a4', 'rms_rope', 'rms_rope1', 'rms_rope_split_half', 'rms_rope_split_half1', 'scaled_mm_mxfp8', 'scaled_mm_nvfp4', 'scaled_mm_svdquant_w4a4', 'stochastic_rounding_fp8']}
[32m[INFO][0m Found comfy_kitchen backend triton: {'available': False, 'disabled': True, 'unavailable_reason': 'Neither CUDA nor XPU available on this system', 'capabilities': []}
[32m[INFO][0m Found comfy_kitchen backend cuda: {'available': False, 'disabled': False, 'unavailable_reason': 'CUDA not available on this system', 'capabilities': []}
[32m[INFO][0m Checkpoint files will always be loaded safely.
Windows fatal exception: access violation

Stack (most recent call first):
  File "F:\ai\u7ed8\u753b\JianxiaAI-CreativePack-v2.2\python\Lib\site-packages\torch\cuda\__init__.py", line 410 in _lazy_init
  File "F:\ai\u7ed8\u753b\JianxiaAI-CreativePack-v2.2\python\Lib\site-packages\torch\cuda\__init__.py", line 1069 in current_device
  File "F:\ai\u7ed8\u753b\JianxiaAI-CreativePack-v2.2\ComfyUI\comfy\model_management.py", line 211 in get_torch_device
  File "F:\ai\u7ed8\u753b\JianxiaAI-CreativePack-v2.2\ComfyUI\comfy\model_management.py", line 362 in <module>
  File "<frozen importlib._bootstrap>", line 488 in _call_with_frames_removed
  File "<frozen importlib._bootstrap_external>", line 1023 in exec_module
  File "<frozen importlib._bootstrap>", line 935 in _load_unlocked
  File "<frozen importlib._bootstrap>", line 1331 in _find_and_load_unlocked
  File "<frozen importlib._bootstrap>", line 1360 in _find_and_load
  File "F:\ai\u7ed8\u753b\JianxiaAI-CreativePack-v2.2\ComfyUI\execution.py", line 18 in <module>
  File "<frozen importlib._bootstrap>", line 488 in _call_with_frames_removed
  File "<frozen importlib._bootstrap_external>", line 1023 in exec_module
  File "<frozen importlib._bootstrap>", line 935 in _load_unlocked
  File "<frozen importlib._bootstrap>", line 1331 in _find_and_load_unlocked
  File "<frozen importlib._bootstrap>", line 1360 in _find_and_load
  File "F:\ai\u7ed8\u753b\JianxiaAI-CreativePack-v2.2\ComfyUI\main.py", line 227 in <module>

[release] 鍚姩澶辫触
Traceback (most recent call last):
  File "release.py", line 52, in run_release
RuntimeError: ComfyUI 鍚姩瓒呮椂锛岃鏌ョ湅 data/runtime.log

