showlab / Tune-A-Video

[ICCV 2023] Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation
https://tuneavideo.github.io
Apache License 2.0
4.15k stars 377 forks source link

Colab Error: "Error no file named diffusion_pytorch_model.bin found in directory outputs/man-skiing" #88

Open zainkazi opened 8 months ago

zainkazi commented 8 months ago

Cell 8 gives me this error. How to resolve this?

Complete error description:

"OSError Traceback (most recent call last) in <cell line: 9>() 7 8 ----> 9 unet = UNet3DConditionModel.from_pretrained(OUTPUT_DIR, subfolder='unet', torch_dtype=torch.float16).to('cuda') 10 scheduler = DDIMScheduler.from_pretrained(MODEL_NAME, subfolder='scheduler') 11 pipe = TuneAVideoPipeline.from_pretrained(MODEL_NAME, unet=unet, scheduler=scheduler, torch_dtype=torch.float16).to("cuda")

1 frames /usr/local/lib/python3.10/dist-packages/diffusers/modeling_utils.py in _get_model_file(cls, pretrained_model_name_or_path, weights_name, subfolder, cache_dir, force_download, proxies, resume_download, local_files_only, use_auth_token, user_agent, revision) 591 model_file = os.path.join(pretrained_model_name_or_path, subfolder, weights_name) 592 else: --> 593 raise EnvironmentError( 594 f"Error no file named {weights_name} found in directory {pretrained_model_name_or_path}." 595 )

OSError: Error no file named diffusion_pytorch_model.bin found in directory outputs/man-skiing."