Skip to content

[bug] Fix float/int guidance scale not working in StableVideoDiffusionPipeline #7143

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 4 commits into from
Mar 6, 2024
Merged

[bug] Fix float/int guidance scale not working in StableVideoDiffusionPipeline #7143

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
f26edf5
[bug] Fix float/int guidance scale not working in `StableVideoDiffusi…
JinayJain Feb 29, 2024
74b8000
Merge branch 'main' into fix-svd-guidance-scale
sayakpaul Mar 4, 2024
8409bc0
Add test to disable CFG on SVD
JinayJain Mar 5, 2024
0a8d4a8
Merge branch 'main' into fix-svd-guidance-scale
JinayJain Mar 6, 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
2 changes: 1 addition & 1 deletion src/diffusers/pipelines/stable_video_diffusion/pipeline_stable_video_diffusion.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -322,7 +322,7 @@ def guidance_scale(self):
@property
def do_classifier_free_guidance(self):
if isinstance(self.guidance_scale, (int, float)):
return self.guidance_scale
return self.guidance_scale > 1
return self.guidance_scale.max() > 1

@property
Expand Down
16 changes: 16 additions & 0 deletions tests/pipelines/stable_video_diffusion/test_stable_video_diffusion.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -496,6 +496,22 @@ def test_xformers_attention_forwardGenerator_pass(self):
max_diff = np.abs(to_np(output_with_offload) - to_np(output_without_offload)).max()
self.assertLess(max_diff, expected_max_diff, "XFormers attention should not affect the inference results")

def test_disable_cfg(self):
components = self.get_dummy_components()
pipe = self.pipeline_class(**components)
for component in pipe.components.values():
if hasattr(component, "set_default_attn_processor"):
component.set_default_attn_processor()

pipe.to(torch_device)
pipe.set_progress_bar_config(disable=None)

generator_device = "cpu"
inputs = self.get_dummy_inputs(generator_device)
inputs["max_guidance_scale"] = 1.0
output = pipe(**inputs).frames
self.assertEqual(len(output.shape), 5)


@slow
@require_torch_gpu
Expand Down