search

johannakarras / DreamPose

Official implementation of "DreamPose: Fashion Image-to-Video Synthesis via Stable Diffusion"
MIT License
962 stars 73 forks source link

Demo run issue #27

Closed YuanZi1501040205 closed 1 year ago

YuanZi1501040205 commented 1 year ago

Looks like the model is loaded successfully in your update version. But I have met another issue that says the hugging face validation needs the repo_name. What should I do ti resolve this issue? Many thanks!

Tried the demo:

jupyter@jupycolab:~/aik3d/DreamPose$ python test.py --epoch 499 --folder demo/custom-chkpts --pose_folder demo/sample/poses --key_frame_path demo/sample/key_frame.png --s1 8 --s2 3 --n_steps 100 --output_dir demo/sample/results --custom_vae demo/custom-chkpts/vae_1499.pth

Got the following issue:

Loading demo/custom-chkpts/unet_epoch_499.pth Loading custom model from: demo/custom-chkpts/checkpoint-499 Traceback (most recent call last): File "test.py", line 60, in pipe = StableDiffusionImg2ImgPipeline.from_pretrained(model_id, unet=unet, torch_dtype=torch.float16, revision="fp16") File "/opt/conda/envs/anerf/lib/python3.8/site-packages/diffusers/pipelines/pipeline_utils.py", line 856, in from_pretrained cached_folder = cls.download( File "/opt/conda/envs/anerf/lib/python3.8/site-packages/diffusers/pipelines/pipeline_utils.py", line 1177, in download config_file = hf_hub_download( File "/opt/conda/envs/anerf/lib/python3.8/site-packages/huggingface_hub/utils/_validators.py", line 112, in _inner_fn validate_repo_id(arg_value) File "/opt/conda/envs/anerf/lib/python3.8/site-packages/huggingface_hub/utils/_validators.py", line 160, in validate_repo_id raise HFValidationError( huggingface_hub.utils._validators.HFValidationError: Repo id must be in the form 'repo_name' or 'namespace/repo_name': 'demo/custom-chkpts/checkpoint-499'. Use repo_type argument if needed.

YuanZi1501040205 commented 1 year ago

I figured out I need to paste all files in zip file instead of only vae pth file