mayuelala
commented
1 month ago you can download the weight from huggingface and put them in right path
Open ychenZHANG opened 1 month ago
mayuelala
commented
1 month ago you can download the weight from huggingface and put them in right path
Awesome work! Please kindly provide the download links for models designated as "vae_model_path" and "image_encoder_path" in the infer.yaml. As when I run the scripts, I met issues when downloading from huggingface.
Traceback (most recent call last): File "/opt/tiger/tools/sd/follow_emoji/FollowYourEmoji/infer.py", line 228, in <module> main(args, config) File "/opt/tiger/tools/sd/follow_emoji/FollowYourEmoji/infer.py", line 127, in main image_encoder = CLIPVisionModelWithProjection.from_pretrained(config.image_encoder_path).to(dtype=weight_dtype, device="cuda") File "/home/tiger/.local/lib/python3.9/site-packages/transformers/modeling_utils.py", line 3128, in from_pretrained resolved_config_file = cached_file( File "/home/tiger/.local/lib/python3.9/site-packages/transformers/utils/hub.py", line 425, in cached_file raise EnvironmentError( OSError: sd-image-variations-diffusers/image_encoder is not a local folder and is not a valid model identifier listed on 'https://huggingface.co/models'