无法载入flow

Question

无法载入flow

Opened this issue 4 months ago · 4 comments

Save Completed!
Save Completed!
Save Completed!
Start parsing settings...
Start parsing settings...

Answer 1 · 2024-08-26T16:40:41.000Z

Answer 2 · 2024-08-27T12:42:12.000Z

https://ipqg3qdsf0.feishu.cn/docx/ILxNdpJFOoTlmnx9XjfcC7qvnIg
有问题可以先对着我们的文档看一下~
然后还是不行的话，把运行的SDWebUI的版本，还有控制台的输出都截图发出来，我们才能知道是什么问题。

Answer 3 · 2024-09-09T11:56:24.000Z

我也遇到同样的问题，按文档操作也不行
控制台输出：
Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug 1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)] Version: f2.0.1v1.10.1-previous-525-gefe6fed4 Commit hash: efe6fed4994e6d29627d5172aecde71e7e496255 Installing requirements loading WD14-tagger reqs from F:\aidraw\webui-forge\webui\extensions\stable-diffusion-webui-wd14-tagger\requirements.txt Checking WD14-tagger requirements. Launching Web UI with arguments: --ckpt-dir F:/aidraw/stable-diffusion-webui/models/Stable-diffusion --hypernetwork-dir F:/aidraw/stable-diffusion-webui/models/hypernetworks --embeddings-dir F:/aidraw/stable-diffusion-webui/embeddings --lora-dir F:/aidraw/stable-diffusion-webui/models/Lora --vae-dir F:/aidraw/stable-diffusion-webui/models/VAE Total VRAM 12282 MB, total RAM 32608 MB pytorch version: 2.3.1+cu121 Set vram state to: NORMAL_VRAM Device: cuda:0 NVIDIA GeForce RTX 4070 : native Hint: your device supports --cuda-malloc for potential speed improvements. VAE dtype preferences: [torch.bfloat16, torch.float32] -> torch.bfloat16 CUDA Using Stream: False F:\aidraw\webui-forge\system\python\lib\site-packages\transformers\utils\hub.py:127: FutureWarning: Using TRANSFORMERS_CACHEis deprecated and will be removed in v5 of Transformers. UseHF_HOMEinstead. warnings.warn( 2024-09-09 19:51:51.225954: I tensorflow/core/util/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 variableTF_ENABLE_ONEDNN_OPTS=0. 2024-09-09 19:51:51.804229: I tensorflow/core/util/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`.
Using pytorch cross attention
Using pytorch attention for VAE
ControlNet preprocessor location: F:\aidraw\webui-forge\webui\models\ControlNetPreprocessor
[-] ADetailer initialized. version: 24.9.0, num models: 10
dirname: F:\aidraw\webui-forge\webui\localizations
localizations: {'zh_CN': 'F:\aidraw\webui-forge\webui\extensions\stable-diffusion-webui-localization-zh_CN\localizations\zh_CN.json'}
== WD14 tagger /gpu:0, uname_result(system='Windows', node='DESKTOP-QGEKM5K', release='10', version='10.0.19045', machine='AMD64') ==
2024-09-09 19:52:00,408 - ControlNet - INFO - ControlNet UI callback registered.
LightDiffusionFlow 绑定完成
F:\aidraw\webui-forge\webui\extensions\stable-diffusion-webui-wd14-tagger\tagger\ui.py:232: GradioDeprecationWarning: unexpected argument for HTML: interactive
info = gr.HTML(
Model selected: {'checkpoint_info': {'filename': 'F:\aidraw\stable-diffusion-webui\models\Stable-diffusion\AOM3A3_orangemixs.safetensors', 'hash': '9600da17'}, 'additional_modules': ['F:\aidraw\stable-diffusion-webui\models\VAE\clearvae_v23.safetensors'], 'unet_storage_dtype': None}
Using online LoRAs in FP16: False
Running on local URL: http://127.0.0.1:7860

To create a public link, set share=True in launch().
----------------- light_diffusion_flow api start------------------
Startup time: 24.4s (prepare environment: 9.0s, import torch: 6.7s, other imports: 0.4s, load scripts: 4.0s, create ui: 2.3s, gradio launch: 1.6s, app_started_callback: 0.2s).
refresh_ui
Environment vars changed: {'stream': False, 'inference_memory': 1024.0, 'pin_shared_memory': False}
[GPU Setting] You will use 91.66% GPU memory (11257.00 MB) to load weights, and use 8.34% GPU memory (1024.00 MB) to do matrix computation.
开始解析设置...`

