VictorMylle/Kohya-ss-sd-scripts
1
0
Fork 1
mirror of https://github.com/kohya-ss/sd-scripts.git synced 2026-04-09 06:45:09 +00:00
Code Issues Packages Projects Releases Wiki Activity
1,746 Commits 25 Branches 38 Tags
1286e00bb0fc34c296f24b7057777f1c37cf8e11
Commit Graph

1746 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Kohya S.
1e30aa83b4 Merge pull request #1541 from sdbds/flux_shift 
Add Flux_Shift for solving the problem of multi-resolution training blurry
 2024-09-01 19:00:16 +09:00
Kohya S
92e7600cc2 Move freeze_blocks to sd3_train because it's only for sd3 2024-09-01 18:57:07 +09:00
青龍聖者@bdsqlsz
ef510b3cb9 Sd3 freeze x_block (#1417) 
* Update sd3_train.py

* add freeze block lr

* Update train_util.py

* update
 2024-09-01 18:41:01 +09:00
Kohya S.
928e0fc096 Merge pull request #1529 from Akegarasu/sd3 
fix: text_encoder_conds referenced before assignment
 2024-09-01 18:29:27 +09:00
dependabot[bot]
1bcf8d600b Bump crate-ci/typos from 1.19.0 to 1.24.3 
Bumps [crate-ci/typos](https://github.com/crate-ci/typos) from 1.19.0 to 1.24.3.
- [Release notes](https://github.com/crate-ci/typos/releases)
- [Changelog](https://github.com/crate-ci/typos/blob/master/CHANGELOG.md)
- [Commits](https://github.com/crate-ci/typos/compare/v1.19.0...v1.24.3)

---
updated-dependencies:
- dependency-name: crate-ci/typos
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>
 2024-09-01 01:33:04 +00:00
Kohya S.
f8f5b16958 Merge pull request #1540 from kohya-ss/dependabot/pip/opencv-python-4.8.1.78 
Bump opencv-python from 4.7.0.68 to 4.8.1.78
 2024-08-31 21:37:07 +09:00
Kohya S.
826ab5ce2e Merge pull request #1532 from nandometzger/main 
Update train_util.py, bug fix
 2024-08-31 21:36:33 +09:00
sdbds
25c9040f4f Update flux_train_utils.py 2024-08-31 19:53:59 +08:00
dependabot[bot]
3a6154b7b0 Bump opencv-python from 4.7.0.68 to 4.8.1.78 
Bumps [opencv-python](https://github.com/opencv/opencv-python) from 4.7.0.68 to 4.8.1.78.
- [Release notes](https://github.com/opencv/opencv-python/releases)
- [Commits](https://github.com/opencv/opencv-python/commits)

---
updated-dependencies:
- dependency-name: opencv-python
  dependency-type: direct:production
...

