aboutsummaryrefslogtreecommitdiffstats
path: root/extensions-builtin/Lora
Commit message (Expand)AuthorAgeFilesLines
* fix: ignore calc_scale() for COFT which has very small alphav0xie2023-11-151-11/+5
* refactor: remove unused functionv0xie2023-11-041-47/+0
* refactor: use same updown for both kohya OFT and LyCORIS diag-oftv0xie2023-11-041-17/+74
* refactor: move factorization to lyco_helpers, separate calc_updown for kohya ...v0xie2023-11-042-101/+77
* skip multihead attn for nowv0xie2023-11-041-17/+37
* no idea what i'm doing, trying to support both type of OFT, kblueleaf diag_of...v0xie2023-11-021-47/+145
* detect diag_oft typev0xie2023-11-021-0/+7
* test implementation based on kohaku diag-oft implementationv0xie2023-11-021-21/+38
* style: conform stylev0xie2023-10-221-1/+1
* fix: multiplier applied twice in finalize_updownv0xie2023-10-221-1/+22
* refactor: remove used OFT functionsv0xie2023-10-221-72/+10
* fix: use merge_weight to cache valuev0xie2023-10-221-17/+40
* style: cleanup oftv0xie2023-10-211-75/+7
* fix: support multiplier, no forward pass hookv0xie2023-10-211-10/+33
* fix: return orig weights during updown, merge weights before forwardv0xie2023-10-211-21/+69
* refactor: use forward hook instead of custom forwardv0xie2023-10-211-9/+24
* style: fix ambiguous variable namev0xie2023-10-191-2/+2
* style: formattingv0xie2023-10-192-37/+2
* refactor: fix constraint, re-use get_weightv0xie2023-10-191-24/+16
* faster by calculating R in updown and using cached R in forwardv0xie2023-10-181-7/+8
* faster by using cached R in forwardv0xie2023-10-181-3/+14
* inference working but SLOWv0xie2023-10-182-40/+75
* wip incorrect OFT implementationv0xie2023-10-182-0/+87
* Merge pull request #13568 from AUTOMATIC1111/lora_emb_bundleAUTOMATIC11112023-10-143-0/+75
|\
| * remove duplicated codeAUTOMATIC11112023-10-141-29/+2
| * Fix lintKohaku-Blueleaf2023-10-101-1/+1
| * Add warning when meet emb name conflictingKohaku-Blueleaf2023-10-102-32/+81
| * Remove dev debug printKohaku-Blueleaf2023-10-101-1/+0
| * Support string_to_param nested dictKohaku-Blueleaf2023-10-101-1/+6
| * add lora bundle systemKohaku-Blueleaf2023-10-092-0/+49
* | support inference with LyCORIS GLora networksv0xie2023-10-122-0/+35
|/
* fix: lora-bias-backup don't reset cachedongwenpu2023-09-101-0/+1
* feat: display file metadata ss_output_namebluelovers2023-08-281-0/+1
* RAM optimization round 2AUTOMATIC11112023-08-161-1/+4
* lintAUTOMATIC11112023-08-151-2/+1
* Merge pull request #12584 from AUTOMATIC1111/full-module-with-biasAUTOMATIC11112023-08-151-1/+6
|\
| * full module with ex_biasKohaku-Blueleaf2023-08-151-1/+6
* | store patches for Lora in a specialized moduleAUTOMATIC11112023-08-153-61/+54
|/
* remove "if bias exist" checkKohaku-Blueleaf2023-08-141-1/+1
* Merge branch 'dev' into extra-norm-moduleKohaku-Blueleaf2023-08-144-33/+55
|\
| * Merge pull request #12510 from catboxanon/feat/extnet/hashesAUTOMATIC11112023-08-131-1/+2
| |\
| | * Support search and display of hashes for all extra network itemscatboxanon2023-08-131-1/+2
| * | linterAUTOMATIC11112023-08-131-1/+1
| * | Lora: output warnings in UI rather than fail for unfitting loras; switch to l...AUTOMATIC11112023-08-133-29/+50
| |/
* / Fix MHA updown err and support ex-bias for no-bias layerKohaku-Blueleaf2023-08-141-8/+29
|/
* remove debug printKohaku-Blueleaf2023-08-121-1/+0
* return None if no ex_biasKohaku-Blueleaf2023-08-122-4/+4
* Add extra norm module into built-in lora extKohaku-Blueleaf2023-08-124-11/+105
* Fix to make LoRA old method setting workcatboxanon2023-08-111-1/+1
* Lora cache in memoryAUTOMATIC11112023-08-092-3/+22
generated by cgit v1.2.3 (git 2.25.1) at 2025-04-29 20:11:32 +0000