be3406140b
Remove dev indicators
2026-07-24 13:30:30 -06:00
8f2d001eae
Improvements to video frame loading. Added ability to cache as uint8 pixelspace for video
2026-07-24 12:36:47 -06:00
67984754c3
Put more information about model gating and how to solve it
2026-07-24 09:56:02 -06:00
ede6f9ecee
Major ui speed improvements. Moved file server out of next js app and made it multithreadded. Significantly faster downloads for files, images, and videos.
2026-07-23 09:35:08 -06:00
1086bd0b3e
Improvements to file transfer speed when downloading loras from cloud
2026-07-23 08:17:17 -06:00
d5612dd35c
Adjust the x0 of some DFEs
2026-07-22 10:38:40 -06:00
e8573dad34
Fix trailing progress bar print when stopping a job in the ui
2026-07-22 10:11:08 -06:00
c4db100e17
Version bump
2026-07-21 11:36:36 -06:00
3a4341dee3
Improve ui polling code to prevent poll buildup
2026-07-21 11:35:52 -06:00
e54a0fe78c
Move to a single prisma client connection for the ui backend to prevent competing connections.
2026-07-21 11:21:28 -06:00
9e9439015e
Switch sqlite database to WAL mode. It will be significantly faster with multiple writers and readers.
2026-07-21 11:07:18 -06:00
c2864bba48
Enable val/loss by default on the loss graph ( #966 )
2026-07-20 11:33:03 -06:00
088084e2c2
Resize validation images with the bucket sizing strategy.
2026-07-20 11:22:33 -06:00
df354da23e
Replace trigger word in validation prompts for [trigger] tags
2026-07-20 07:56:04 -06:00
6e158dd1f1
Adjust validation loss defaults
2026-07-19 19:35:33 -06:00
1eb97b7443
Added validation loss
2026-07-19 19:33:45 -06:00
cd677c70b5
Fix issue where more than 12 samples would break sample grid.
2026-07-19 09:21:44 -06:00
479c72ada2
Add replacing triggers on prompts when caching text encoder
2026-07-19 09:03:05 -06:00
7ba7e35e19
Fix several cases of silent crashing on UI ( #922 )
...
Co-authored-by: Jaret Burkett <jaretburkett@gmail.com>
2026-07-19 08:23:57 -06:00
a0224793ce
Restore device runtime scales for compiled adapters ( #963 )
...
Co-authored-by: Rydén Johan <johan.ryden@bostad.uppsala.se>
2026-07-18 08:19:57 -06:00
cfdc9033a6
Add min and max LR or automagic to prefent runaway edge cases.
2026-07-17 14:19:53 -06:00
f1bc6508ad
Fix issue with qwen image edit models.
2026-07-17 09:14:04 -06:00
6696117a94
Fix issue where the log lone for samples would double up sometimes
2026-07-17 08:11:32 -06:00
988d891102
Added a Sample Next Step in the job gear dropdown to force a sample on the next step.
2026-07-17 07:59:30 -06:00
7a3d94ed03
Add caching to active job pull
2026-07-16 16:51:05 -06:00
bf15b65972
Add caching for api calls to speed them up. Added caching for cpu and gpu stat calls
2026-07-16 16:47:10 -06:00
3c75735ba2
remove unicode ( #955 )
2026-07-16 16:20:16 -06:00
0552d85aa7
Gice the loss graph more diverse colors
2026-07-16 16:06:05 -06:00
5fbfb502b5
Leave the generating samples bar in the log when samples finish.
2026-07-16 12:00:45 -06:00
e805389f1e
Remove print buffer. Add new line after sampling.
2026-07-16 11:37:23 -06:00
b6f334e676
Version bump
2026-07-16 08:56:32 -06:00
bbaef7852a
Do not materalize weights on ostris quantizer when getting state dict. Require dequantization of weight like other quantization methods.
2026-07-16 08:55:51 -06:00
31c45cf37d
Update huggingface hub requirement. Remove forced xet removal as some models are so large it wont work without it. Hopefully the latest version of huggingface_hub doesnt have the hanging issues.
