ostris/ai-toolkit
1
0
Fork 0
mirror of https://github.com/ostris/ai-toolkit.git synced 2026-05-11 16:30:40 +00:00
Code Issues Packages Projects Releases Wiki Activity
1,004 Commits 11 Branches 0 Tags
a7bb4ddb2cfb1db0556d5eee0761863d2c05dd1e
Commit Graph

1004 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Jaret Burkett
a7bb4ddb2c Work on loss graph. Add smoothed overlay. Allow user to hilite a secton of the graph to zoom into. 2026-03-26 10:05:09 -06:00
Jaret Burkett
401f7df425 Merge branch 'main' of github.com:ostris/ai-toolkit 2026-03-26 09:11:50 -06:00
Jaret Burkett
4df3b0463f Save job pid to the database and sing sigint to kill it when stopping so it stops immediatly. 2026-03-26 09:10:37 -06:00
科林 KELIN
489b194231 Fix CPU/CUDA device mismatch in Klein edit control image encoding (#742) 
When training Klein models with a `control_path` (edit/kontext-style
paired datasets), `encode_image_refs()` returns tensors that reside on
the VAE's device (CPU, since the VAE weights are loaded via
`load_file(..., device="cpu")` and are never explicitly moved to the
training device).  Concatenating those CPU tensors with the training
latents (`packed_latents`) that live on CUDA raises:

    RuntimeError: Expected all tensors to be on the same device

Fix: move `img_cond_seq` and `img_cond_seq_ids` to the same device
(and dtype) as `img_input` / `img_input_ids` before concatenation.

Co-authored-by: HuangYuChuh <HuangYuChuh@users.noreply.github.com>
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-03-25 11:45:38 -06:00
Jaret Burkett
89d2090962 Fixed race condition that would occasionally set the dataset path to the first one when editing a job 2026-03-25 11:22:42 -06:00
Jaret Burkett
3f7a3d8d87 Shorten stal action to 3 months 2026-03-25 10:42:18 -06:00
Jaret Burkett
45647c15d3 Added github actions to close stale issues automatically. Hopefully it doesnt break things 2026-03-25 10:25:56 -06:00
Jaret Burkett
899ee528f9 Update git ignore 2026-03-25 10:16:36 -06:00
Jaret Burkett
5d5a8ef9da Fixed issue with deleting datasets and jobs with newer version of node.js. Bumped minimum version of node js to 20 2026-03-25 10:04:36 -06:00
Jaret Burkett
dfde30f231 Fix issue with ltx2 custom te repo path 2026-03-25 09:50:18 -06:00
Jaret Burkett
b8000dbcbc Bump version 2026-03-25 08:18:42 -06:00
Rodrigo Reis
54f4732c9b Fix the bug in temporal_compression data loader (#754) 2026-03-25 08:16:44 -06:00
Jaret Burkett
7f3309b291 Add support for audo frame count so datasets can have varrying length videos. Varous ltx 2.3 VAE optimizations such as removing tiling articacts, and doing frame split encoding to reduce vram on encoding/decoding. 2026-03-24 12:20:09 -06:00
Rasmus Lerdorf
4ad14d211a Add an import config button (#733) 2026-03-23 15:41:27 -06:00
Remix
7a0bbca5b1 Fix random_noise_multiplier (#738) 
Apply random_noise_multiplier to noise.
 2026-03-23 15:22:16 -06:00
Rayane
99a4a5887b Fix Qwen attention mask crash with diffusers >=0.37 (#748) 
* Fix Qwen Image mask handling

* Fix Qwen attention mask crash with diffusers >=0.37

diffusers v0.37 (PR #12987) optimizes all-ones attention masks to None
in encode_prompt() when there is no padding. This breaks ai-toolkit's
Qwen extensions which call .to() on the mask unconditionally.

Fix: reconstruct the all-ones mask at the boundary (get_prompt_embeds)
right after encode_prompt() returns. This keeps the rest of the code
unchanged and works with both old and new diffusers versions.

Also removes redundant duplicate mask assignments in qwen_image_edit
and qwen_image_edit_plus.

