search

s4afa451dgf415f / colab_stable_diffusion

stable_diffusion_webui的colab部署版本(including English version)，下载了所流行插件依赖和并进行初始化配置。拥有mod管理、手机自适应、图片信息本地读取等脚本。
655 stars 78 forks source link

[BUG]無法運行webui #46

Closed Cosplayeridol closed 6 months ago

Cosplayeridol commented 7 months ago

/content/stable-diffusion-webui Python 3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0] Version: v1.6.0 Commit hash: 5ef669de080814067961f28357256e8fe27544f4 Installing clip Installing open_clip Cloning Stable Diffusion into /content/stable-diffusion-webui/repositories/stable-diffusion-stability-ai... Cloning into '/content/stable-diffusion-webui/repositories/stable-diffusion-stability-ai'... remote: Enumerating objects: 580, done. remote: Counting objects: 100% (357/357), done. remote: Compressing objects: 100% (126/126), done. remote: Total 580 (delta 260), reused 231 (delta 231), pack-reused 223 Receiving objects: 100% (580/580), 73.44 MiB | 15.68 MiB/s, done. Resolving deltas: 100% (279/279), done. Cloning Stable Diffusion XL into /content/stable-diffusion-webui/repositories/generative-models... Cloning into '/content/stable-diffusion-webui/repositories/generative-models'... remote: Enumerating objects: 941, done. remote: Total 941 (delta 0), reused 0 (delta 0), pack-reused 941 Receiving objects: 100% (941/941), 43.85 MiB | 16.05 MiB/s, done. Resolving deltas: 100% (491/491), done. Cloning K-diffusion into /content/stable-diffusion-webui/repositories/k-diffusion... Cloning into '/content/stable-diffusion-webui/repositories/k-diffusion'... remote: Enumerating objects: 1340, done. remote: Counting objects: 100% (622/622), done. remote: Compressing objects: 100% (86/86), done. remote: Total 1340 (delta 576), reused 547 (delta 536), pack-reused 718 Receiving objects: 100% (1340/1340), 242.04 KiB | 18.62 MiB/s, done. Resolving deltas: 100% (939/939), done. Cloning CodeFormer into /content/stable-diffusion-webui/repositories/CodeFormer... Cloning into '/content/stable-diffusion-webui/repositories/CodeFormer'... remote: Enumerating objects: 594, done. remote: Counting objects: 100% (594/594), done. remote: Compressing objects: 100% (316/316), done. remote: Total 594 (delta 287), reused 493 (delta 269), pack-reused 0 Receiving objects: 100% (594/594), 17.31 MiB | 16.61 MiB/s, done. Resolving deltas: 100% (287/287), done. Cloning BLIP into /content/stable-diffusion-webui/repositories/BLIP... Cloning into '/content/stable-diffusion-webui/repositories/BLIP'... remote: Enumerating objects: 277, done. remote: Counting objects: 100% (165/165), done. remote: Compressing objects: 100% (30/30), done. remote: Total 277 (delta 137), reused 136 (delta 135), pack-reused 112 Receiving objects: 100% (277/277), 7.03 MiB | 20.18 MiB/s, done. Resolving deltas: 100% (152/152), done. Installing requirements for CodeFormer Installing requirements Downloading pose_landmark_full.tflite... Downloading pose_web.binarypb... Downloading pose_solution_packed_assets.data... Downloading pose_solution_simd_wasm_bin.wasm... Downloading pose_solution_packed_assets_loader.js... Downloading pose_solution_simd_wasm_bin.js... Installing sd-webui-controlnet requirement: fvcore Installing sd-webui-controlnet requirement: mediapipe Installing sd-webui-controlnet requirement: onnxruntime Installing sd-webui-controlnet requirement: svglib ControlNet init warning: Unable to install insightface automatically. Please try run pip install insightface manually. Installing sd-webui-controlnet requirement: handrefinerportable Installing sd-webui-controlnet requirement: depth_anything Installing sd-webui-prompt-all-in-one: execjs Installing sd-webui-prompt-all-in-one: pathos Installing sd-webui-prompt-all-in-one: openai Installing sd-webui-prompt-all-in-one: boto3 Installing sd-webui-prompt-all-in-one: aliyunsdkcore Installing sd-webui-prompt-all-in-one: aliyunsdkalimt loading WD14-tagger reqs from /content/stable-diffusion-webui/extensions/stable-diffusion-webui-wd14-tagger/requirements.txt Checking WD14-tagger requirements. Launching Web UI with arguments: --share --medvram-sdxl --disable-safe-unpickle --disable-console-progressbars --xformers --enable-insecure-extension-access --opt-sub-quad-attention --no-half-vae --opt-channelslast --api --theme=light WARNING:xformers:WARNING[XFORMERS]: xFormers can't load C++/CUDA extensions. xFormers was built for: PyTorch 2.1.0+cu121 with CUDA 1201 (you have 2.2.1+cu121) Python 3.10.13 (you have 3.10.12) Please reinstall xformers (see https://github.com/facebookresearch/xformers#installing-xformers) Memory-efficient attention, SwiGLU, sparse and more won't be available. Set XFORMERS_MORE_DETAILS=1 for more details ** Error setting up CodeFormer Traceback (most recent call last): File "/content/stable-diffusion-webui/modules/codeformer_model.py", line 30, in setup_model from modules.codeformer.codeformer_arch import CodeFormer File "/content/stable-diffusion-webui/modules/codeformer/codeformer_arch.py", line 9, in from modules.codeformer.vqgan_arch import VQAutoEncoder, ResBlock File "/content/stable-diffusion-webui/modules/codeformer/vqgan_arch.py", line 11, in from basicsr.utils import get_root_logger File "/usr/local/lib/python3.10/dist-packages/basicsr/init.py", line 4, in from .data import File "/usr/local/lib/python3.10/dist-packages/basicsr/data/init.py", line 22, in _dataset_modules = [importlib.import_module(f'basicsr.data.{file_name}') for file_name in dataset_filenames] File "/usr/local/lib/python3.10/dist-packages/basicsr/data/init.py", line 22, in _dataset_modules = [importlib.import_module(f'basicsr.data.{file_name}') for file_name in dataset_filenames] File "/usr/lib/python3.10/importlib/init.py", line 126, in import_module return _bootstrap._gcd_import(name[level:], package, level) File "/usr/local/lib/python3.10/dist-packages/basicsr/data/realesrgan_dataset.py", line 11, in from basicsr.data.degradations import circular_lowpass_kernel, random_mixed_kernels File "/usr/local/lib/python3.10/dist-packages/basicsr/data/degradations.py", line 8, in from torchvision.transforms.functional_tensor import rgb_to_grayscale ModuleNotFoundError: No module named 'torchvision.transforms.functional_tensor'

