Custom Wan diffusion Lora runs without error but doesn't apply effect and gives warning: No LoRA keys associated to WanTransformer3DModel found with the prefix='transformer'.

[st-projects-00]

Describe the bug

I run the diffusers pipe using the standard process with a custom diffusers trained lora:

pipe = WanPipeline.from_pretrained(model_id, vae=vae, torch_dtype=torch.bfloat16)
pipe.scheduler = scheduler
pipe.load_lora_weights("lora/customdiffusers_lora.safetensors")
etc...

it runs without error but the effect was not applied, and I see the following warning:
No LoRA keys associated to WanTransformer3DModel found with the prefix='transformer'. This is safe to ignore if LoRA state dict didn't originally have any WanTransformer3DModel related params. You can also try specifying prefix=None to resolve the warning. Otherwise, open an issue if you think it's unexpected: https://github.com/huggingface/diffusers/issues/new

Is there any config file I need to change for this to work? Thanks

Reproduction

N/A as a custom Lora

Logs

System Info

0.33, linux, python 3.10

Who can help?

No response

[asomoza]

is that a lora trained by you? does it work in other libraries?

If yes, you will need to upload the lora to the huggingface hub, without the lora we can't do much.

[st-projects-00]

please close this. Thx

[Mooncattt]

Can you please tell me how to fix this problem? I met the same thing. my lora didnt work