Commit Graph
100 Commits
Author SHA1 Message Date
Jaret Burkett ab5fef8970 Fix caption dropout so it now works identically when caching text embeddings. 2026-08-10 18:53:33 -06:00
Jaret Burkett 356ce7e84e Version bump 2026-08-10 09:21:27 -06:00
Jaret Burkett 257da9b586 Rework DOP so it works with caching text embeddings 2026-08-09 22:13:49 -06:00
Jaret Burkett 5ff8a0435a Make v1 the default training adapter 2026-08-09 14:56:39 -06:00
Jaret Burkett 61da9c95d3 Version bump 2026-08-09 12:39:30 -06:00
Jaret Burkett 72623ed3d6 When doing auto frame count. Ensure the time is not squeezed or expanded to fit tempooral spacing. trime the few extra frames. Also fixed frame counts of buckets. 2026-08-09 12:31:02 -06:00
Jaret Burkett 682b27c6ee Reworked freeing memory manager for removing text encoder completly when not needed. 2026-08-09 07:08:24 -06:00
Jaret Burkett 3a28c4b1b7 Keep alive cron server to prevent failed connections 2026-08-08 20:27:01 -06:00
Jaret Burkett 8c1a4082fd Allow images to work with auto frame count, and include images in video datasets if they exist. 2026-08-08 20:26:28 -06:00
Jaret Burkett 6d8afa5684 Version bump 2026-08-08 18:58:11 -06:00
Jaret Burkett (Ostris) c596d4ab27 Merge pull request #1002 from whatsthisaithing/codex/fix-convrot-offload-stream-lifetime
Fix offload buffer stream lifetime
2026-08-08 18:55:18 -06:00
Jaret Burkett f4e9130547 Fix race condition that can corrupt grads under certain conditions. 2026-08-07 14:52:47 -06:00
Jaret Burkett 817f3dcbcb Fix finite check on inverted masked prior 2026-08-07 09:49:12 -06:00
Jaret Burkett 685ce37a8d Adjust sample timestep sigmas to be model evals for h3 for 1 extra step 2026-08-06 19:54:04 -06:00
Jaret Burkett 9171d5ec1d Update training adapter path 2026-08-06 11:21:28 -06:00
Jaret Burkett 71625d1207 Add the alpha version of the MiniMax H3 trianing adapter and set it as the new default training method. 2026-08-06 11:11:31 -06:00
Jaret Burkett b904b99705 varsion bump 2026-08-06 09:25:35 -06:00
Jaret Burkett b811636ae4 Check for finite vs isnan on loss before backpropigating. to catch infinity overflows 2026-08-06 09:18:56 -06:00
Jaret Burkett edacd406b3 Handle minimax loading of non pruned model 2026-08-06 09:18:00 -06:00
Jaret Burkett 7309db4d74 Fix layer offloaded adaln projection layer move 2026-08-06 08:10:20 -06:00
Jaret Burkett 139a38f5bd Upcast adaln pruned layers to fp32 on h3 to prevent overflow. 2026-08-06 07:51:15 -06:00
Jaret Burkett 1e1418b22c Apply sigma to contrastive guidance to balance loss better. Prevent noise grads on images/non audio datasets. Prep for training adapters on MiniMax H3 2026-08-05 13:27:12 -06:00
Jaret Burkett 9065951da3 Version bump 2026-08-04 22:14:54 -06:00
Jaret Burkett 3afa270ab5 Fix audio losses for DOP and other preservation losses 2026-08-04 22:08:48 -06:00
Jaret Burkett 0f9094db95 Fix audio loss when doing do_guidance_loss 2026-08-04 21:43:31 -06:00
Jaret Burkett d870e9b68a Fix backwards compatability for older versions of triton 2026-08-04 21:07:57 -06:00
