github/ai-toolkit
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

Commit Graph

  • d870e9b68a Fix backwards compatability for older versions of triton Jaret Burkett 2026-08-04 21:07:57 -06:00
  • a8d67ecd90 Version Bump Jaret Burkett 2026-08-04 16:28:04 -06:00
  • 9fc1f208df Remove adaln_proj from the network modules for minimax_h3 Jaret Burkett 2026-08-04 16:19:46 -06:00
  • 183433ae8e Make MiniMax H3 default to using contrastive guidance loss to prevent distillation breakdown Jaret Burkett 2026-08-04 16:13:45 -06:00
  • 00a93e3830 Add dataset flag to cache the raw tensors Jaret Burkett 2026-08-04 15:32:48 -06:00
  • 8a0bcf1ffe Fix issue loading H3 test encoder on older GPUS Jaret Burkett 2026-08-04 15:30:29 -06:00
  • dc29ae1187 Version Bump Jaret Burkett 2026-08-04 09:27:46 -06:00
  • d20a17c10e Limit max tokens to 512. Allow override with model kwargs. Jaret Burkett 2026-08-04 07:55:21 -06:00
  • 602306da77 Add gradient checkpointing to vae Jaret Burkett 2026-08-04 07:54:51 -06:00
  • 18f5810d6c Adjust default alpha for h3 Jaret Burkett 2026-08-03 20:15:28 -06:00
  • a9a04547e9 Dont move encoders on and off device when caching until the first instance of needing to process a cache item. Jaret Burkett 2026-08-03 15:54:30 -06:00
  • 41676bb258 Queue up videos with multiple threads when caching latents so the VAE is not waiting on videos to process Jaret Burkett 2026-08-03 15:41:36 -06:00
  • 546eb7daff Look for existing models in folders recursivly Jaret Burkett 2026-08-03 15:39:55 -06:00
  • d3a3f70a2a Speed up quantization processing on H3 Jaret Burkett 2026-08-03 15:21:39 -06:00
  • 88ac27fc8f Handle images with MiniMax H3. Jaret Burkett 2026-08-03 11:58:44 -06:00
  • bf739ff966 Fix issue with layer offloading with MinMax H3 Jaret Burkett 2026-08-03 11:32:36 -06:00
  • 9d614a51fb Hard fail if a step in the docker build fails. Jaret Burkett 2026-08-03 10:38:31 -06:00
  • 8502a845b1 Add support for MiniMax H3 T2V and I2V training Jaret Burkett 2026-08-03 10:17:39 -06:00
  • 73cab2acf5 Reworked merge in out of loras with convrot weights for better roundtrip accuracy. Jaret Burkett 2026-08-02 08:29:17 -06:00
  • a6f6b6b896 Fixed experiment opt name match Jaret Burkett 2026-08-01 17:43:36 -06:00
  • 6b95282097 Recover from issue when a video model first fram may not have been cached properly Jaret Burkett 2026-08-01 12:00:33 -06:00
  • 5baa495585 DFE optimizations Jaret Burkett 2026-08-01 10:06:16 -06:00
  • fc78b07332 Attach the ema to the base model so it can be used on specific models Jaret Burkett 2026-08-01 10:05:42 -06:00
  • c68e58083f Add code for automagic experiment Jaret Burkett 2026-08-01 10:04:46 -06:00
  • 497014bf5d Set i2v to default to false when omitted from the config Jaret Burkett 2026-07-31 19:11:58 -06:00
  • 038f24e8c3 Revert torchao back to older version Jaret Burkett 2026-07-31 16:34:06 -06:00
  • 6e7bc81241 Allow random noise shift with video latents. Jaret Burkett 2026-07-31 05:58:08 -06:00
  • ddc69745fe Update docker build image with newer dependencies Jaret Burkett 2026-07-30 14:20:31 -06:00
  • 2cab330392 Merge pull request #986 from ostris/dev Jaret Burkett (Ostris) 2026-07-30 11:55:13 -06:00
  • c8636478f9 Version Bump Jaret Burkett 2026-07-30 11:48:01 -06:00
  • 7b2386c096 Handle video codecs that fail in opencv Jaret Burkett 2026-07-29 21:01:57 -06:00
  • 9021caa723 Merge branch 'dev' of github.com:ostris/ai-toolkit into dev Jaret Burkett 2026-07-29 17:50:50 -06:00
