Where is the requirements.txt? Could you provide a colab notebook?

[hsgwktb]

Where is the requirements.txt? Could you provide a colab notebook? #1

[hsgwktb]

This is my notebook, it doesn't work.

!git clone https://github.com/ali-vilab/MangaNinjia
%cd /content/MangaNinjia
!conda env create -f environment.yaml
!conda activate MangaNinjia
!pip install -r requirements.txt
!apt -y install -qq aria2
!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5/resolve/main/v1-5-pruned.safetensors -d "/content/checkpoints/StableDiffusion" -o v1-5-pruned.safetensors
!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/openai/clip-vit-large-patch14/resolve/main/model.safetensors -d "/content/checkpoints/clip-vit-large-patch14" -o clip-vit-large-patch14.safetensors
!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lllyasviel/control_v11p_sd15_lineart/resolve/main/diffusion_pytorch_model.safetensors -d "/content/checkpoints/control_v11p_sd15_lineart" -o control_v11p_sd15_lineart.safetensors
!wget https://huggingface.co/lllyasviel/Annotators/resolve/main/sk_model.pth -O "/content/checkpoints/Annotators/sk_model.pth"
!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/Johanan0528/MangaNinjia/resolve/main/denoising_unet.pth -d "/content/checkpoints/MangaNinjia" -o denoising_unet.pth
!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/Johanan0528/MangaNinjia/resolve/main/reference_unet.pth -d "/content/checkpoints/MangaNinjia" -o reference_unet.pth
!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/Johanan0528/MangaNinjia/resolve/main/point_net.pth -d "/content/checkpoints/MangaNinjia" -o point_net.pth
!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/Johanan0528/MangaNinjia/resolve/main/controlnet.pth -d "/content/checkpoints/MangaNinjia" -o controlnet.pth

%cd scripts
!bash infer.sh

!python run_gradio.py

[Johanan528]

Hi, we provide a yaml environment file. Btw, where is the problem?

[hsgwktb]

checkpoints/
├── Annotators/
│ └── sk_model.pth
├── MangaNinja/
│ ├── controlnet.pth
│ ├── denoising_unet.pth
│ ├── point_net.pth
│ └── reference_unet.pth
├── StableDiffusion/
│ └── v1-5-pruned.safetensors
├── clip-vit-large-patch14/
│ └── clip-vit-large-patch14.safetensors
└── control_v11p_sd15_lineart/
└── control_v11p_sd15_lineart.safetensors

run !python run_gradio.py

output:
/usr/local/lib/python3.10/dist-packages/gradio_client/documentation.py:106: UserWarning: Could not get documentation group for <class 'gradio.mix.Parallel'>: No known documentation group for module 'gradio.mix'
warnings.warn(f"Could not get documentation group for {cls}: {exc}")
/usr/local/lib/python3.10/dist-packages/gradio_client/documentation.py:106: UserWarning: Could not get documentation group for <class 'gradio.mix.Series'>: No known documentation group for module 'gradio.mix'
warnings.warn(f"Could not get documentation group for {cls}: {exc}")
2025-01-15 12:16:45.179245: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:485] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
2025-01-15 12:16:45.213293: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:8454] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
2025-01-15 12:16:45.226527: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1452] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
2025-01-15 12:16:46.612029: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
/usr/local/lib/python3.10/dist-packages/diffusers/models/dual_transformer_2d.py:20: FutureWarning: DualTransformer2DModel is deprecated and will be removed in version 0.29. Importing DualTransformer2DModel from diffusers.models.dual_transformer_2d is deprecated and this will be removed in a future version. Please use from diffusers.models.transformers.dual_transformer_2d import DualTransformer2DModel, instead.
deprecate("DualTransformer2DModel", "0.29", deprecation_message)
Traceback (most recent call last):
File "/usr/local/lib/python3.10/dist-packages/diffusers/configuration_utils.py", line 380, in load_config
config_file = hf_hub_download(
File "/usr/local/lib/python3.10/dist-packages/huggingface_hub/utils/_deprecation.py", line 101, in inner_f
return f(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/huggingface_hub/utils/_validators.py", line 106, in _inner_fn
validate_repo_id(arg_value)
File "/usr/local/lib/python3.10/dist-packages/huggingface_hub/utils/_validators.py", line 154, in validate_repo_id
raise HFValidationError(
huggingface_hub.errors.HFValidationError: Repo id must be in the form 'repo_name' or 'namespace/repo_name': './checkpoints/StableDiffusion'. Use repo_type argument if needed.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/content/MangaNinjia/run_gradio.py", line 43, in
noise_scheduler = DDIMScheduler.from_pretrained(pretrained_model_name_or_path,subfolder='scheduler')
File "/usr/local/lib/python3.10/dist-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn
return fn(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/diffusers/schedulers/scheduling_utils.py", line 143, in from_pretrained
config, kwargs, commit_hash = cls.load_config(
File "/usr/local/lib/python3.10/dist-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn
return fn(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/diffusers/configuration_utils.py", line 415, in load_config
raise EnvironmentError(
OSError: We couldn't connect to 'https://huggingface.co/' to load this model, couldn't find it in the cached files and it looks like ./checkpoints/StableDiffusion is not the path to a directory containing a scheduler_config.json file.
Checkout your internet connection or see how to run the library in offline mode at 'https://huggingface.co/docs/diffusers/installation#offline-mode'.

[Deathdadev]

You have directly installed the model file from huggingface, where this project is trying to reference files from the diffusers version of this model.

i.e: The code is looking for scheduler_config.json from https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5/tree/main , but you have only installed the safetensors file: https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5/resolve/main/v1-5-pruned.safetensors

This is the same for most of the installed models you have in your colab code. Make sure that you are following the correct directory structure; if there is no file such as *.pth, then you can assume it is the full folder for the model:

-- checkpoints
    |-- StableDiffusion
    |-- models
        |-- clip-vit-large-patch14
        |-- control_v11p_sd15_lineart
        |-- Annotators
            |--sk_model.pth
    |-- MangaNinjia
        |-- denoising_unet.pth
        |-- reference_unet.pth
        |-- point_net.pth
        |-- controlnet.pth