search

yangxy / PASD

[ECCV2024] Pixel-Aware Stable Diffusion for Realistic Image Super-Resolution and Personalized Stylization
Apache License 2.0
885 stars 61 forks source link

Is there any installation guidance? #11

Open Kiteretsu77 opened 1 year ago

Kiteretsu77 commented 1 year ago

Hello! Is there any package installation guidance? I try to use pip install -r requirements.txt. However, the diffusers package with the latest one cannot find some function sometimes. Is there any specific version for diffusers used in the experiments of the paper? Thanks!

DashBe commented 1 year ago

I think the codebase of this repository is from diffusers 0.17 or 0.18. for example, StableDiffusionControlNetPipeline of PASD has the method enable_sequential_cpu_offload, but it doesn't exist in 0.19 and higher. It's only in 0.17 and 0.18.

yangxy commented 1 year ago

I have updated the project to support the latest diffusers(=0.21.4). Please have a try now.

h3clikejava commented 11 months ago

(h3c_temp) h3c@H3c-4070:~/Documents/PASD$ python gradio_pasd.py /home/h3c/Documents/PASD/pipelines/pipeline_pasd.py:41: FutureWarning: Importing DiffusionPipeline or ImagePipelineOutput from diffusers.pipeline_utils is deprecated. Please import from diffusers.pipelines.pipeline_utils instead. from diffusers.pipeline_utils import DiffusionPipeline /home/h3c/.local/lib/python3.10/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead. warnings.warn( /home/h3c/.local/lib/python3.10/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or None for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing weights=None. warnings.warn(msg) /home/h3c/.local/lib/python3.10/site-packages/torchvision/transforms/functional_tensor.py:5: UserWarning: The torchvision.transforms.functional_tensor module is deprecated in 0.15 and will be removed in 0.17. Please don't rely on it. You probably just need to use APIs in torchvision.transforms.functional or in torchvision.transforms.v2.functional. warnings.warn( Traceback (most recent call last): File "/home/h3c/Documents/PASD/gradio_pasd.py", line 41, in text_encoder = CLIPTextModel.from_pretrained(pretrained_model_path, subfolder="text_encoder") File "/home/h3c/anaconda3/envs/h3c_temp/lib/python3.10/site-packages/transformers/modeling_utils.py", line 2301, in from_pretrained state_dict = load_state_dict(resolved_archive_file) File "/home/h3c/anaconda3/envs/h3c_temp/lib/python3.10/site-packages/transformers/modeling_utils.py", line 402, in load_state_dict with safe_open(checkpoint_file, framework="pt") as f: safetensors_rust.SafetensorError: Error while deserializing header: HeaderTooLarge