Commit Graph

6602 Commits

Author SHA1 Message Date
v0xie
f6c8201e56 refactor: move factorization to lyco_helpers, separate calc_updown for kohya and kb 2023-11-03 19:35:15 -07:00
v0xie
fe1967a4c4 skip multihead attn for now 2023-11-03 17:52:55 -07:00
AUTOMATIC1111
452ab8fe72
Merge pull request #13718 from avantcontra/bugfix_gfpgan_custom_path
fix bug when using --gfpgan-models-path
2023-11-03 20:19:58 +03:00
AUTOMATIC1111
399baa54c2
Merge pull request #13733 from dben/patch-1
Update prompts_from_file script to allow concatenating entries with the general prompt.
2023-11-03 20:19:04 +03:00
AUTOMATIC1111
21d561885e
Merge pull request #13762 from wkpark/nextjob
call state.jobnext() before postproces*()
2023-11-03 20:16:58 +03:00
AUTOMATIC1111
73c74baa6a
Merge pull request #13797 from Meerkov/master
Fix #13796
2023-11-03 20:11:54 +03:00
AUTOMATIC1111
1f373a2baa
Merge pull request #13829 from AUTOMATIC1111/paren-fix
Fix parenthesis auto selection
2023-11-03 19:59:01 +03:00
AUTOMATIC1111
4afaaf8a02 add changelog entry 2023-11-03 19:50:14 +03:00
AUTOMATIC1111
bda2ecdbf5 Merge pull request #13839 from AUTOMATIC1111/httpx==0.24.1
requirements_versions httpx==0.24.1
2023-11-03 19:46:07 +03:00
AUTOMATIC1111
4c423f6d37
Merge pull request #13839 from AUTOMATIC1111/httpx==0.24.1
requirements_versions httpx==0.24.1
2023-11-03 19:44:57 +03:00
w-e-w
cc80a09d82 Update requirements_versions.txt 2023-11-04 00:50:30 +09:00
missionfloyd
8052a4971e Fix parenthesis auto selection
Fixes #13813
2023-11-03 00:59:19 -06:00
Emily Zeng
759515316e added accordion settings options 2023-11-02 21:54:48 -04:00
v0xie
d727ddfccd no idea what i'm doing, trying to support both type of OFT, kblueleaf diag_oft has MultiheadAttn which kohya's doesn't?, attempt create new module based off network_lora.py, errors about tensor dim mismatch 2023-11-02 00:13:11 -07:00
v0xie
65ccd6305f detect diag_oft type 2023-11-02 00:11:32 -07:00
v0xie
a2fad6ee05 test implementation based on kohaku diag-oft implementation 2023-11-01 22:34:27 -07:00
Meerkov
fbc5c531b9 Fix #13796
Fix comment error that makes understanding scheduling more confusing.
2023-10-29 15:37:08 -07:00
KohakuBlueleaf
ddc2a3499b Add MPS manual cast 2023-10-28 16:52:35 +08:00
Kohaku-Blueleaf
d4d3134f6d ManualCast for 10/16 series gpu 2023-10-28 15:24:26 +08:00
Won-Kyu Park
5121846d34
call state.jobnext() before postproces*() 2023-10-25 21:57:41 +09:00
Kohaku-Blueleaf
0beb131c7f change torch version 2023-10-25 20:07:37 +08:00
Kohaku-Blueleaf
dda067f64d ignore mps for fp8 2023-10-25 19:53:22 +08:00
Kohaku-Blueleaf
bf5067f50c Fix alphas cumprod 2023-10-25 12:54:28 +08:00
Kohaku-Blueleaf
4830b25136 Fix alphas_cumprod dtype 2023-10-25 11:53:37 +08:00
Kohaku-Blueleaf
1df6c8bfec fp8 for TE 2023-10-25 11:36:43 +08:00
Kohaku-Blueleaf
9c1eba2af3 Fix lint 2023-10-24 02:11:27 +08:00
Kohaku-Blueleaf
eaa9f5162f Add CPU fp8 support
Since norm layer need fp32, I only convert the linear operation layer(conv2d/linear)

And TE have some pytorch function not support bf16 amp in CPU. I add a condition to indicate if the autocast is for unet.
2023-10-24 01:49:05 +08:00
David Benson
dfc4c27b24
linting issue 2023-10-23 08:26:40 -04:00
David Benson
88b2ef3b04
Update prompts_from_file script to allow concatenating entries with the general prompt. 2023-10-23 08:16:26 -04:00
v0xie
6523edb8a4 style: conform style 2023-10-22 09:31:15 -07:00
v0xie
3b8515d2c9 fix: multiplier applied twice in finalize_updown 2023-10-22 09:27:48 -07:00
v0xie
4a50c9638c refactor: remove used OFT functions 2023-10-22 08:54:24 -07:00
v0xie
de8ee92ed8 fix: use merge_weight to cache value 2023-10-21 17:37:17 -07:00
v0xie
76f5abdbdb style: cleanup oft 2023-10-21 16:07:45 -07:00
v0xie
fce86ab7d7 fix: support multiplier, no forward pass hook 2023-10-21 16:03:54 -07:00
v0xie
7683547728 fix: return orig weights during updown, merge weights before forward 2023-10-21 14:42:24 -07:00
v0xie
2d8c894b27 refactor: use forward hook instead of custom forward 2023-10-21 13:43:31 -07:00
avantcontra
236dd55dbe fix Blank line contains whitespace 2023-10-22 04:32:13 +08:00
avantcontra
443ca983ad fix bug when using --gfpgan-models-path 2023-10-22 03:21:23 +08:00
AUTOMATIC1111
464fbcd921 fix the situation with emphasis editing (aaaa:1.1) bbbb (cccc:1.1) 2023-10-21 09:09:32 +03:00
AUTOMATIC1111
384fab9627 rework some of changes for emphasis editing keys, force conversion of old-style emphasis 2023-10-21 08:45:51 +03:00
v0xie
0550659ce6 style: fix ambiguous variable name 2023-10-19 13:13:02 -07:00
v0xie
d10c4db57e style: formatting 2023-10-19 12:52:14 -07:00
v0xie
321680ccd0 refactor: fix constraint, re-use get_weight 2023-10-19 12:41:17 -07:00
Kohaku-Blueleaf
5f9ddfa46f Add sdxl only arg 2023-10-19 23:57:22 +08:00
Kohaku-Blueleaf
7c128bbdac Add fp8 for sd unet 2023-10-19 13:56:17 +08:00
v0xie
eb01d7f0e0 faster by calculating R in updown and using cached R in forward 2023-10-18 04:56:53 -07:00
v0xie
853e21d98e faster by using cached R in forward 2023-10-18 04:27:44 -07:00
v0xie
1c6efdbba7 inference working but SLOW 2023-10-18 04:16:01 -07:00
v0xie
ec718f76b5 wip incorrect OFT implementation 2023-10-17 23:35:50 -07:00