Kohya S
|
351bed965c
|
fix model type handling in analyze_state_dict_state function for SD3
|
2025-08-13 21:38:51 +09:00 |
|
Kohya S.
|
dcce057609
|
Merge pull request #2168 from rockerBOO/model-spec-1.0.1
Update model spec to 1.0.1
|
2025-08-13 21:31:21 +09:00 |
|
Kohya S.
|
a125c10852
|
Merge pull request #2167 from rockerBOO/patch-6
Fix validation documentation
|
2025-08-12 19:30:15 +09:00 |
|
rockerBOO
|
c149cf283b
|
Add parser args for other trainers.
|
2025-08-03 00:58:25 -04:00 |
|
rockerBOO
|
9bb50c26c4
|
Set sai_model_spec to must
|
2025-08-03 00:43:09 -04:00 |
|
rockerBOO
|
10bfcb9ac5
|
Remove text model spec
|
2025-08-03 00:40:10 -04:00 |
|
rockerBOO
|
bf0f86e797
|
Add sai_model_spec to train_network.py
|
2025-08-02 21:35:45 -04:00 |
|
rockerBOO
|
056472c2fc
|
Add tests
|
2025-08-02 21:16:56 -04:00 |
|
rockerBOO
|
d24d733892
|
Update model spec to 1.0.1. Refactor model spec
|
2025-08-02 21:14:27 -04:00 |
|
Dave Lage
|
0ad2cb854d
|
Update flux_train_network.md
|
2025-08-02 17:27:55 -04:00 |
|
Dave Lage
|
24c605ee3b
|
Update flux_train_network.md
|
2025-08-02 17:21:25 -04:00 |
|
Dave Lage
|
b9c091eafc
|
Fix validation documentation
|
2025-08-02 17:19:26 -04:00 |
|
Kohya S
|
5249732a0f
|
chore: update README to include --apply_t5_attn_mask requirement for Chroma training #2163
|
2025-08-01 23:38:02 +09:00 |
|
Kohya S.
|
75dd8c872b
|
Merge pull request #2160 from kozistr/update/pytorch-optimizer
Update `pytorch-optimizer` to `3.7.0`
|
2025-08-01 21:55:41 +09:00 |
|
Kohya S.
|
aebfea255f
|
Merge pull request #2165 from kohya-ss/force_t5_attn_mask_for_chroma_training
Force t5 attn mask for chroma training
|
2025-08-01 21:55:23 +09:00 |
|
Kohya S
|
bd6418a940
|
fix: add assertion for apply_t5_attn_mask requirement in Chroma
|
2025-08-01 21:47:38 +09:00 |
|
Kohya S.
|
5dff02a65d
|
Merge pull request #2157 from kohya-ss/feature-chroma-support
Feature Chroma support
|
2025-07-30 22:13:37 +09:00 |
|
Kohya S
|
250f0eb9b0
|
doc: update README and training guide with breaking changes for CFG scale and model download instructions
|
2025-07-30 22:08:51 +09:00 |
|
Kohya S
|
96feb61c0a
|
feat: implement modulation vector extraction for Chroma and update related methods
|
2025-07-30 21:34:49 +09:00 |
|
Kohya S
|
450630c6bd
|
fix: create network from weights not working
|
2025-07-29 20:32:24 +09:00 |
|
kozistr
|
10de781806
|
build(deps): pytorch-optimizer to 3.7.0
|
2025-07-28 23:40:38 +09:00 |
|
Kohya S
|
6c8973c2da
|
doc: add reference link for input vector gradient requirement in Chroma class
|
2025-07-28 22:08:02 +09:00 |
|
Kohya S
|
af14eab6d7
|
doc: update section number for regex-based rank and learning rate configuration in FLUX.1 LoRA guide
|
2025-07-26 19:37:15 +09:00 |
|
Kohya S
|
c28e7a47c3
|
feat: add regex-based rank and learning rate configuration for FLUX.1 LoRA
|
2025-07-26 19:35:42 +09:00 |
|
kohya-ss
|
32f06012a7
|
doc: update flux train document and add about breaking changes in sample generation prompts
|
2025-07-21 21:48:06 +09:00 |
|
Kohya S
|
eef05504de
|
Merge branch 'sd3' into feature-chroma-support
|
2025-07-21 13:49:08 +09:00 |
|
Kohya S.
