TODO

If you can solve any of these, feel free to make a pull request.

Documentation

• The Install Video Guide (especially now that it should be even easier)
• Update what features exist on the Features page.

Feature Videos

Short, under 5 mins videos demonstrating each feature.

Note to self: Easiest/most flexible approach is to record as small snippets, voiceover later. Snippets can be reused for full install/demo video.

Another note to self: Youtube's free audio/sound effect library exists. I don't know how you forgot about its existence when making the old demo video.

• Inpainting
  • Explaining the superior mask blur/full resolution system
  • Sketching + inpainting
  • Rerolling features
  • Removing boundaries (i.e. from img2img, outpainting or txt2img)
  • Photoshopping in characters
• Txt2Img
  • base size/max size system for highres fix
  • AUTO's highres fix
  • Removing background from txt2img to use as stamps
• Img2Img
  • Sketching
  • Creating variants of a good image
  • Selecting a polygon for img2img followed by inpainting to clean up
• Outpainting
  • Sketching + outpainting
  • Txt2Img/Img2Img + outpainting
  • Outpainting MK2
• Upscaling
  • SD upscale
  • Conventional upscale
• Others
  • UI Docking
  • Settings Profiles

Maintenance

• Fix bugs due to upstream internal API changes.
• Improve & document the API.

Upstream

• Fix new samplers that need configuration.
• Expose sampler parameters with explanation.
• Expose all config options in the GUI.

Features

• Outpainting, of which possibilities are:
  • Dedicated outpainting tab
  • Using Sketch + Inpaint as Outpaint technique
  • Use outpainting Mk 2.
• Save a subset of config options as swappable profiles.
• Make it more convenient to send images to/from webUI.
• Investigate using the sketched corrections itself as the mask instead of needing a separate inpaint layer.

Bugs

Unrelated

• Hmmm tag auto-complete... How would I do that in PyQt? https://github.com/DominikDoom/a1111-sd-webui-tagcomplete