  • 3f8afcac7e Allow dataloader to encode first frame with the text embeddings if the model needs it. Jaret Burkett 2026-07-29 17:50:45 -06:00
  • 23f1ebfb76 Update to high speed xet env var Jaret Burkett 2026-07-29 17:47:53 -06:00
  • 3d472de2f1 Reworked spawning on dataloader so windows and mac can use multiple data loader workers now Jaret Burkett 2026-07-29 17:47:04 -06:00
  • 65443cfffa Add information about the new manager to the README Jaret Burkett 2026-07-29 10:29:36 -06:00
  • 3bd2119c04 Add flash-linear-attention package for hardware that supports it. Jaret Burkett 2026-07-29 09:14:37 -06:00
  • 1e22732db7 Merge branch 'dev' of https://github.com/ostris/ai-toolkit into dev Jaret Burkett 2026-07-28 12:27:55 -06:00
  • aa762103b3 Add build support for Nvidia Spark Jaret Burkett 2026-07-28 12:27:51 -06:00
  • c3afd95cc4 Improvements for mps convrot quants Jaret Burkett 2026-07-28 12:11:19 -06:00
  • 038270eb2f Fix issue with macstats on mac Jaret Burkett 2026-07-28 08:27:31 -06:00
  • 83879ac7c2 Fix issue with user agent downloading ffmpeg Jaret Burkett 2026-07-28 08:15:28 -06:00
  • 6d6c5a3d91 Prevent overwriting package-lock.json when installing deps Jaret Burkett 2026-07-27 18:47:28 -06:00
  • 461e798708 Rework windows start and stop methods so that command windows dont appear. Stop with signal since we cannot signint. Jaret Burkett 2026-07-27 17:43:01 -06:00
  • 6b0449c326 Fixed install issues with windows builds Jaret Burkett 2026-07-27 16:06:48 -06:00
  • 1e58c9a0f0 Built a universal manager and installer for all operating systems and environments. Bumped a lot of versions of things. Still needs deep testing. Jaret Burkett 2026-07-27 15:10:29 -06:00
  • 7e7053fc9a Remove k-sampler requirement and remove it form the cold. not used anymore anyway Jaret Burkett 2026-07-27 14:58:31 -06:00
  • b677cdb026 Move uintx quantization to ostris quant with bit identical matching. Now we are not bound to an older version of torch ao. Jaret Burkett 2026-07-27 12:59:42 -06:00
  • fb204b7677 Fixed for DFEs with pixelspace and video models Jaret Burkett 2026-07-27 11:12:02 -06:00
  • 0e17841767 Version bump Jaret Burkett 2026-07-25 11:34:33 -06:00
  • 92bdb6e473 Add support for Mage-Flow and Mage-Flow Edit Jaret Burkett 2026-07-25 11:34:20 -06:00
  • 0c3a5e6970 Default to lokr full rank when not passed. Jaret Burkett 2026-07-25 09:06:49 -06:00
  • efb58c8641 Switch to thumbnails and thumbnail creation on the sample grid page until clicked. Jaret Burkett 2026-07-25 08:40:33 -06:00
  • e00f3791e2 Update some node packages. Jaret Burkett 2026-07-24 13:50:06 -06:00
  • be3406140b Remove dev indicators Jaret Burkett 2026-07-24 13:30:30 -06:00
  • 8f2d001eae Improvements to video frame loading. Added ability to cache as uint8 pixelspace for video Jaret Burkett 2026-07-24 12:36:47 -06:00
  • 67984754c3 Put more information about model gating and how to solve it Jaret Burkett 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. Jaret Burkett 2026-07-23 09:35:08 -06:00
  • 1086bd0b3e Improvements to file transfer speed when downloading loras from cloud Jaret Burkett 2026-07-23 08:17:17 -06:00
  • d5612dd35c Adjust the x0 of some DFEs Jaret Burkett 2026-07-22 10:38:40 -06:00
  • e8573dad34 Fix trailing progress bar print when stopping a job in the ui Jaret Burkett 2026-07-22 10:11:08 -06:00
  • c4db100e17 Version bump Jaret Burkett 2026-07-21 11:36:36 -06:00
  • 3a4341dee3 Improve ui polling code to prevent poll buildup Jaret Burkett 2026-07-21 11:35:52 -06:00