Fixes #740
 2026-03-23 14:43:08 -06:00
Jaret Burkett
295094b4b5 Fixed new breaking change in diffusers with with qwen image 2026-03-23 14:10:55 -06:00
Jaret Burkett
5642b656b9 Fix audio issues with ltx2 models. Silent codec fails now raised. Auto convert surround sound audio to stereo. Invalidate old caches just to be safe so they recache now. 2026-03-23 20:08:33 +00:00
Jaret Burkett
561e6f201c Fixed an issue with ltx 2.3 i2v training 2026-03-23 12:41:18 -06:00
Jaret Burkett
330059d8a1 version bump 2026-03-23 11:01:16 -06:00
Jaret Burkett
e91827f9be Change gemma repo to lightricks one that is not gated 2026-03-23 11:00:32 -06:00
Jaret Burkett
253cb31362 Fix issue with video and images with no audio on ltx models 2026-03-22 22:09:23 -06:00
Jaret Burkett
4a3d317e2b Fix issue with using the default text encoder with ltx 2.3 2026-03-22 18:53:59 -06:00
Jaret Burkett
859635e95b Add support for training LTX 2.3 (#745) 
* Initial support for ltx 2.3. Still needs a lot of testing to make sure it is all right.

* bump version

* Handle lora renaming keys for new ltx 2.3 layers
 2026-03-22 17:56:59 -06:00
Jaret Burkett
7e1fdc3844 Remove the 0.1 floor for amplification 2026-03-22 09:01:58 -06:00
Jaret Burkett
0f075fc45e Adjust signal amplification target. Allow signal amplification strength in config. 2026-03-22 08:30:13 -06:00
Jaret Burkett
dcd98dc0d5 Add signal amplification 2026-03-21 07:44:18 -06:00
Jaret Burkett
35b1cde3cb Fixed issue on z-image that prevented training at a larger batch size 2026-03-10 15:43:25 -06:00
Jaret Burkett
4909b809c7 Fixed issue with audio loss multiplier. 2026-03-10 15:16:09 -06:00
Jaret Burkett
06ef3d343a add ability to use batch noise correction during training 2026-03-10 09:05:57 -06:00
Jaret Burkett
b04c64e0f8 Add a dino version of DFE 2026-03-04 08:20:37 -07:00
Jaret Burkett
9dee42fc09 Updated supporters 2026-03-03 08:04:37 -07:00
Jaret Burkett
35978df8a3 Adjust defaults for ui graph to get and show all losses 2026-03-02 10:27:15 -07:00
Jaret Burkett
57d407cfd4 Add support for training lodestones/Zeta-Chroma 2026-03-01 12:52:29 -07:00
Jaret Burkett
40f995f616 Add method to do continuious lora merging in for low vram full finetuning. 2026-02-26 09:00:41 -07:00
Jaret Burkett
de7d22c9be Version bump 2026-02-19 11:58:15 -07:00
Jaret Burkett
1c74ca5d22 Add audio_loss_multiplier to scale audio loss to larger values if desired. 2026-02-19 11:57:44 -07:00
Jaret Burkett
3632656cda make DFE work with more VAEs 2026-02-18 09:46:37 -07:00
Jaret Burkett
a055947d56 Add signal_correction_noise_scale to config to scale the signal correction strength 2026-02-07 12:04:21 -07:00
Jaret Burkett
454722cc97 Add signal correction noise 2026-02-07 09:49:55 -07:00
Jaret Burkett
e82cf6eec2 Fixed issue that prevented full fine-tuning of flux2 models when using gradient checkpointing 2026-02-06 16:18:43 -07:00
Jaret Burkett
1422789452 Improved the method to augment random noise 2026-02-06 15:44:10 -07:00
Jaret Burkett
115f0a3670 Fixed error with wan models when caching text embeddings 2026-02-06 14:26:53 -07:00
Jaret Burkett
5c37db04f9 Added ability to activate experimental blank stabilization during training to zero out latents with blank prompts. 2026-02-04 13:00:03 -07:00
Jaret Burkett
42acb0d4be Build out an audio player card in preperation for audio datasets and samples. 2026-02-03 08:15:55 -07:00
Jaret Burkett
50664c2421 Version bump 2026-01-28 12:55:32 -07:00
Jaret Burkett
1ce2428722 Shrink text embeds to max token length for LTX-2. Drastically reduces cached text embedding sizes 2026-01-28 12:54:49 -07:00
Jaret Burkett
ea912d2d7b Increase default sample steps from 25 to 30 for z_image 2026-01-27 09:39:21 -07:00
Jaret Burkett
2db090144a Add support for Z-Image 2026-01-27 09:34:46 -07:00
Jaret Burkett
9ef6f1a828 Increase client body size to 100 gb 2026-01-24 12:44:17 -07:00