版本信息：（webui用的forge）
WebUI 版本：f2.0.1v1.10.1-previous-525-gefe6fed4
Python 版本：3.10.6
torch: 2.3.1+cu121
xformers: N/A
gradio: 4.40.0

Answer 4 · 2024-09-09T11:57:45.000Z

我也遇到同样的问题，按文档操作也不行控制台输出： Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug 1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)] Version: f2.0.1v1.10.1-previous-525-gefe6fed4 Commit hash: efe6fed4994e6d29627d5172aecde71e7e496255 Installing requirements loading WD14-tagger reqs from F:\aidraw\webui-forge\webui\extensions\stable-diffusion-webui-wd14-tagger\requirements.txt Checking WD14-tagger requirements. Launching Web UI with arguments: --ckpt-dir F:/aidraw/stable-diffusion-webui/models/Stable-diffusion --hypernetwork-dir F:/aidraw/stable-diffusion-webui/models/hypernetworks --embeddings-dir F:/aidraw/stable-diffusion-webui/embeddings --lora-dir F:/aidraw/stable-diffusion-webui/models/Lora --vae-dir F:/aidraw/stable-diffusion-webui/models/VAE Total VRAM 12282 MB, total RAM 32608 MB pytorch version: 2.3.1+cu121 Set vram state to: NORMAL_VRAM Device: cuda:0 NVIDIA GeForce RTX 4070 : native Hint: your device supports --cuda-malloc for potential speed improvements. VAE dtype preferences: [torch.bfloat16, torch.float32] -> torch.bfloat16 CUDA Using Stream: False F:\aidraw\webui-forge\system\python\lib\site-packages\transformers\utils\hub.py:127: FutureWarning: Using TRANSFORMERS_CACHEis deprecated and will be removed in v5 of Transformers. UseHF_HOMEinstead. warnings.warn( 2024-09-09 19:51:51.225954: I tensorflow/core/util/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 variableTF_ENABLE_ONEDNN_OPTS=0. 2024-09-09 19:51:51.804229: I tensorflow/core/util/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`. Using pytorch cross attention Using pytorch attention for VAE ControlNet preprocessor location: F:\aidraw\webui-forge\webui\models\ControlNetPreprocessor [-] ADetailer initialized. version: 24.9.0, num models: 10 dirname: F:\aidraw\webui-forge\webui\localizations localizations: {'zh_CN': 'F:\aidraw\webui-forge\webui\extensions\stable-diffusion-webui-localization-zh_CN\localizations\zh_CN.json'} == WD14 tagger /gpu:0, uname_result(system='Windows', node='DESKTOP-QGEKM5K', release='10', version='10.0.19045', machine='AMD64') == 2024-09-09 19:52:00,408 - ControlNet - INFO - ControlNet UI callback registered. LightDiffusionFlow 绑定完成 F:\aidraw\webui-forge\webui\extensions\stable-diffusion-webui-wd14-tagger\tagger\ui.py:232: GradioDeprecationWarning: unexpected argument for HTML: interactive info = gr.HTML( Model selected: {'checkpoint_info': {'filename': 'F:\aidraw\stable-diffusion-webui\models\Stable-diffusion\AOM3A3_orangemixs.safetensors', 'hash': '9600da17'}, 'additional_modules': ['F:\aidraw\stable-diffusion-webui\models\VAE\clearvae_v23.safetensors'], 'unet_storage_dtype': None} Using online LoRAs in FP16: False Running on local URL: http://127.0.0.1:7860

To create a public link, set share=True in launch(). ----------------- light_diffusion_flow api start------------------ Startup time: 24.4s (prepare environment: 9.0s, import torch: 6.7s, other imports: 0.4s, load scripts: 4.0s, create ui: 2.3s, gradio launch: 1.6s, app_started_callback: 0.2s). refresh_ui Environment vars changed: {'stream': False, 'inference_memory': 1024.0, 'pin_shared_memory': False} [GPU Setting] You will use 91.66% GPU memory (11257.00 MB) to load weights, and use 8.34% GPU memory (1024.00 MB) to do matrix computation. 开始解析设置...`

版本信息：（webui用的forge） WebUI 版本：f2.0.1v1.10.1-previous-525-gefe6fed4 Python 版本：3.10.6 torch: 2.3.1+cu121 xformers: N/A gradio: 4.40.0

补充一下，载入的文件是example/lightflow艺术二维码.flow