========================================
[launcher] 鍚姩 ComfyUI
[32m[INFO][0m setup plugin alembic.autogenerate.schemas
[32m[INFO][0m setup plugin alembic.autogenerate.tables
[32m[INFO][0m setup plugin alembic.autogenerate.types
[32m[INFO][0m setup plugin alembic.autogenerate.constraints
[32m[INFO][0m setup plugin alembic.autogenerate.defaults
[32m[INFO][0m setup plugin alembic.autogenerate.comments
[32m[INFO][0m Setting output directory to: F:\JianxiaAI-CreativePack-v2.2\output
[START] Security scan
[DONE] Security scan
## ComfyUI-Manager: installing dependencies done.
** ComfyUI startup time: 2026-09-10 14:57:53.803
** Platform: Windows
** Python version: 3.13.11 (tags/v3.13.11:6278944, Dec  5 2025, 16:26:58) [MSC v.1944 64 bit (AMD64)]
** Python executable: F:\JianxiaAI-CreativePack-v2.2\python\python.exe
** ComfyUI Path: F:\JianxiaAI-CreativePack-v2.2\ComfyUI
** ComfyUI Base Folder Path: F:\JianxiaAI-CreativePack-v2.2\ComfyUI
** User directory: F:\JianxiaAI-CreativePack-v2.2\ComfyUI\user
** ComfyUI-Manager config path: F:\JianxiaAI-CreativePack-v2.2\ComfyUI\user\__manager\config.ini
** Log path: F:\JianxiaAI-CreativePack-v2.2\ComfyUI\user\comfyui.log
[32m[INFO][0m
Prestartup times for custom nodes:
[32m[INFO][0m 0.0 seconds: F:\JianxiaAI-CreativePack-v2.2\ComfyUI\custom_nodes\rgthree-comfy
[32m[INFO][0m 0.0 seconds: F:\JianxiaAI-CreativePack-v2.2\ComfyUI\custom_nodes\comfyui-easy-use
[32m[INFO][0m 0.0 seconds: F:\JianxiaAI-CreativePack-v2.2\ComfyUI\custom_nodes\deno-custom-nodes
[32m[INFO][0m 3.2 seconds: F:\JianxiaAI-CreativePack-v2.2\ComfyUI\custom_nodes\ComfyUI-Manager
[32m[INFO][0m
F:\JianxiaAI-CreativePack-v2.2\python\Lib\site-packages\torch\cuda\__init__.py:182: UserWarning: cudaGetDeviceCount() returned cudaErrorNotSupported, likely using older driver or on CPU machine (Triggered internally at C:\actions-runner\_work\pytorch\pytorch\pytorch\c10\cuda\CUDAFunctions.cpp:88.)
  return torch._C._cuda_getDeviceCount() > 0
[32m[INFO][0m Found comfy_kitchen backend triton: {'available': False, 'disabled': True, 'unavailable_reason': 'Neither CUDA nor XPU available on this system', 'capabilities': []}
[32m[INFO][0m Found comfy_kitchen backend eager: {'available': True, 'disabled': False, 'unavailable_reason': None, 'capabilities': ['adaln', 'apply_rope', 'apply_rope1', 'apply_rope_split_half', 'apply_rope_split_half1', 'convrot_w4a4_linear', 'dequantize_convrot_w4a4_weight', 'dequantize_int8_convrot_weight', 'dequantize_int8_convrot_weight_dtype', 'dequantize_int8_simple', 'dequantize_int8_simple_dtype', 'dequantize_mxfp8', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'gemv_awq_w4a16', 'int8_linear', 'prepare_int4_weight_for_int8_linear', 'quantize_and_rotate_rowwise', 'quantize_convrot_w4a4_weight', 'quantize_int8_convrot_weight', 'quantize_int8_rowwise', 'quantize_int8_tensorwise', 'quantize_mxfp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8', 'quantize_svdquant_w4a4', 'rms_rope', 'rms_rope1', 'rms_rope_split_half', 'rms_rope_split_half1', 'scaled_mm_mxfp8', 'scaled_mm_nvfp4', 'scaled_mm_svdquant_w4a4', 'stochastic_rounding_fp8']}
[32m[INFO][0m Found comfy_kitchen backend cuda: {'available': False, 'disabled': False, 'unavailable_reason': 'CUDA not available on this system', 'capabilities': []}
[32m[INFO][0m Checkpoint files will always be loaded safely.
Windows fatal exception: access violation

Stack (most recent call first):
  File "F:\JianxiaAI-CreativePack-v2.2\python\Lib\site-packages\torch\cuda\__init__.py", line 410 in _lazy_init
  File "F:\JianxiaAI-CreativePack-v2.2\python\Lib\site-packages\torch\cuda\__init__.py", line 1069 in current_device
  File "F:\JianxiaAI-CreativePack-v2.2\ComfyUI\comfy\model_management.py", line 211 in get_torch_device
  File "F:\JianxiaAI-CreativePack-v2.2\ComfyUI\comfy\model_management.py", line 362 in <module>
  File "<frozen importlib._bootstrap>", line 488 in _call_with_frames_removed
  File "<frozen importlib._bootstrap_external>", line 1023 in exec_module
  File "<frozen importlib._bootstrap>", line 935 in _load_unlocked
  File "<frozen importlib._bootstrap>", line 1331 in _find_and_load_unlocked
  File "<frozen importlib._bootstrap>", line 1360 in _find_and_load
  File "F:\JianxiaAI-CreativePack-v2.2\ComfyUI\execution.py", line 18 in <module>
  File "<frozen importlib._bootstrap>", line 488 in _call_with_frames_removed
  File "<frozen importlib._bootstrap_external>", line 1023 in exec_module
  File "<frozen importlib._bootstrap>", line 935 in _load_unlocked
  File "<frozen importlib._bootstrap>", line 1331 in _find_and_load_unlocked
  File "<frozen importlib._bootstrap>", line 1360 in _find_and_load
  File "F:\JianxiaAI-CreativePack-v2.2\ComfyUI\main.py", line 227 in <module>

[release] 鍚姩澶辫触
Traceback (most recent call last):
  File "release.py", line 52, in run_release
RuntimeError: ComfyUI 鍚姩瓒呮椂锛岃鏌ョ湅 data/runtime.log