Traceback (most recent call last): File "/content/stable-diffusion-webui/launch.py", line 48, in main() File "/content/stable-diffusion-webui/launch.py", line 44, in main start() File "/content/stable-diffusion-webui/modules/launch_utils.py", line 436, in start webui.webui() File "/content/stable-diffusion-webui/webui.py", line 52, in webui initialize.initialize() File "/content/stable-diffusion-webui/modules/initialize.py", line 71, in initialize from modules import gfpgan_model File "/content/stable-diffusion-webui/modules/gfpgan_model.py", line 4, in import gfpgan File "/usr/local/lib/python3.10/dist-packages/gfpgan/init.py", line 3, in from .data import File "/usr/local/lib/python3.10/dist-packages/gfpgan/data/init.py", line 10, in _dataset_modules = [importlib.import_module(f'gfpgan.data.{file_name}') for file_name in dataset_filenames] File "/usr/local/lib/python3.10/dist-packages/gfpgan/data/init.py", line 10, in _dataset_modules = [importlib.import_module(f'gfpgan.data.{file_name}') for file_name in dataset_filenames] File "/usr/lib/python3.10/importlib/init.py", line 126, in import_module return _bootstrap._gcd_import(name[level:], package, level) File "/usr/local/lib/python3.10/dist-packages/gfpgan/data/ffhq_degradation_dataset.py", line 7, in from basicsr.data import degradations as degradations File "/usr/local/lib/python3.10/dist-packages/basicsr/init.py", line 4, in from .data import File "/usr/local/lib/python3.10/dist-packages/basicsr/data/init.py", line 22, in _dataset_modules = [importlib.import_module(f'basicsr.data.{file_name}') for file_name in dataset_filenames] File "/usr/local/lib/python3.10/dist-packages/basicsr/data/init.py", line 22, in _dataset_modules = [importlib.import_module(f'basicsr.data.{file_name}') for file_name in dataset_filenames] File "/usr/lib/python3.10/importlib/init.py", line 126, in import_module return _bootstrap._gcd_import(name[level:], package, level) File "/usr/local/lib/python3.10/dist-packages/basicsr/data/realesrgan_dataset.py", line 11, in from basicsr.data.degradations import circular_lowpass_kernel, random_mixed_kernels File "/usr/local/lib/python3.10/dist-packages/basicsr/data/degradations.py", line 8, in from torchvision.transforms.functional_tensor import rgb_to_grayscale ModuleNotFoundError: No module named 'torchvision.transforms.functional_tensor'

s4afa451dgf415f commented 7 months ago

Google updated Torch's version, which led to Xformers not being compatible with the corresponding version of SD. Currently, I can only reinstall Torch, which will take an extra 1-2 minutes. I will look for a solution afterwards

Cosplayeridol commented 7 months ago

Google updated Torch's version, which led to Xformers not being compatible with the corresponding version of SD. Currently, I can only reinstall Torch, which will take an extra 1-2 minutes. I will look for a solution afterwards

The webui still cannot be used. The prompt in step 4 includes, for example, the file path of lora, which is missing. The situation seems to be getting worse.

s4afa451dgf415f commented 7 months ago

image I tested it locally and it ran fine, generating the corresponding images. If you still encounter issues after updating from Git, i need your printed error log to analyze.

