ryan/ComfyUI
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Adjust used dtypes for hunyuan video VAE and diffusion model.

Browse Source
This commit is contained in:
comfyanonymous
2024-12-16 23:31:10 -05:00
parent 0b25f47bd9
commit 39b1fc4ccc
2 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
comfy/supported_models.py
View File

@@ -753,7 +753,7 @@ class HunyuanVideo(supported_models_base.BASE):
memory_usage_factor = 2.0 #TODO
supported_inference_dtypes = [torch.bfloat16, torch.float16, torch.float32]
supported_inference_dtypes = [torch.bfloat16, torch.float32]
vae_key_prefix = ["vae."]
text_encoder_key_prefix = ["text_encoders."]