Skip to content

[Cog] some minor fixes and nits #9466

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.

Sign up for GitHub

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

Merged
merged 8 commits into from
Sep 23, 2024
Merged

[Cog] some minor fixes and nits #9466

Changes from 4 commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
f4ce633
fix positional arguments in check_inputs().
sayakpaul Sep 19, 2024
588d759
add video and latetns to check_inputs().
sayakpaul Sep 19, 2024
37c8922
prep latents_in_channels.
sayakpaul Sep 19, 2024
4b0dc80
quality
sayakpaul Sep 19, 2024
24b83a6
multiple fixes.
sayakpaul Sep 19, 2024
514ed23
fix
sayakpaul Sep 19, 2024
e237924
Merge branch 'main' into correct-args-cog-v2v
sayakpaul Sep 21, 2024
271c110
Merge branch 'main' into correct-args-cog-v2v
sayakpaul Sep 21, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
25 changes: 16 additions & 9 deletions src/diffusers/pipelines/cogvideo/pipeline_cogvideox_video2video.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -206,6 +206,11 @@ def __init__(
self.register_modules(
tokenizer=tokenizer, text_encoder=text_encoder, vae=vae, transformer=transformer, scheduler=scheduler
)
self.latents_in_channels = (
self.transformer.config.in_channels
if hasattr(self, "transformer") and self.transformer is not None
else 16
)
self.vae_scale_factor_spatial = (
2 ** (len(self.vae.config.block_out_channels) - 1) if hasattr(self, "vae") and self.vae is not None else 8
)
Expand Down Expand Up @@ -657,14 +662,16 @@ def __call__(

# 1. Check inputs. Raise error if not correct
self.check_inputs(
prompt,
height,
width,
strength,
negative_prompt,
callback_on_step_end_tensor_inputs,
prompt_embeds,
negative_prompt_embeds,
prompt=prompt,
height=height,
width=width,
strength=strength,
negative_prompt=negative_prompt,
callback_on_step_end_tensor_inputs=callback_on_step_end_tensor_inputs,
video=video,
latents=latents,
prompt_embeds=prompt_embeds,
negative_prompt_embeds=negative_prompt_embeds,
)
self._guidance_scale = guidance_scale
self._interrupt = False
Expand Down Expand Up @@ -709,7 +716,7 @@ def __call__(
video = self.video_processor.preprocess_video(video, height=height, width=width)
video = video.to(device=device, dtype=prompt_embeds.dtype)

latent_channels = self.transformer.config.in_channels
latent_channels = self.latents_in_channels
latents = self.prepare_latents(
video,
batch_size * num_videos_per_prompt,
Expand Down
Loading