  • e54a0fe78c Move to a single prisma client connection for the ui backend to prevent competing connections. Jaret Burkett 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. Jaret Burkett 2026-07-21 11:07:18 -06:00
  • c2864bba48 Enable val/loss by default on the loss graph (#966) fatalis 2026-07-20 12:33:03 -05:00
  • 088084e2c2 Resize validation images with the bucket sizing strategy. Jaret Burkett 2026-07-20 11:22:33 -06:00
  • df354da23e Replace trigger word in validation prompts for [trigger] tags Jaret Burkett 2026-07-20 07:56:04 -06:00
  • 6e158dd1f1 Adjust validation loss defaults Jaret Burkett 2026-07-19 19:35:33 -06:00
  • 1eb97b7443 Added validation loss Jaret Burkett 2026-07-19 19:33:45 -06:00
  • cd677c70b5 Fix issue where more than 12 samples would break sample grid. Jaret Burkett 2026-07-19 09:21:44 -06:00
  • 479c72ada2 Add replacing triggers on prompts when caching text encoder Jaret Burkett 2026-07-19 09:03:05 -06:00
  • 7ba7e35e19 Fix several cases of silent crashing on UI (#922) fatalis 2026-07-19 09:23:57 -05:00
  • a0224793ce Restore device runtime scales for compiled adapters (#963) Zironic 2026-07-18 16:19:57 +02:00
  • cfdc9033a6 Add min and max LR or automagic to prefent runaway edge cases. Jaret Burkett 2026-07-17 14:19:53 -06:00
  • f1bc6508ad Fix issue with qwen image edit models. Jaret Burkett 2026-07-17 09:14:04 -06:00
  • 6696117a94 Fix issue where the log lone for samples would double up sometimes Jaret Burkett 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. Jaret Burkett 2026-07-17 07:59:30 -06:00
  • 7a3d94ed03 Add caching to active job pull Jaret Burkett 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 Jaret Burkett 2026-07-16 16:47:10 -06:00
  • 3c75735ba2 remove unicode (#955) PlagueKind 2026-07-17 00:20:16 +02:00
  • 0552d85aa7 Gice the loss graph more diverse colors Jaret Burkett 2026-07-16 16:06:05 -06:00
  • 5fbfb502b5 Leave the generating samples bar in the log when samples finish. Jaret Burkett 2026-07-16 12:00:45 -06:00
  • e805389f1e Remove print buffer. Add new line after sampling. Jaret Burkett 2026-07-16 11:37:23 -06:00
  • b6f334e676 Version bump Jaret Burkett 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. Jaret Burkett 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. Jaret Burkett 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. Jaret Burkett 2026-07-16 08:50:40 -06:00
  • 5cb54ba9cc Allow setting weight saving flag on hidream_o1 Jaret Burkett 2026-07-16 07:40:25 -06:00
  • 741aeb9ce0 Clear stale return-to-queue flag when starting jobs, fixes crash loop (#920) fatalis 2026-07-15 13:48:39 -05:00
  • fe619405f3 Merge branch 'main' of github.com:ostris/ai-toolkit Jaret Burkett 2026-07-15 12:44:47 -06:00
  • a92f18bf71 krea2: don't hardcode the NVIDIA-only cuDNN SDPA backend (#933) DasPauluteli 2026-07-15 20:44:34 +02:00
  • 4f5974ffa1 Version bump Jaret Burkett 2026-07-15 12:17:35 -06:00
  • b8f8a08ba4 Fix sampling bar with anima Jaret Burkett 2026-07-15 12:17:06 -06:00
  • 3e6bd874c4 feat: Add Anima support (#860) rmatif 2026-07-15 19:59:01 +02:00
  • 8bbd051667 Add sample_start_step setting to configure when sampling starts (#949) fatalis 2026-07-15 12:15:50 -05:00
  • 4ece17b71f Fix adapter scalar handling under torch.compile (#946) Zironic 2026-07-15 19:07:55 +02:00
  • e44c34a955 fix lokr speed and convrot compile (#945) PlagueKind 2026-07-15 18:46:30 +02:00
  • 30162c0602 Improvements for captioner quantization to speed it up. Block compile on captioners. Jaret Burkett 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. Jaret Burkett 2026-07-15 10:24:52 -06:00