fal

/

AuraFlow-v0.3

like 90

Using the example, on the model page:

 from diffusers import AuraFlowPipeline
 import torch 

 pipeline = AuraFlowPipeline.from_pretrained(
     "fal/AuraFlow-v0.3",
     torch_dtype=torch.float16,
     variant="fp16",
 ).to("cuda")

downloaded the normal safetensors file and not the fp16.safetensors file. This also happened when I updated to the to the latest diffusers on git as the model page suggests.

After downloading the non fp16 transformer files, running the pipeline generated this warning:

 A mixture of fp16 and non-fp16 filenames will be loaded.
 Loaded fp16 filenames:
 [vae/diffusion_pytorch_model.fp16.safetensors, text_encoder/model.fp16.safetensors]
 Loaded non-fp16 filenames:
 [transformer/diffusion_pytorch_model-00001-of-00003.safetensors, transformer/diffusion_pytorch_model-00002-of-00003.safetensors, transformer/diffusion_pytorch_model-00003-of-00003.safetensors
 If this behavior is not expected, please check your folder structure.

Any ideas what the problem might be or how to fix this? Thanks.