[chore] Add diffusers-format example to LongCatAudioDiTPipeline#13483
[chore] Add diffusers-format example to LongCatAudioDiTPipeline#13483dg845 merged 5 commits intohuggingface:mainfrom
Conversation
…ioDiTPipeline Signed-off-by: Lancer <maruixiang6688@gmail.com>
f25c3a7 to
974c829
Compare
|
@dg845 I uploaded a Diffusers-format repository, updated usage docs. |
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
| - `output_type="pt"` returns a PyTorch tensor shaped `(batch, channels, samples)`. | ||
| - `audio_duration_s` is the most direct way to control output duration. | ||
| - `seed` makes generation reproducible (optional, defaults to None). | ||
| - Output shape is `(batch, channels, samples)` - use `.audios[0, 0]` to get a single audio sample. |
There was a problem hiding this comment.
nit: I think it might be more clear here if we clarify how the pipeline handles mono and stereo outputs.
There was a problem hiding this comment.
Added mono/stereo clarification in Tips
|
@bot /style |
|
Style bot fixed some files and pushed the changes. |
dg845
left a comment
There was a problem hiding this comment.
Thanks for the follow-up PR! Left a few small comments/suggestions :).
Co-authored-by: dg845 <58458699+dg845@users.noreply.github.com>
Fixed, PTAL |
|
@bot /style |
|
Style bot fixed some files and pushed the changes. |
dg845
left a comment
There was a problem hiding this comment.
Thanks! (BTW, you can fix the code style with make style and make quality.)
|
Merging as the CI failures are unrelated. |
What does this PR do?
Before submitting
documentation guidelines, and
here are tips on formatting docstrings.
Who can review?
Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.