huggingface / huggingface/diffusers
[Modular] Krea 2 image-to-image generation
Open
- Dominant language
- Python
- Stars
- 34.5k
- Forks
- 7.3k
- Avg merge
- 3d 3h
- Merged PRs (30d)
- 91
Description
It would be great to have image-to-image in the Krea 2 modular pipeline.
That would let us use cool LoRAs, such [Krea 2 Identity Edit](https://huggingface.co/conradlocke/krea2-identity-edit), with Diffusers.
Contributor guide
Research direction
Start by reviewing the Diffusers modular pipeline support for Krea 2 and the linked Krea 2 Identity Edit LoRA. Identify the existing Krea 2 entry points, image-to-image pipeline conventions, and relevant tests before defining the integration scope. Done should include working image-to-image generation with the referenced LoRA and test coverage.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100