Jaret Burkett a8d67ecd90 Version Bump 2026-08-04 16:28:04 -06:00
Jaret Burkett 9fc1f208df Remove adaln_proj from the network modules for minimax_h3 2026-08-04 16:19:46 -06:00
Jaret Burkett 183433ae8e Make MiniMax H3 default to using contrastive guidance loss to prevent distillation breakdown 2026-08-04 16:13:45 -06:00
Jaret Burkett 00a93e3830 Add dataset flag to cache the raw tensors 2026-08-04 15:32:48 -06:00
Jaret Burkett 8a0bcf1ffe Fix issue loading H3 test encoder on older GPUS 2026-08-04 15:30:29 -06:00
Jaret Burkett dc29ae1187 Version Bump 2026-08-04 09:27:46 -06:00
Jaret Burkett d20a17c10e Limit max tokens to 512. Allow override with model kwargs. 2026-08-04 07:55:21 -06:00
Jaret Burkett 602306da77 Add gradient checkpointing to vae 2026-08-04 07:54:51 -06:00
Jaret Burkett 18f5810d6c Adjust default alpha for h3 2026-08-03 20:15:28 -06:00
Jaret Burkett a9a04547e9 Dont move encoders on and off device when caching until the first instance of needing to process a cache item. 2026-08-03 15:54:30 -06:00
Jaret Burkett 41676bb258 Queue up videos with multiple threads when caching latents so the VAE is not waiting on videos to process 2026-08-03 15:41:36 -06:00
Jaret Burkett 546eb7daff Look for existing models in folders recursivly 2026-08-03 15:39:55 -06:00
Jaret Burkett d3a3f70a2a Speed up quantization processing on H3 2026-08-03 15:21:39 -06:00
Jaret Burkett 88ac27fc8f Handle images with MiniMax H3. 2026-08-03 11:58:44 -06:00
Jaret Burkett bf739ff966 Fix issue with layer offloading with MinMax H3 2026-08-03 11:32:36 -06:00
Jaret Burkett 9d614a51fb Hard fail if a step in the docker build fails. 2026-08-03 10:38:31 -06:00
Jaret Burkett 8502a845b1 Add support for MiniMax H3 T2V and I2V training 2026-08-03 10:17:39 -06:00
Jaret Burkett 73cab2acf5 Reworked merge in out of loras with convrot weights for better roundtrip accuracy. 2026-08-02 08:29:17 -06:00
Jaret Burkett a6f6b6b896 Fixed experiment opt name match 2026-08-01 17:43:36 -06:00
Jaret Burkett 6b95282097 Recover from issue when a video model first fram may not have been cached properly 2026-08-01 12:00:33 -06:00
Jaret Burkett 5baa495585 DFE optimizations 2026-08-01 10:06:16 -06:00
Jaret Burkett fc78b07332 Attach the ema to the base model so it can be used on specific models 2026-08-01 10:05:42 -06:00
Jaret Burkett c68e58083f Add code for automagic experiment 2026-08-01 10:04:46 -06:00
Jaret Burkett 497014bf5d Set i2v to default to false when omitted from the config 2026-07-31 19:11:58 -06:00
Jaret Burkett 038f24e8c3 Revert torchao back to older version 2026-07-31 16:34:06 -06:00
Jaret Burkett 6e7bc81241 Allow random noise shift with video latents. 2026-07-31 05:58:08 -06:00
Jaret Burkett ddc69745fe Update docker build image with newer dependencies 2026-07-30 14:20:31 -06:00
Jaret Burkett (Ostris) 2cab330392 Merge pull request #986 from ostris/dev
Add AI Toolkit Manager script that auto installs/runs/and updates AI Toolkit.
