11 Commits

Author SHA1 Message Date
DenOfEquity
f23bc80d2f SD3+ (#2688)
Co-authored-by: graemeniedermayer graemeniedermayer@users.noreply.github.com
2025-02-27 17:54:44 +00:00
DenOfEquity
2051c4100b Apply emphasis mode changes immediately (#2423)
Previously emphasis mode changes applied only on model load.
Also added handling for mode 'None' (literal interpretation), which previously gave results identical to mode 'Ignore'.
2024-12-08 19:25:39 +00:00
layerdiffusion
a05a06b337 make results more consistent to A1111 2024-08-08 01:53:03 -07:00
layerdiffusion
e396307e9d hard code clip token device
#950
2024-08-08 01:36:01 -07:00
layerdiffusion
64baac36b6 improve clip cast 2024-08-06 21:09:40 -07:00
layerdiffusion
0863765173 rework sd1.5 and sdxl from scratch 2024-08-05 03:08:17 -07:00
layerdiffusion
e28e11fa97 allow clip to skip TI 2024-08-04 19:28:53 -07:00
layerdiffusion
0d81ccb387 print to make sure that everything works well 2024-08-04 19:03:12 -07:00
layerdiffusion
9679232d29 fix TI embedding info text
original webui is also broken but forge is fixed now
2024-08-04 18:49:35 -07:00
layerdiffusion
a72154405e Text Processing Engine is Finished
100% reproduce all previous results, including TI embeddings, LoRAs in CLIP, emphasize settings, BREAK, timestep swap scheduling, AB mixture, advanced uncond, etc
Backend is 85% finished
2024-08-04 18:42:51 -07:00
layerdiffusion
2791203d5b move file 2024-08-04 13:49:58 -07:00