huggingface / huggingface/diffusers

Is there any img2img KDiffusion equivalent of StableDiffusionKDiffusionPipeline?

Offen
#10,050 2 Kommentare 0 Reaktionen 0 zugewiesene Personen Auf GitHub ansehen
stale
Vorherrschende Sprache
Python
Sterne
34.5k
Forks
7.3k
Ø Merge
3 T. 3 Std.
Gemergte PRs (30 T.)
91

Beschreibung

### Model/Pipeline/Scheduler description

I'm working on result alignment between diffusers and A1111 webui.
In txt2img scene, I can achieve via `StableDiffusionKDiffusionPipeline`, refer to https://github.com/huggingface/diffusers/issues/3253.
But in img2img scene, is there any KDiffusion pipeline equivalent?

I'm also trying to implement this by merging `StableDiffusionKDiffusionPipeline` and `StableDiffusionImg2ImgPipeline` together.
Any clarification and help is appreciated.

### Open source status

- [ ] The model implementation is available.
- [ ] The model weights are available (Only relevant if addition is not a scheduler).

### Provide useful links for the implementation

_No response_

Beitragsleitfaden

Beitragsleitfaden öffnen

Rechercherichtung

Start with the referenced diffusers issue #3253, then compare the entry points named in this report: StableDiffusionKDiffusionPipeline and StableDiffusionImg2ImgPipeline. Determine whether an img2img KDiffusion equivalent already exists; done would require a clear answer or a separately scoped implementation plan.

Vom Indexierungsmodell aus dem Issue-Text verfasst.

Bewertung

Tech-Stack
python, pytorch
Bereich
machine-learning
Issue-Typ
Feature
Schwierigkeit
5/5
Geschätzter Aufwand
Über eine Woche
Aktivitätsstatus
Veraltet
Klarheit
Muss geklärt werden
Anfängerfreundlichkeit
18/100

Neue Issues direkt in Ihr Postfach

Eine kurze Übersicht über anfängerfreundliche GitHub-Issues.