New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
what is the correct way to run demo? #27
Comments
I also met with a similar problem. I solved it through installing an assigned version of diffusers as follows:
|
Had the same problem: this fixed it! Thank you! |
benjaminbojko
added a commit
to benjaminbojko/TokenFlow
that referenced
this issue
Sep 23, 2023
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
python preprocess.py --data_path data/woman-running.mp4 --inversion_prompt "a marble sculpture of a woman running, Venus de Milossets"
the "latents" folder is created , but the video file "inverted.mp4" is not changed .
then I run "python run_tokenflow_pnp.py"
Traceback (most recent call last):
File "/home/xxx/TokenFlow/run_tokenflow_pnp.py", line 300, in
run(config)
File "/home/xxx/TokenFlow/run_tokenflow_pnp.py", line 280, in run
editor.edit_video()
File "/home/xxx/TokenFlow/run_tokenflow_pnp.py", line 258, in edit_video
edited_frames = self.sample_loop(noisy_latents, torch.arange(self.config["n_frames"]))
File "/home/xxx/TokenFlow/run_tokenflow_pnp.py", line 267, in sample_loop
x = self.batched_denoise_step(x, t, indices)
File "/home/xxx/anaconda3/envs/tokenflow/lib/python3.9/site-packages/torch/amp/autocast_mode.py", line 14, in decorate_autocast
return func(*args, **kwargs)
File "/home/xxx/TokenFlow/run_tokenflow_pnp.py", line 227, in batched_denoise_step
self.denoise_step(x[pivotal_idx], t, indices[pivotal_idx])
File "/home/xxx/anaconda3/envs/tokenflow/lib/python3.9/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "/home/xxx/TokenFlow/run_tokenflow_pnp.py", line 210, in denoise_step
noise_pred = self.unet(latent_model_input, t, encoder_hidden_states=text_embed_input)['sample']
File "/home/xxx/anaconda3/envs/tokenflow/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "/home/xxx/anaconda3/envs/tokenflow/lib/python3.9/site-packages/diffusers/models/unet_2d_condition.py", line 1018, in forward
sample = upsample_block(
File "/home/xxx/anaconda3/envs/tokenflow/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "/home/xxx/anaconda3/envs/tokenflow/lib/python3.9/site-packages/diffusers/models/unet_2d_blocks.py", line 2227, in forward
hidden_states = resnet(hidden_states, temb, scale=lora_scale)
File "/home/xxx/anaconda3/envs/tokenflow/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
TypeError: forward() got an unexpected keyword argument 'scale'
could you help?
The text was updated successfully, but these errors were encountered: