Moore-AnimateAnyone icon indicating copy to clipboard operation
Moore-AnimateAnyone copied to clipboard

OSError: Error no file named diffusion_pytorch_model.bin found in directory ./pretrained_weights/sd-vae-ft-mse.

Open wotise opened this issue 1 year ago • 3 comments

I ran the app.py on colab. When I clicked the [Animate] button, the error occurred. Here is the detail message: Traceback (most recent call last): File "/usr/local/lib/python3.10/dist-packages/gradio/routes.py", line 488, in run_predict output = await app.get_blocks().process_api( File "/usr/local/lib/python3.10/dist-packages/gradio/blocks.py", line 1431, in process_api result = await self.call_function( File "/usr/local/lib/python3.10/dist-packages/gradio/blocks.py", line 1103, in call_function prediction = await anyio.to_thread.run_sync( File "/usr/local/lib/python3.10/dist-packages/anyio/to_thread.py", line 33, in run_sync return await get_asynclib().run_sync_in_worker_thread( File "/usr/local/lib/python3.10/dist-packages/anyio/_backends/_asyncio.py", line 877, in run_sync_in_worker_thread return await future File "/usr/local/lib/python3.10/dist-packages/anyio/_backends/_asyncio.py", line 807, in run result = context.run(func, *args) File "/usr/local/lib/python3.10/dist-packages/gradio/utils.py", line 707, in wrapper response = f(*args, **kwargs) File "/content/Moore-AnimateAnyone-master/app.py", line 48, in animate vae = AutoencoderKL.from_pretrained( File "/usr/local/lib/python3.10/dist-packages/diffusers/models/modeling_utils.py", line 777, in from_pretrained model_file = _get_model_file( File "/usr/local/lib/python3.10/dist-packages/diffusers/utils/hub_utils.py", line 284, in _get_model_file raise EnvironmentError( OSError: Error no file named diffusion_pytorch_model.bin found in directory ./pretrained_weights/sd-vae-ft-mse.

Here is my filepath on colab. 708c9201-7625-4093-9e14-c0bbfdcb20ab Can anyone has idea to solve the problem? Thanks a lot!

wotise avatar Feb 14 '24 15:02 wotise

As my experience, u could rerun the weight loading script and the error will dispear, while i do not know the ultimate reason now.

Tsaiyue avatar Feb 16 '24 17:02 Tsaiyue

The model weights did not completely. Try to use our provided weight downloading scripts, and make sure your network can connect to huggingface.com successfully.

lixunsong avatar Feb 29 '24 09:02 lixunsong

Check if ./pretrained_weights/sd-vae-ft-mse contains 'diffusion_pytorch_model.bin' or not. And if yes, ensure it exactly matches with the name: 'diffusion_pytorch_model.bin'. I had to rename it by removing the trailing "002".

Heisenberg301116 avatar Mar 15 '24 12:03 Heisenberg301116