========================================
[launcher] 鍚姩 ComfyUI
[32m[INFO][0m setup plugin alembic.autogenerate.schemas
[32m[INFO][0m setup plugin alembic.autogenerate.tables
[32m[INFO][0m setup plugin alembic.autogenerate.types
[32m[INFO][0m setup plugin alembic.autogenerate.constraints
[32m[INFO][0m setup plugin alembic.autogenerate.defaults
[32m[INFO][0m setup plugin alembic.autogenerate.comments
[32m[INFO][0m Setting output directory to: F:\JianxiaAI-CreativePack-v2.2\output
[START] Security scan
[DONE] Security scan
## ComfyUI-Manager: installing dependencies done.
** ComfyUI startup time: 2026-09-10 18:29:03.310
** Platform: Windows
** Python version: 3.13.11 (tags/v3.13.11:6278944, Dec  5 2025, 16:26:58) [MSC v.1944 64 bit (AMD64)]
** Python executable: F:\JianxiaAI-CreativePack-v2.2\python\python.exe
** ComfyUI Path: F:\JianxiaAI-CreativePack-v2.2\ComfyUI
** ComfyUI Base Folder Path: F:\JianxiaAI-CreativePack-v2.2\ComfyUI
** User directory: F:\JianxiaAI-CreativePack-v2.2\ComfyUI\user
** ComfyUI-Manager config path: F:\JianxiaAI-CreativePack-v2.2\ComfyUI\user\__manager\config.ini
** Log path: F:\JianxiaAI-CreativePack-v2.2\ComfyUI\user\comfyui.log
[32m[INFO][0m
Prestartup times for custom nodes:
[32m[INFO][0m 0.0 seconds: F:\JianxiaAI-CreativePack-v2.2\ComfyUI\custom_nodes\rgthree-comfy
[32m[INFO][0m 0.0 seconds: F:\JianxiaAI-CreativePack-v2.2\ComfyUI\custom_nodes\comfyui-easy-use
[32m[INFO][0m 0.0 seconds: F:\JianxiaAI-CreativePack-v2.2\ComfyUI\custom_nodes\deno-custom-nodes
[32m[INFO][0m 3.1 seconds: F:\JianxiaAI-CreativePack-v2.2\ComfyUI\custom_nodes\ComfyUI-Manager
[32m[INFO][0m
F:\JianxiaAI-CreativePack-v2.2\python\Lib\site-packages\torch\cuda\__init__.py:182: UserWarning: cudaGetDeviceCount() returned cudaErrorNotSupported, likely using older driver or on CPU machine (Triggered internally at C:\actions-runner\_work\pytorch\pytorch\pytorch\c10\cuda\CUDAFunctions.cpp:88.)
  return torch._C._cuda_getDeviceCount() > 0
[32m[INFO][0m Found comfy_kitchen backend triton: {'available': False, 'disabled': True, 'unavailable_reason': 'Neither CUDA nor XPU available on this system', 'capabilities': []}
[32m[INFO][0m Found comfy_kitchen backend eager: {'available': True, 'disabled': False, 'unavailable_reason': None, 'capabilities': ['adaln', 'apply_rope', 'apply_rope1', 'apply_rope_split_half', 'apply_rope_split_half1', 'convrot_w4a4_linear', 'dequantize_convrot_w4a4_weight', 'dequantize_int8_convrot_weight', 'dequantize_int8_convrot_weight_dtype', 'dequantize_int8_simple', 'dequantize_int8_simple_dtype', 'dequantize_mxfp8', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'gemv_awq_w4a16', 'int8_linear', 'prepare_int4_weight_for_int8_linear', 'quantize_and_rotate_rowwise', 'quantize_convrot_w4a4_weight', 'quantize_int8_convrot_weight', 'quantize_int8_rowwise', 'quantize_int8_tensorwise', 'quantize_mxfp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8', 'quantize_svdquant_w4a4', 'rms_rope', 'rms_rope1', 'rms_rope_split_half', 'rms_rope_split_half1', 'scaled_mm_mxfp8', 'scaled_mm_nvfp4', 'scaled_mm_svdquant_w4a4', 'stochastic_rounding_fp8']}
[32m[INFO][0m Found comfy_kitchen backend cuda: {'available': False, 'disabled': False, 'unavailable_reason': 'CUDA not available on this system', 'capabilities': []}
[32m[INFO][0m Checkpoint files will always be loaded safely.
Windows fatal exception: access violation

