Fix bug in panorama pipeline when using dpmsolver scheduler #3499
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Related issue: #3494
In dpmsolver scheduler,
self.model_outputs
is used to save diffusion model output in previous and current timestep, and calculateprev_sample
.diffusers/src/diffusers/schedulers/scheduling_dpmsolver_multistep.py
Lines 634 to 659 in 49ad61c
However, since we crop panorama image into several blocks and use
scheduler.step
in loop,self.model_outputs
became outputs in previous and current blocks.As a result, when using dpmsolver scheduler in PanoramaPipeline, we should collect rematch
self.model_outputs
in each block to right order to generate normal image.test code
Before
After