Commit Graph

534 Commits

Author SHA1 Message Date
Jaret Burkett 3413fa537f Wan22 14b training is working, still need tons of testing and some bug fixes 2025-08-14 13:03:27 -06:00
Jaret Burkett be71cc75ce Switch to unified text encoder for wan models. Pred for 2.2 14b 2025-08-14 10:07:18 -06:00
Jaret Burkett e12bb21780 Quantize blocks sequentialls without a ARA 2025-08-14 09:59:58 -06:00
Jaret Burkett 3ff4430e84 Fix issue with fake text encoder unload 2025-08-14 09:33:44 -06:00
Jaret Burkett 85bad57df3 Fix bug that would use EMA when set false 2025-08-13 11:39:40 -06:00
Jaret Burkett 77b10d884d Add support for training with an accuracy recovery adapter with qwen image 2025-08-12 08:21:36 -06:00
Jaret Burkett bb6db3d635 Added support for caching text embeddings. This is just initial support and will probably fail for some models. Still needs to be ompimized 2025-08-07 10:27:55 -06:00
Jaret Burkett 5d8922fca2 Add ability to designate a dataset as i2v or t2v for models that support it 2025-08-06 09:29:47 -06:00
Jaret Burkett 9da8b5408e Initial but untested support for qwen_image 2025-08-04 13:29:37 -06:00
Jaret Burkett 9dfb614755 Initial work for training wan first and last frame 2025-08-04 11:37:26 -06:00
Jaret Burkett f453e28ea3 Fixed deprecation of lumina pipeline error 2025-07-29 08:26:51 -06:00
Jaret Burkett ca7c5c950b Add support for Wan2.2 5B 2025-07-29 05:31:54 -06:00
Jaret Burkett cefa2ca5fe Added initial support for Hidream E1 training 2025-07-27 15:12:56 -06:00
Jaret Burkett 77dc38a574 Some work on caching text embeddings 2025-07-26 09:22:04 -06:00
Jaret Burkett c5eb763342 Improvements to VAE trainer. Allow CLIP loss. 2025-07-24 06:50:56 -06:00
Jaret Burkett f500b9f240 Add ability to do more advanced sample prompt objects to prepart for a UI rework on control images and other things. 2025-07-17 07:13:35 -06:00
Jaret Burkett e5ed450dc7 Allow finetuning tiny autoencoder in vae trainer 2025-07-16 07:13:30 -06:00
Jaret Burkett 1930c3edea Fix naming with wan i2v new keys in lora 2025-07-14 07:34:01 -06:00
Jaret Burkett 755f0e207c Fix issue with wan i2v scaling. Adjust aggressive loader to be compatable with updated diffusers. 2025-07-12 16:56:27 -06:00
Jaret Burkett 60ef2f1df7 Added support for FLUX.1-Kontext-dev 2025-06-26 15:24:37 -06:00
Jaret Burkett 8d9c47316a Work on mean flow. Minor bug fixes. Omnigen improvements 2025-06-26 13:46:20 -06:00
Jaret Burkett 24cd94929e Fix bug that can happen with fast processing dataset 2025-06-25 14:01:08 -06:00
Jaret Burkett 19ea8ecc38 Added support for finetuning OmniGen2. 2025-06-25 13:58:16 -06:00
Jaret Burkett 03bc431279 Fixed an issue training lumina 2 2025-06-24 10:29:47 -06:00
Jaret Burkett f3eb1dff42 Add a config flag to trigger fast image size db builder. Add config flag to set unconditional prompt for guidance loss 2025-06-24 08:51:29 -06:00
Jaret Burkett ba1274d99e Added a guidance burning loss. Modified DFE to work with new model. Bug fixes 2025-06-23 08:38:27 -06:00
Jaret Burkett 8602470952 Updated diffusion feature extractor 2025-06-19 15:36:10 -06:00
Jaret Burkett 989ebfaa11 Added a basic torch profiler that can be used in config during development to find some obvious issues. 2025-06-17 13:03:39 -06:00
Jaret Burkett 1cc663a664 Performance optimizations for pre processing the batch 2025-06-17 07:37:41 -06:00
Jaret Burkett 1c2b7298dd More work on mean flow loss. Moved it to an adapter. Still not functioning properly though. 2025-06-16 07:17:35 -06:00
Jaret Burkett c0314ba325 Fixed some issues with training mean flow algo. Still testing WIP 2025-06-16 07:14:59 -06:00
Jaret Burkett fc83eb7691 WIP on mean flow loss. Still a WIP. 2025-06-12 08:00:51 -06:00
Hameer Abbasi 5e86139e0a
Fix `NameError`. 2025-06-11 15:07:20 +02:00
Hameer Abbasi c5d6b74fea
Fix caption loading. 2025-06-11 15:05:31 +02:00
Jaret Burkett 97e101522c Increase ema feedback amount. Normalize the dfe 4 image embeds 2025-06-10 08:01:13 -06:00
Jaret Burkett eefa93f16e Various code to support experiments. 2025-06-09 11:19:21 -06:00
Jaret Burkett 22cdfadab6 Added new timestep weighing strategy 2025-06-04 01:16:02 -06:00
Jaret Burkett adc31ec77d Small updates and bug fixes for various things 2025-06-03 20:08:35 -06:00
Jaret Burkett b6d25fcd10 Improvements to vae trainer. Adjust denoise prediction of DFE v3 2025-05-30 12:06:47 -06:00
Jaret Burkett 79499fa795 Allow fine tuning pruned versions of chroma. Allow flash attention 2 for chroma if it is installed. 2025-05-21 07:02:50 -06:00
Jaret Burkett 48e11cf843 Fallback unwrapping logic if fails 2025-05-21 03:10:33 -06:00
Jaret Burkett fca7fd6c38 Merge branch 'main' of github.com:ostris/ai-toolkit 2025-05-21 02:20:06 -06:00
Jaret Burkett e5181d23cd Added some experimental training techniques. Ignore for now. Still in testing. 2025-05-21 02:19:54 -06:00
Jaret Burkett 4f896c0d8a Fixed issue where sampling fails if doing a full finetune for some models 2025-05-17 19:37:55 +00:00
Jaret Burkett 1210050ead Reworked control generator. It is now significantly faster. Also uses better pose model with better license. 2025-05-08 14:35:55 -06:00
Jaret Burkett 43cb5603ad Added chroma model to the ui. Added logic to easily pull latest, use local, or use a specific version of chroma. Allow ustom name or path in the ui for custom models 2025-05-07 12:06:30 -06:00
Jaret Burkett d9700bdb99 Added initial support for f-lite model 2025-05-01 11:15:18 -06:00
Jaret Burkett 5890e67a46 Various bug fixes 2025-04-29 09:30:33 -06:00
Jaret Burkett 2b4c525489 Reworked automagic optimizer and did more testing. Starting to really like it. Working well. 2025-04-28 08:01:10 -06:00
Jaret Burkett 88b3fbae37 Various experiments and minor bug fixes for edge cases 2025-04-25 13:44:38 -06:00