Kohya S
|
18e017bec1
|
feat: add note on PyTorch version requirement to prevent NaN loss
|
2026-02-12 23:47:53 +09:00 |
|
Kohya S
|
e3d8698656
|
feat: add clarification on learning rate adjustments
|
2026-02-12 23:35:45 +09:00 |
|
Kohya S
|
cff10434e2
|
feat: update caption dropout documentation to clarify cache regeneration requirement
|
2026-02-12 23:27:58 +09:00 |
|
Kohya S
|
9a607bec43
|
feat: improve ComfyUI conversion script with prefix constants and module name adjustments
|
2026-02-12 23:17:25 +09:00 |
|
Kohya S
|
4b2283491e
|
feat: add VAE chunking and caching options to reduce memory usage
|
2026-02-11 21:32:00 +09:00 |
|
Kohya S
|
f355a97a32
|
feat: update Anima training guide with new argument specifications and regex-based module selection. Thank you Claude!
|
2026-02-10 22:11:34 +09:00 |
|
kohya-ss
|
9e2b4dc8a0
|
fix: update default value for --discrete_flow_shift in anima training guide
|
2026-02-08 10:56:34 +09:00 |
|
duongve13112002
|
e21a7736f8
|
Support Anima model (#2260)
* Support Anima model
* Update document and fix bug
* Fix latent normlization
* Fix typo
* Fix cache embedding
* fix typo in tests/test_anima_cache.py
* Remove redundant argument apply_t5_attn_mask
* Improving caching with argument caption_dropout_rate
* Fix W&B logging bugs
* Fix discrete_flow_shift default value
|
2026-02-08 10:18:55 +09:00 |
|