Skip to content
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

Jump to bottom

fix CogVideoX check_inputs and limit I2V frames to 49 #9469

Closed
wants to merge 1 commit into from
+17 −28
Closed

fix CogVideoX check_inputs and limit I2V frames to 49 #9469

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
16 changes: 7 additions & 9 deletions src/diffusers/pipelines/cogvideo/pipeline_cogvideox.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -577,19 +577,17 @@ def __call__(
if isinstance(callback_on_step_end, (PipelineCallback, MultiPipelineCallbacks)):
callback_on_step_end_tensor_inputs = callback_on_step_end.tensor_inputs

height = height or self.transformer.config.sample_size * self.vae_scale_factor_spatial
width = width or self.transformer.config.sample_size * self.vae_scale_factor_spatial
num_videos_per_prompt = 1

# 1. Check inputs. Raise error if not correct
self.check_inputs(
prompt,
height,
width,
negative_prompt,
callback_on_step_end_tensor_inputs,
prompt_embeds,
negative_prompt_embeds,
prompt=prompt,
height=height,
width=width,
negative_prompt=negative_prompt,
callback_on_step_end_tensor_inputs=callback_on_step_end_tensor_inputs,
prompt_embeds=prompt_embeds,
negative_prompt_embeds=negative_prompt_embeds,
)
self._guidance_scale = guidance_scale
self._interrupt = False
Expand Down
27 changes: 10 additions & 17 deletions src/diffusers/pipelines/cogvideo/pipeline_cogvideox_image2video.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -438,8 +438,6 @@ def check_inputs(
width,
negative_prompt,
callback_on_step_end_tensor_inputs,
video=None,
latents=None,
prompt_embeds=None,
negative_prompt_embeds=None,
):
Expand Down Expand Up @@ -494,9 +492,6 @@ def check_inputs(
f" {negative_prompt_embeds.shape}."
)

if video is not None and latents is not None:
raise ValueError("Only one of `video` or `latents` should be provided")

# Copied from diffusers.pipelines.cogvideo.pipeline_cogvideox.CogVideoXPipeline.fuse_qkv_projections
def fuse_qkv_projections(self) -> None:
r"""Enables fused QKV projections."""
Expand Down Expand Up @@ -657,28 +652,26 @@ def __call__(
`tuple`. When returning a tuple, the first element is a list with the generated images.
"""

if num_frames > 49:
if num_frames != 49:
raise ValueError(
"The number of frames must be less than 49 for now due to static positional embeddings. This will be updated in the future to remove this limitation."
"The number of frames must be 49 for now due to static learned positional embeddings. This will be updated in the future to remove this limitation."
)

if isinstance(callback_on_step_end, (PipelineCallback, MultiPipelineCallbacks)):
callback_on_step_end_tensor_inputs = callback_on_step_end.tensor_inputs

height = height or self.transformer.config.sample_size * self.vae_scale_factor_spatial
width = width or self.transformer.config.sample_size * self.vae_scale_factor_spatial
num_videos_per_prompt = 1

# 1. Check inputs. Raise error if not correct
self.check_inputs(
image,
prompt,
height,
width,
negative_prompt,
callback_on_step_end_tensor_inputs,
prompt_embeds,
negative_prompt_embeds,
image=image,
prompt=prompt,
height=height,
width=width,
negative_prompt=negative_prompt,
callback_on_step_end_tensor_inputs=callback_on_step_end_tensor_inputs,
prompt_embeds=prompt_embeds,
negative_prompt_embeds=negative_prompt_embeds,
)
self._guidance_scale = guidance_scale
self._interrupt = False
Expand Down
2 changes: 0 additions & 2 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 @@ -651,8 +651,6 @@ def __call__(
if isinstance(callback_on_step_end, (PipelineCallback, MultiPipelineCallbacks)):
callback_on_step_end_tensor_inputs = callback_on_step_end.tensor_inputs

height = height or self.transformer.config.sample_size * self.vae_scale_factor_spatial
width = width or self.transformer.config.sample_size * self.vae_scale_factor_spatial
num_videos_per_prompt = 1

# 1. Check inputs. Raise error if not correct
Expand Down
Loading