|
4987057701
|
Merge pull request #2042 from kohya-ss/update-docs
experimental: Documentation Updates with Gemini
|
2025-07-21 13:48:34 +09:00 |
|
Kohya S
|
c84a163b32
|
docs: update README for documentation
|
2025-07-21 13:40:03 +09:00 |
|
Kohya S
|
7de68c1eb1
|
Merge branch 'sd3' into update-docs
|
2025-07-21 13:32:43 +09:00 |
|
Kohya S
|
9eda938876
|
Merge branch 'sd3' into feature-chroma-support
|
2025-07-21 13:32:22 +09:00 |
|
Kohya S.
|
d98400b06e
|
Merge pull request #2138 from kohya-ss/feature-lumina-image
Feature lumina image
|
2025-07-21 13:21:26 +09:00 |
|
Kohya S
|
518545bffb
|
docs: add support information for Lumina-Image 2.0 in recent updates
|
2025-07-21 13:16:42 +09:00 |
|
Kohya S
|
d300f19045
|
docs: update Lumina training guide to include inference script and options
|
2025-07-21 13:15:09 +09:00 |
|
Kohya S
|
aec7e16094
|
feat: add an option to add system prompt for negative in lumina inference
|
2025-07-21 13:14:59 +09:00 |
|
Kohya S
|
77a160d886
|
fix: skip LoRA creation for None text encoders (CLIP-L for Chroma)
|
2025-07-20 21:25:43 +09:00 |
|
Kohya S
|
0b763ef1f1
|
feat: fix timestep for input_vec for Chroma
|
2025-07-20 20:53:06 +09:00 |
|
Kohya S
|
b4e862626a
|
feat: add LoRA training support for Chroma
|
2025-07-20 19:00:09 +09:00 |
|
Kohya S
|
c4958b5dca
|
feat: change img/txt order for attention and single blocks
|
2025-07-20 16:30:43 +09:00 |
|
Kohya S
|
8fd0b12d1f
|
feat: update DoubleStreamBlock and SingleStreamBlock to handle text sequence lengths instead of mask
|
2025-07-20 16:00:58 +09:00 |
|
Kohya S
|
404ddb060d
|
fix: inference for Chroma model
|
2025-07-20 14:08:54 +09:00 |
|
kohya-ss
|
24d2ea86c7
|
feat: support Chroma model in loading and inference processes
|
2025-07-20 12:56:42 +09:00 |
|
Kohya S.
|
d53a532a82
|
Merge pull request #2153 from rockerBOO/fix-alphas-cumprod
Fix alphas cumprod after add_noise for DDIMScheduler
|
2025-07-17 21:37:55 +09:00 |
|
Dave Lage
|
3adbbb6e33
|
Add note about why we are moving it
|
2025-07-16 16:09:20 -04:00 |
|
rockerBOO
|
a7b33f3204
|
Fix alphas cumprod after add_noise for DDIMScheduler
|
2025-07-15 22:36:46 -04:00 |
|
Kohya S
|
c0c36a4e2f
|
fix: remove duplicated latent normalization in decoding
|
2025-07-15 21:58:03 +09:00 |
|
Kohya S
|
25771a5180
|
fix: update help text for cfg_trunc_ratio argument
|
2025-07-15 21:53:13 +09:00 |
|
Kohya S
|
e0fcb5152a
|
feat: support Neta Lumina all-in-one weights
|
2025-07-15 21:34:35 +09:00 |
|
Kohya S
|
a96d684ffa
|
feat: add Chroma model implementation
|
2025-07-15 20:44:43 +09:00 |
|
Kohya S
|
13ccfc39f8
|
fix: update flow matching loss and variable names
|
2025-07-13 21:26:06 +09:00 |
|
Kohya S
|
30295c9668
|
fix: update parameter names for CFG truncate and Renorm CFG in documentation and code
|
2025-07-13 21:00:27 +09:00 |
|