TODO

Issues

Stuff to be fixed, in no particular order...

N/A

Stuff to be added, in no particular order...

Diffusers:
- Add Lyco support
- Add ControlNet
- Fix DeepFloyd IF model
- Add unCLIP model
- Add Training support
- Add long prompts
Technical debt:
- Port A1111 stuff
- Port p.all_hr_prompts
- Import core repos to reduce dependencies
Non-technical:
- Update Wiki
- Rename repo: automatic -> sdnext
- Localization
New Minor
- Prompt padding for positive/negative
- Add EN provider for VAEs
- Built-in motd-style notifications
New Major
- Profile manager (for config.json and ui-config.json)
- Multi-user support
- Add SAG, SAG
- Image phash and hdash using imagehash
- Model merge using git-rebasin
- Enable refiner-style workflow for ldm backend
- Add sgm backend
- Cache models in VRAM
- Train:
  - Use interrogator
  - Use rembg
  - Templates for SD-XL training
  - Lora train UI
Redesign
- New UI
- New inpainting canvas controls (move from backend to purely frontend)
- New image browser (move from backend to purely frontend)
- Change workflows from static/legacy to steps-based

Stuff to be investigated...

Pick & merge PRs from main repo...

Tech that can be integrated as part of the core workflow...