Signed-off-by: dependabot[bot] <support@github.com>
 2024-08-31 06:21:16 +00:00
Nando Metzger
2a3aefb4e4 Update train_util.py, bug fix 2024-08-30 08:15:05 +02:00
Akegarasu
35882f8d5b fix 2024-08-29 23:03:43 +08:00
Akegarasu
34f2315047 fix: text_encoder_conds referenced before assignment 2024-08-29 22:33:37 +08:00
Kohya S
8fdfd8c857 Update safetensors to version 0.4.4 in requirements.txt #1524 2024-08-29 22:26:29 +09:00
Kohya S
8ecf0fc4bf Refactor code to ensure args.guidance_scale is always a float #1525 2024-08-29 22:10:57 +09:00
Kohya S.
930d709e3d Merge pull request #1525 from Akegarasu/sd3 
make guidance_scale keep float in args
 2024-08-29 22:08:57 +09:00
Kohya S.
daa6ad5165 Update README.md 2024-08-29 21:25:30 +09:00
Kohya S
a0cfb0894c Cleaned up README 2024-08-29 21:20:33 +09:00
Akegarasu
6c0e8a5a17 make guidance_scale keep float in args 2024-08-29 14:50:29 +08:00
Kohya S
a61cf73a5c update readme 2024-08-27 21:44:10 +09:00
Kohya S
3be712e3e0 feat: Update direct loading fp8 ckpt for LoRA training 2024-08-27 21:40:02 +09:00
Kohya S
0087a46e14 FLUX.1 LoRA supports CLIP-L 2024-08-27 19:59:40 +09:00
Kohya S
72287d39c7 feat: Add shift option to --timestep_sampling in FLUX.1 fine-tuning and LoRA training 2024-08-25 16:01:24 +09:00
Kohya S
ea9242653c Merge branch 'dev' into sd3 2024-08-24 21:24:44 +09:00
Kohya S
d5c076cf90 update readme 2024-08-24 21:21:39 +09:00
Kohya S.
4ca29edbff Merge pull request #1505 from liesened/patch-2 
Add v-pred support for SDXL train
 2024-08-24 21:16:53 +09:00
Kohya S
5639c2adc0 fix typo 2024-08-24 16:37:49 +09:00
Kohya S
cf689e7aa6 feat: Add option to split projection layers and apply LoRA 2024-08-24 16:35:43 +09:00
Kohya S
2e89cd2cc6 Fix issue with attention mask not being applied in single blocks 2024-08-24 12:39:54 +09:00
liesen
1e8108fec9 Handle args.v_parameterization properly for MinSNR and changed prediction target 2024-08-24 01:38:17 +03:00
Kohya S
99744af53a Merge branch 'dev' into sd3 2024-08-22 21:34:24 +09:00
Kohya S
afb971f9c3 fix SD1.5 LoRA extraction #1490 2024-08-22 21:33:15 +09:00
Kohya S
bf9f798985 chore: fix typos, remove debug print 2024-08-22 19:59:38 +09:00
Kohya S
b0a980844a added a script to extract LoRA 2024-08-22 19:57:29 +09:00
Kohya S
2d8fa3387a Fix to remove zero pad for t5xxl output 2024-08-22 19:56:27 +09:00
Kohya S
a4d27a232b Fix --debug_dataset to work. 2024-08-22 19:55:31 +09:00
kohya-ss
98c91a7625 Fix bug in FLUX multi GPU training 2024-08-22 12:37:41 +09:00
Kohya S
e1cd19c0c0 add stochastic rounding, fix single block 2024-08-21 21:04:10 +09:00
Kohya S
2b07a92c8d Fix error in applying mask in Attention and add LoRA converter script 2024-08-21 12:30:23 +09:00
Kohya S
e17c42cb0d Add BFL/Diffusers LoRA converter #1467 #1458 #1483 2024-08-21 12:28:45 +09:00
Kohya S
7e459c00b2 Update T5 attention mask handling in FLUX 2024-08-21 08:02:33 +09:00
Kohya S
6ab48b09d8 feat: Support multi-resolution training with caching latents to disk 2024-08-20 21:39:43 +09:00
Kohya S.
388b3b4b74 Merge pull request #1482 from kohya-ss/flux-merge-lora 
Flux merge lora
 2024-08-20 19:34:57 +09:00
Kohya S
dbed5126bd chore: formatting 2024-08-20 19:33:47 +09:00
Kohya S
9381332020 revert merge function add add option to use new func 2024-08-20 19:32:26 +09:00
Kohya S
6f6faf9b5a fix to work with ai-toolkit LoRA 2024-08-20 19:16:25 +09:00
Kohya S.
92b1f6d968 Merge pull request #1469 from exveria1015/sd3 
Flux の LoRA マージ機能を修正
 2024-08-20 19:06:06 +09:00
Kohya S
c62c95e862 update about multi-resolution training in FLUX.1 2024-08-20 08:21:01 +09:00
Kohya S
9e72be0a13 Fix debug_dataset to work 2024-08-20 08:19:00 +09:00
Kohya S
486fe8f70a feat: reduce memory usage and add memory efficient option for model saving 2024-08-19 22:30:24 +09:00
Kohya S
6e72a799c8 reduce peak VRAM usage by excluding some blocks to cuda 2024-08-19 21:55:28 +09:00