Stack (most recent call first):
  File "F:\JianxiaAI-CreativePack-v2.2\python\Lib\site-packages\torch\cuda\__init__.py", line 410 in _lazy_init
  File "F:\JianxiaAI-CreativePack-v2.2\python\Lib\site-packages\torch\cuda\__init__.py", line 1069 in current_device
  File "F:\JianxiaAI-CreativePack-v2.2\ComfyUI\comfy\model_management.py", line 211 in get_torch_device
  File "F:\JianxiaAI-CreativePack-v2.2\ComfyUI\comfy\model_management.py", line 362 in <module>
  File "<frozen importlib._bootstrap>", line 488 in _call_with_frames_removed
  File "<frozen importlib._bootstrap_external>", line 1023 in exec_module
  File "<frozen importlib._bootstrap>", line 935 in _load_unlocked
  File "<frozen importlib._bootstrap>", line 1331 in _find_and_load_unlocked
  File "<frozen importlib._bootstrap>", line 1360 in _find_and_load
  File "F:\JianxiaAI-CreativePack-v2.2\ComfyUI\execution.py", line 18 in <module>
  File "<frozen importlib._bootstrap>", line 488 in _call_with_frames_removed
  File "<frozen importlib._bootstrap_external>", line 1023 in exec_module
  File "<frozen importlib._bootstrap>", line 935 in _load_unlocked
  File "<frozen importlib._bootstrap>", line 1331 in _find_and_load_unlocked
  File "<frozen importlib._bootstrap>", line 1360 in _find_and_load
  File "F:\JianxiaAI-CreativePack-v2.2\ComfyUI\main.py", line 227 in <module>

[release] 鍚姩澶辫触
Traceback (most recent call last):
  File "release.py", line 52, in run_release
RuntimeError: ComfyUI 鍚姩瓒呮椂锛岃鏌ョ湅 data/runtime.log

========================================
[launcher] 鍚姩 ComfyUI
[32m[INFO][0m setup plugin alembic.autogenerate.schemas
[32m[INFO][0m setup plugin alembic.autogenerate.tables
[32m[INFO][0m setup plugin alembic.autogenerate.types
[32m[INFO][0m setup plugin alembic.autogenerate.constraints
[32m[INFO][0m setup plugin alembic.autogenerate.defaults
[32m[INFO][0m setup plugin alembic.autogenerate.comments
[32m[INFO][0m Setting output directory to: F:\JianxiaAI\output
[START] Security scan
[DONE] Security scan
## ComfyUI-Manager: installing dependencies done.
** ComfyUI startup time: 2026-09-10 18:34:14.850
** Platform: Windows
** Python version: 3.13.11 (tags/v3.13.11:6278944, Dec  5 2025, 16:26:58) [MSC v.1944 64 bit (AMD64)]
** Python executable: F:\JianxiaAI\python\python.exe
** ComfyUI Path: F:\JianxiaAI\ComfyUI
** ComfyUI Base Folder Path: F:\JianxiaAI\ComfyUI
** User directory: F:\JianxiaAI\ComfyUI\user
** ComfyUI-Manager config path: F:\JianxiaAI\ComfyUI\user\__manager\config.ini
** Log path: F:\JianxiaAI\ComfyUI\user\comfyui.log
[32m[INFO][0m
Prestartup times for custom nodes:
[32m[INFO][0m 0.0 seconds: F:\JianxiaAI\ComfyUI\custom_nodes\rgthree-comfy
[32m[INFO][0m 0.0 seconds: F:\JianxiaAI\ComfyUI\custom_nodes\comfyui-easy-use
[32m[INFO][0m 0.0 seconds: F:\JianxiaAI\ComfyUI\custom_nodes\deno-custom-nodes
[32m[INFO][0m 3.1 seconds: F:\JianxiaAI\ComfyUI\custom_nodes\ComfyUI-Manager
[32m[INFO][0m
F:\JianxiaAI\python\Lib\site-packages\torch\cuda\__init__.py:182: UserWarning: cudaGetDeviceCount() returned cudaErrorNotSupported, likely using older driver or on CPU machine (Triggered internally at C:\actions-runner\_work\pytorch\pytorch\pytorch\c10\cuda\CUDAFunctions.cpp:88.)
  return torch._C._cuda_getDeviceCount() > 0
[32m[INFO][0m Found comfy_kitchen backend cuda: {'available': False, 'disabled': False, 'unavailable_reason': 'CUDA not available on this system', 'capabilities': []}
[32m[INFO][0m Found comfy_kitchen backend eager: {'available': True, 'disabled': False, 'unavailable_reason': None, 'capabilities': ['adaln', 'apply_rope', 'apply_rope1', 'apply_rope_split_half', 'apply_rope_split_half1', 'convrot_w4a4_linear', 'dequantize_convrot_w4a4_weight', 'dequantize_int8_convrot_weight', 'dequantize_int8_convrot_weight_dtype', 'dequantize_int8_simple', 'dequantize_int8_simple_dtype', 'dequantize_mxfp8', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'gemv_awq_w4a16', 'int8_linear', 'prepare_int4_weight_for_int8_linear', 'quantize_and_rotate_rowwise', 'quantize_convrot_w4a4_weight', 'quantize_int8_convrot_weight', 'quantize_int8_rowwise', 'quantize_int8_tensorwise', 'quantize_mxfp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8', 'quantize_svdquant_w4a4', 'rms_rope', 'rms_rope1', 'rms_rope_split_half', 'rms_rope_split_half1', 'scaled_mm_mxfp8', 'scaled_mm_nvfp4', 'scaled_mm_svdquant_w4a4', 'stochastic_rounding_fp8']}
[32m[INFO][0m Found comfy_kitchen backend triton: {'available': False, 'disabled': True, 'unavailable_reason': 'Neither CUDA nor XPU available on this system', 'capabilities': []}
[32m[INFO][0m Checkpoint files will always be loaded safely.
Windows fatal exception: access violation

