Kohya S
a437949d47
feat: Add support for Safetensors format in caching strategies (WIP)
...
- Introduced Safetensors output format for various caching strategies including Hunyuan, Lumina, SD, SDXL, and SD3.
- Updated methods to handle loading and saving of tensors in Safetensors format.
- Enhanced output validation to check for required tensors in both NPZ and Safetensors formats.
- Modified dataset argument parser to include `--cache_format` option for selecting between NPZ and Safetensors formats.
- Updated caching logic to accommodate partial loading and merging of existing Safetensors files.
2026-03-22 21:15:12 +09:00
Kohya S.
f90fa1a89a
feat: backward compatibility for SD/SDXL latent cache ( #2276 )
...
* fix: improve handling of legacy npz files and add logging for fallback scenarios
* fix: simplify fallback handling in SdSdxlLatentsCachingStrategy
2026-02-23 21:44:51 +09:00
woctordho
50694df3cf
Multi-resolution dataset for SD1/SDXL ( #2269 )
...
* Multi-resolution dataset for SD1/SDXL
* Add fallback to legacy key without resolution suffix
* Support numpy 2.2
2026-02-23 15:30:36 +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
Kohya S
f41e9e2b58
feat: add vae_chunk_size argument for memory-efficient VAE decoding and processing
2025-09-21 11:09:37 +09:00
rockerBOO
025cca699b
Fix samples, LoRA training. Add system prompt, use_flash_attn
2025-02-23 01:29:18 -05:00
Kohya S
1434d8506f
Support SD3.5M multi resolutional training
2024-10-31 19:58:22 +09:00
kohya-ss
886ffb4d65
Merge branch 'sd3' into multi-gpu-caching
2024-10-13 19:14:06 +09:00
Kohya S
c65cf3812d
Merge branch 'sd3' into fast_image_sizes
2024-10-13 17:31:11 +09:00
kohya-ss
74228c9953
update cache_latents/text_encoder_outputs
2024-10-13 16:27:22 +09:00
Kohya S
f2bc820133
support weighted captions for SD/SDXL
2024-10-11 08:48:55 +09:00
Kohya S
886f75345c
support weighted captions for sdxl LoRA and fine tuning
2024-10-10 08:27:15 +09:00
Kohya S
793999d116
sample generation in SDXL ControlNet training
2024-09-30 23:39:32 +09:00
Kohya S
81411a398e
speed up getting image sizes
2024-08-22 22:02:29 +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
1a977e847a
fix typos
2024-07-27 13:51:50 +09:00
Kohya S
41dee60383
Refactor caching mechanism for latents and text encoder outputs, etc.
2024-07-27 13:50:05 +09:00