2026-07-16 08:52:24 -06:00
e1e1996c16
Rework the logging and terminal emulator on the ui to work like an actual emulator for better output.
2026-07-16 08:50:40 -06:00
5cb54ba9cc
Allow setting weight saving flag on hidream_o1
2026-07-16 07:40:25 -06:00
741aeb9ce0
Clear stale return-to-queue flag when starting jobs, fixes crash loop ( #920 )
2026-07-15 12:48:39 -06:00
fe619405f3
Merge branch 'main' of github.com:ostris/ai-toolkit
2026-07-15 12:44:47 -06:00
a92f18bf71
krea2: don't hardcode the NVIDIA-only cuDNN SDPA backend ( #933 )
...
* krea2: don't hardcode NVIDIA-only cuDNN SDPA backend
The krea2 attention() forced SDPBackend.CUDNN_ATTENTION, which is
NVIDIA-only. On non-NVIDIA backends (AMD ROCm, Intel XPU, Apple MPS)
every forward pass fails with 'RuntimeError: No available kernel.
Aborting execution.', so Krea 2 LoRA training cannot run at all there.
Pass a priority list [CUDNN, FLASH, EFFICIENT, MATH] instead. NVIDIA
still selects cuDNN; other backends fall back to flash/efficient/math.
Verified training end-to-end on an AMD Radeon 8060S (gfx1151, ROCm 7.2).
* Version bump
* Add set priority flag so CUDNN_ATTENTION is selected on cuda devices first.
---------
Co-authored-by: Jaret Burkett <jaretburkett@gmail.com>
2026-07-15 12:44:34 -06:00
4f5974ffa1
Version bump
2026-07-15 12:17:35 -06:00
b8f8a08ba4
Fix sampling bar with anima
2026-07-15 12:17:06 -06:00
3e6bd874c4
feat: Add Anima support ( #860 )
...
* Add Anima training support
* Update Anima modular training
* Use sample guidance for Anima
* Fix Anima sampling
* Limit Anima LoRA targets
* Convert Anima LoRA exports
* Fix Anima local loading
* Update Anima default model
* Pin upstream Anima diffusers
* Adjust template defaults to be consistent with other models. Update README
---------
Co-authored-by: Jaret Burkett (Ostris) <jaretburkett@gmail.com>
2026-07-15 11:59:01 -06:00
8bbd051667
Add sample_start_step setting to configure when sampling starts ( #949 )
...
Co-authored-by: Jaret Burkett <jaretburkett@gmail.com>
2026-07-15 11:15:50 -06:00
4ece17b71f
Fix adapter scalar handling under torch.compile ( #946 )
...
* Fix adapter scalar handling under torch.compile
* Fix instance where error could happen when merging in a lora to the base model
---------
Co-authored-by: Rydén Johan <johan.ryden@bostad.uppsala.se>
Co-authored-by: Jaret Burkett <jaretburkett@gmail.com>
2026-07-15 11:07:55 -06:00
e44c34a955
fix lokr speed and convrot compile ( #945 )
2026-07-15 10:46:30 -06:00
30162c0602
Improvements for captioner quantization to speed it up. Block compile on captioners.
2026-07-15 10:25:47 -06:00
e28727d5cb
Made a fused GEMV kernel for convrot unpacking to increase speed further. Fix bug in test script that made train time add additional grads to bf16.
2026-07-15 10:24:52 -06:00
691ddf434e
Add Qwen3.6 VL captioner.
2026-07-15 07:02:33 -06:00
18da85153b
Disable xet by default. Seems to be causing a lot of hanging issues.
2026-07-14 10:42:03 -06:00
cf0db39ede
Fix some errors for specific quants. Enable saving quantizations.
2026-07-14 07:25:09 -06:00
abba6b5845
Show better errors on captioner
2026-07-14 07:19:03 -06:00
Jaret Burkett
fatalis
Zironic
PlagueKind
DasPauluteli
rmatif