运行报错

by loong - opened Jul 5

Jul 5

•

pipe = HunyuanDiTPipeline.from_pretrained("/ai/dit_dis", torch_dtype=torch.float16)
pipe.to("cuda:1")

alueError: Cannot load <class 'diffusers.models.transformers.hunyuan_transformer_2d.HunyuanDiT2DModel'> from /ai/dit_dis/transformer because the following keys are missing:
time_extra_emb.style_embedder.weight.
Please make sure to pass low_cpu_mem_usage=False and device_map=None if you want to randomly initialize those weights or else make sure your checkpoint file is correct.

loong

Jul 5

ValueError: Cannot load <class 'diffusers.models.transformers.hunyuan_transformer_2d.HunyuanDiT2DModel'> from /ai/dit_dis/transformer because the following keys are missing:
time_extra_emb.style_embedder.weight.
Please make sure to pass low_cpu_mem_usage=False and device_map=None if you want to randomly initialize those weights or else make sure your checkpoint file is correct.

Ccyrusss

Jul 15

Solved by "pip install git+https://github.com/huggingface/diffusers.git"

Airfer

Jul 15

Windows ComfyUI，how to use？

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment