MooreThreads / Moore-AnimateAnyone

Character Animation (AnimateAnyone, Face Reenactment)
Apache License 2.0
3.17k stars 248 forks source link

how can I inference low memory gpu #95

Open leejaewoo opened 8 months ago

leejaewoo commented 8 months ago

I am currently trying to make inferences using this model using a small vram memory of 8GB. When following the example in the readme file, a memory shortage occurs. If you perform inference by reducing the width and height, the animation will not work properly. To solve this problem, is there any other way than upgrading the current device's GPU?

ButoneDream commented 8 months ago

huggingface_hub.utils._validators.HFValidationError: Repo id must be in the form 'repo_name' or 'namespace/repo_name': './pretrained_weights/sd-vae-ft-mse'. Use repo_type argument if needed. 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 ./pretrained_weights/sd-vae-ft-mse is not the path to a directory containing a config.json file. could you have similar exception ?