this post was submitted on 13 Sep 2024
6 points (87.5% liked)

Stable Diffusion

4301 readers
15 users here now

Discuss matters related to our favourite AI Art generation technology

Also see

Other communities

founded 1 year ago
MODERATORS
 

Highlights for 2024-09-13

Major refactor of FLUX.1 support:

  • Full ControlNet support, better LoRA support, full prompt attention implementation
  • Faster execution, more flexible loading, additional quantization options, and more...
  • Added image-to-image, inpaint, outpaint, hires modes
  • Added workflow where FLUX can be used as refiner for other models
  • Since both Optimum-Quanto and BitsAndBytes libraries are limited in their platform support matrix,
    try enabling NNCF for quantization/compression on-the-fly!

Few image related goodies...

  • Context-aware resize that allows for img2img/inpaint even at massively different aspect ratios without distortions!
  • LUT Color grading apply professional color grading to your images using industry-standard .cube LUTs!
  • Auto HDR image create for SD and SDXL with both 16ch true-HDR and 8-ch HDR-effect images ;)

And few video related goodies...

  • CogVideoX 2b and 5b variants
    with support for text-to-video and video-to-video!
  • AnimateDiff prompt travel and long context windows!
    create video which travels between different prompts and at long video lengths!

Plus tons of other items and fixes - see changelog for details!
Examples:

  • Built-in prompt-enhancer, TAESD optimizations, new DC-Solver scheduler, global XYZ grid management, etc.
  • Updates to ZLUDA, IPEX, OpenVINO...
top 1 comments
sorted by: hot top controversial new old
[–] [email protected] 1 points 1 month ago

New UI is unnecessary complicated