open-mmlab / StyleShot

StyleShot: A SnapShot on Any Style. 一款可以迁移任意风格到任意内容的模型,无需针对图片微调,即能生成高质量的个性风格化图片!
https://styleshot.github.io/
MIT License
270 stars 16 forks source link

Hugginface runwayml/stable-diffusion-v1-5 not working now #26

Closed rhtm02 closed 3 months ago

rhtm02 commented 3 months ago

Hi. first thx to your nice works. really impressed!

but i have one issue running your demo. Traceback (most recent call last): File "styleshot_text_driven_demo.py", line 47, in <module> main(args) File "styleshot_text_driven_demo.py", line 19, in main base_model_path = snapshot_download(base_model_path, local_dir=base_model_path) File "/home/hjlee/anaconda3/envs/styleshot/lib/python3.8/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn return fn(*args, **kwargs) File "/home/hjlee/anaconda3/envs/styleshot/lib/python3.8/site-packages/huggingface_hub/_snapshot_download.py", line 238, in snapshot_download raise api_call_error File "/home/hjlee/anaconda3/envs/styleshot/lib/python3.8/site-packages/huggingface_hub/_snapshot_download.py", line 169, in snapshot_download repo_info = api.repo_info(repo_id=repo_id, repo_type=repo_type, revision=revision, token=token) File "/home/hjlee/anaconda3/envs/styleshot/lib/python3.8/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn return fn(*args, **kwargs) File "/home/hjlee/anaconda3/envs/styleshot/lib/python3.8/site-packages/huggingface_hub/hf_api.py", line 2588, in repo_info return method( File "/home/hjlee/anaconda3/envs/styleshot/lib/python3.8/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn return fn(*args, **kwargs) File "/home/hjlee/anaconda3/envs/styleshot/lib/python3.8/site-packages/huggingface_hub/hf_api.py", line 2373, in model_info hf_raise_for_status(r) File "/home/hjlee/anaconda3/envs/styleshot/lib/python3.8/site-packages/huggingface_hub/utils/_errors.py", line 352, in hf_raise_for_status raise RepositoryNotFoundError(message, response) from e huggingface_hub.utils._errors.RepositoryNotFoundError: 401 Client Error. (Request ID: Root=1-66d19fb2-4cecc1ab79e34c007ad62889;79c2524e-b5bb-4f16-817a-3a891177edd2)

maybe this repo is not working now. so i want to get pre-trained weight for runwayml/stable-diffusion-v1-5.

thank you!

Jeoyal commented 3 months ago

Hi @rhtm02, thank you for your interest in our work. You can search for the keyword stable-diffusion-v1-5 to find other accessible repositories on Huggingface (e.g., benjamin-paine/stable-diffusion-v1-5).

rhtm02 commented 3 months ago

thx for your fast answer! one more thing to ask you.. how much vram request this demo? i just use style transfer using reference image. fp16 is working?

Jeoyal commented 3 months ago

FP16 is working. Inference on FP32 might require 8GB to 10GB of VRAM (depending on whether the content fusion encoder is used), but you can offload some modules to the CPU to free up more VRAM. For more information, refer to #17.

rhtm02 commented 3 months ago

thank you! have a nice day

Jeoyal commented 3 months ago

You're welcome! Hope you achieve the results you desire. :)