Cosplayeridol commented 7 months ago

image I tested it locally and it ran fine, generating the corresponding images. If you still encounter issues after updating from Git, i need your printed error log to analyze.

Unable to download model 2.2 step [{'name': 'fantasticmix25d', 'type': '', 'downloadLink': 'https://civitai.com/models/20632/fantasticmix25d', 'size': '', 'path': '/content/stable-diffusion-webui/models/Lora', 'lastChangeDate': '2024-03-24'}, {'name': 'fantasticmix25d', 'type': '', 'downloadLink': 'https://civitai.com/models/20632/fantasticmix25d', 'size': '', 'path': '/content/stable-diffusion-webui/models/Lora', 'lastChangeDate': '2024-03-26'}, {'name': 'fantasticmix2.5D.5D', 'type': '', 'downloadLink': 'https://civitai.com/models/20632?modelVersionId=143050', 'size': '5.78GB', 'path': '/content/stable-diffusion-webui/models/Stable-diffusion', 'lastChangeDate': '2024-03-26'}, {'name': 'mordred-fateapocrypha-lora-or-6-outfits', 'type': '', 'downloadLink': 'https://civitai.com/models/342287/mordred-fateapocrypha-lora-or-6-outfits', 'size': '', 'path': '/content/stable-diffusion-webui/models/Lora', 'lastChangeDate': '2024-03-26'}] [{'name': 'fantasticmix2.5D', 'type': '', 'downloadLink': 'https://civitai.com/models/20632/fantasticmix25d', 'size': '', 'path': '/content/stable-diffusion-webui/models/Stable-diffusion', 'lastChangeDate': '2024-03-26'}] /content/stable-diffusion-webui/models/Lora/fantasticmix25d不存在，重命名失败 new 1 0 old 1 3 fantasticmix25d为旧不重复mod，将删除 fantasticmix25d不存在，删除失败 fantasticmix2.5D.5D为旧不重复mod，将删除 fantasticmix2.5D.5D不存在，删除失败 mordred-fateapocrypha-lora-or-6-outfits为旧不重复mod，将删除 mordred-fateapocrypha-lora-or-6-outfits不存在，删除失败 [] image

Cosplayeridol commented 7 months ago

image I tested it locally and it ran fine, generating the corresponding images. If you still encounter issues after updating from Git, i need your printed error log to analyze.

Unable to download model 2.2 step [{'name': 'fantasticmix25d', 'type': '', 'downloadLink': 'https://civitai.com/models/20632/fantasticmix25d', 'size': '', 'path': '/content/stable-diffusion-webui/models/Lora', 'lastChangeDate': '2024-03-24'}, {'name': 'fantasticmix25d', 'type': '', 'downloadLink': 'https://civitai.com/models/20632/fantasticmix25d', 'size': '', 'path': '/content/stable-diffusion-webui/models/Lora', 'lastChangeDate': '2024-03-26'}, {'name': 'fantasticmix2.5D.5D', 'type': '', 'downloadLink': 'https://civitai.com/models/20632?modelVersionId=143050', 'size': '5.78GB', 'path': '/content/stable-diffusion-webui/models/Stable-diffusion', 'lastChangeDate': '2024-03-26'}, {'name': 'mordred-fateapocrypha-lora-or-6-outfits', 'type': '', 'downloadLink': 'https://civitai.com/models/342287/mordred-fateapocrypha-lora-or-6-outfits', 'size': '', 'path': '/content/stable-diffusion-webui/models/Lora', 'lastChangeDate': '2024-03-26'}] [{'name': 'fantasticmix2.5D', 'type': '', 'downloadLink': 'https://civitai.com/models/20632/fantasticmix25d', 'size': '', 'path': '/content/stable-diffusion-webui/models/Stable-diffusion', 'lastChangeDate': '2024-03-26'}] /content/stable-diffusion-webui/models/Lora/fantasticmix25d不存在，重命名失败 new 1 0 old 1 3 fantasticmix25d为旧不重复mod，将删除 fantasticmix25d不存在，删除失败 fantasticmix2.5D.5D为旧不重复mod，将删除 fantasticmix2.5D.5D不存在，删除失败 mordred-fateapocrypha-lora-or-6-outfits为旧不重复mod，将删除 mordred-fateapocrypha-lora-or-6-outfits不存在，删除失败 [] image

I tried it again, and the downloaded model file was only 311kb, but the total size of this model was 5.78GB. Not only the CHECKPOINT model, but also the lora model is like this. The complete file cannot be downloaded, and the file size is only between 100~400kb.

s4afa451dgf415f commented 7 months ago

QQ截图20240326193414 In fact, the link you copied is the webpage link of the model, but what's needed here is the download link, as shown in the picture to be correct.And the download paths for the model's files and checkpoints are not necessary as they will automatically be placed in the specified path unless you need to download something else like embedding and then you will need to fill in the path.