Stack (most recent call first):
  File "F:\JianxiaAI\python\Lib\site-packages\torch\cuda\__init__.py", line 410 in _lazy_init
  File "F:\JianxiaAI\python\Lib\site-packages\torch\cuda\__init__.py", line 1069 in current_device
  File "F:\JianxiaAI\ComfyUI\comfy\model_management.py", line 211 in get_torch_device
  File "F:\JianxiaAI\ComfyUI\comfy\model_management.py", line 362 in <module>
  File "<frozen importlib._bootstrap>", line 488 in _call_with_frames_removed
  File "<frozen importlib._bootstrap_external>", line 1023 in exec_module
  File "<frozen importlib._bootstrap>", line 935 in _load_unlocked
  File "<frozen importlib._bootstrap>", line 1331 in _find_and_load_unlocked
  File "<frozen importlib._bootstrap>", line 1360 in _find_and_load
  File "F:\JianxiaAI\ComfyUI\execution.py", line 18 in <module>
  File "<frozen importlib._bootstrap>", line 488 in _call_with_frames_removed
  File "<frozen importlib._bootstrap_external>", line 1023 in exec_module
  File "<frozen importlib._bootstrap>", line 935 in _load_unlocked
  File "<frozen importlib._bootstrap>", line 1331 in _find_and_load_unlocked
  File "<frozen importlib._bootstrap>", line 1360 in _find_and_load
  File "F:\JianxiaAI\ComfyUI\main.py", line 227 in <module>

[release] 鍚姩澶辫触
Traceback (most recent call last):
  File "release.py", line 52, in run_release
RuntimeError: ComfyUI 鍚姩瓒呮椂锛岃鏌ョ湅 data/runtime.log

rnderman0 发表于 2026-9-10 13:57:14

大佬为什么单图编辑的人物会无视关键词选择性生成图片呢？且生成的图片会与原图有极强相似性（动作，表情等），或是直接对原图进行二次的添加型编辑（如：参考图为半身照，生成图在原图基础上强行接上下半身），有办法使它只识别参考图脸部，进行二次创作而不是加工吗，希望大佬不吝赐教

ptm996 发表于 2026-9-10 08:46:05

无法连接，这回事？

360截图20260910083747318.jpg (14.01 KB, 下载次数: 2)

360截图20260910083747318.jpg

ptm996 发表于 2026-9-9 15:54:48

解压失败，启动超时。

13614669200 发表于 2026-9-9 10:13:50

楼主这个素材和模型可以自行添加吗

我要攻击之爪 发表于 2026-9-8 15:22:35

大佬，请问有图生图的整合包吗

yuantanliuhe 发表于 2026-9-6 23:45:19

静若发表于 2026-7-18 21:36
带了，这个主模型：Krea2-TurboNSWAIO_v10_fp8，就支持nsfw图片生成
关于使用图片编辑，一定要把；krea2_ ...

大佬这个模型在哪下载

yuantanliuhe 发表于 2026-9-4 23:26:20

单图编辑跟双图编辑求提示词，感谢大哥

lsw2333 发表于 2026-9-3 23:05:49

太66666

我们不生产资源，只做资源的搬运工。

广告合作-tags标签-app下载-Archiver-小黑屋-