Commit Graph

18 Commits

Author SHA1 Message Date
Bryce
7af1ab66ca fix: add workaround for bug in k_diffusion on mps
As documented here: https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/4558#issuecomment-1310387114

- make image logs more consistent
- note which step the progress images belong to in the filename
2022-11-12 20:19:23 -08:00
Bryce
021a0c540d feature: inpainting model support; improved model manager 2022-10-25 20:07:35 -07:00
Bryce
e8bb3cf5fd refactor: consolidate masking logic 2022-10-13 07:04:37 -07:00
Bryce
72026c8c90 refactor: merge img2img and txt2img pipelines 2022-10-13 07:04:37 -07:00
Bryce
a105dadbc4 refactor: combine identical schedules 2022-10-13 07:04:37 -07:00
Bryce
8d4b5cb9e1 refactor: standardize samplers more 2022-10-13 07:04:37 -07:00
Bryce
b0123a8f43 refactor: remove unused parameters 2022-10-11 01:06:24 -05:00
Bryce
df3c752eb8 refactor: consolidate logging utils 2022-10-10 22:32:39 -05:00
Bryce
9ba302a5f4 refactor: begin to standardize samplers 2022-10-07 00:02:26 -05:00
Bryce
95a8fa31a9 fix: inpainting producing blurry images
while the previous version did produce much better blending it also makes images that lack detail for some reason.

tests: Added more tests to help catch this sort of thing earlies

fix: found that median blur is really slow, so I made sure we only do it on downsampled masks.  Was taking like 3 minutes to run on the large pearl girl picture on M1

- docs: update examples
2022-09-27 17:19:25 -07:00
Bryce
6cae290038 fix: inpainting now matches photo at high generation strength
- 🎉 fix: inpainted areas correlate with surrounding image, even at 100% generation strength.  Previously if the generation strength was high enough the generated image
would be uncorrelated to the rest of the surrounding image.  It created terrible looking images.
 - fix: mask boundaries are more accurate
2022-09-25 22:50:16 -07:00
Bryce
d832f15297 fix: masking now works properly at strengths 0 and 1 2022-09-24 23:31:03 -07:00
Bryce
69af07ab67 style: fix lint issues 2022-09-24 00:31:08 -07:00
Jay Drennan
df28bf8805 refactor: implements changes to comply with pylama 2022-09-22 12:52:37 -06:00
Bryce
a46424c673 feature: img2img now supported with PLMS (instead of just DDIM)
Kinda hacky copy/pasting from ddim.  Need to cleanup
2022-09-20 08:42:00 -07:00
Bryce
6307a0daf5 refactor: cleanup ddim 2022-09-17 12:24:27 -07:00
Bryce
bb665b9eb6 fix: make k-diffusion samplers deterministic
- add test for hashes on mps.  images look same on CUDA but are slightly different.
2022-09-14 09:37:45 -07:00
Bryce
b4a3b8c2b3 feature: k-diffusion samplers
- improved image logging functionality. can just stick log_latent wherever you want
- improved some variable naming
- moved all the samplers together
- vendored k-diffusion library
2022-09-14 00:40:25 -07:00