2026-07-30 11:55:13 -06:00
Jaret Burkett c8636478f9 Version Bump 2026-07-30 11:48:01 -06:00
Jaret Burkett 7b2386c096 Handle video codecs that fail in opencv 2026-07-29 21:01:57 -06:00
Jaret Burkett 9021caa723 Merge branch 'dev' of github.com:ostris/ai-toolkit into dev 2026-07-29 17:50:50 -06:00
Jaret Burkett 3f8afcac7e Allow dataloader to encode first frame with the text embeddings if the model needs it. 2026-07-29 17:50:45 -06:00
Jaret Burkett 23f1ebfb76 Update to high speed xet env var 2026-07-29 17:47:53 -06:00
Jaret Burkett 3d472de2f1 Reworked spawning on dataloader so windows and mac can use multiple data loader workers now 2026-07-29 17:47:04 -06:00
Jaret Burkett 65443cfffa Add information about the new manager to the README 2026-07-29 10:29:36 -06:00
Jaret Burkett 3bd2119c04 Add flash-linear-attention package for hardware that supports it. 2026-07-29 09:14:37 -06:00
Jaret Burkett 1e22732db7 Merge branch 'dev' of https://github.com/ostris/ai-toolkit into dev 2026-07-28 12:27:55 -06:00
Jaret Burkett aa762103b3 Add build support for Nvidia Spark 2026-07-28 12:27:51 -06:00
Jaret Burkett c3afd95cc4 Improvements for mps convrot quants 2026-07-28 12:11:19 -06:00
Jaret Burkett 038270eb2f Fix issue with macstats on mac 2026-07-28 08:27:31 -06:00
Jaret Burkett 83879ac7c2 Fix issue with user agent downloading ffmpeg 2026-07-28 08:15:28 -06:00
Jaret Burkett 6d6c5a3d91 Prevent overwriting package-lock.json when installing deps 2026-07-27 18:47:28 -06:00
Jaret Burkett 461e798708 Rework windows start and stop methods so that command windows dont appear. Stop with signal since we cannot signint. 2026-07-27 17:43:01 -06:00
Jaret Burkett 6b0449c326 Fixed install issues with windows builds 2026-07-27 16:06:48 -06:00
Jaret Burkett 1e58c9a0f0 Built a universal manager and installer for all operating systems and environments. Bumped a lot of versions of things. Still needs deep testing. 2026-07-27 15:10:29 -06:00
Jaret Burkett 7e7053fc9a Remove k-sampler requirement and remove it form the cold. not used anymore anyway 2026-07-27 14:58:31 -06:00
Jaret Burkett b677cdb026 Move uintx quantization to ostris quant with bit identical matching. Now we are not bound to an older version of torch ao. 2026-07-27 12:59:42 -06:00
Jaret Burkett fb204b7677 Fixed for DFEs with pixelspace and video models 2026-07-27 11:12:02 -06:00
Jaret Burkett 0e17841767 Version bump 2026-07-25 11:34:33 -06:00
Jaret Burkett 92bdb6e473 Add support for Mage-Flow and Mage-Flow Edit 2026-07-25 11:34:20 -06:00
Jaret Burkett 0c3a5e6970 Default to lokr full rank when not passed. 2026-07-25 09:06:49 -06:00
Jaret Burkett efb58c8641 Switch to thumbnails and thumbnail creation on the sample grid page until clicked. 2026-07-25 08:40:33 -06:00
Jaret Burkett e00f3791e2 Update some node packages. 2026-07-24 13:50:06 -06:00
Jaret Burkett be3406140b Remove dev indicators 2026-07-24 13:30:30 -06:00
Jaret Burkett 8f2d001eae Improvements to video frame loading. Added ability to cache as uint8 pixelspace for video 2026-07-24 12:36:47 -06:00
Jaret Burkett 67984754c3 Put more information about model gating and how to solve it 2026-07-24 09:56:02 -06:00
Jaret Burkett 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
Jaret Burkett 1086bd0b3e Improvements to file transfer speed when downloading loras from cloud 2026-07-23 08:17:17 -06:00
Jaret Burkett d5612dd35c Adjust the x0 of some DFEs 2026-07-22 10:38:40 -06:00
Jaret Burkett e8573dad34 Fix trailing progress bar print when stopping a job in the ui 2026-07-22 10:11:08 -06:00
Jaret Burkett c4db100e17 Version bump 2026-07-21 11:36:36 -06:00
Jaret Burkett 3a4341dee3 Improve ui polling code to prevent poll buildup 2026-07-21 11:35:52 -06:00
Jaret Burkett e54a0fe78c Move to a single prisma client connection for the ui backend to prevent competing connections. 2026-07-21 11:21:28 -06:00
Jaret Burkett 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
Jaret Burkett 088084e2c2 Resize validation images with the bucket sizing strategy. 2026-07-20 11:22:33 -06:00
Jaret Burkett df354da23e Replace trigger word in validation prompts for [trigger] tags 2026-07-20 07:56:04 -06:00
Jaret Burkett 6e158dd1f1 Adjust validation loss defaults 2026-07-19 19:35:33 -06:00
Jaret Burkett 1eb97b7443 Added validation loss 2026-07-19 19:33:45 -06:00
Jaret Burkett cd677c70b5 Fix issue where more than 12 samples would break sample grid. 2026-07-19 09:21:44 -06:00
Jaret Burkett 479c72ada2 Add replacing triggers on prompts when caching text encoder 2026-07-19 09:03:05 -06:00
Jaret Burkett cfdc9033a6 Add min and max LR or automagic to prefent runaway edge cases. 2026-07-17 14:19:53 -06:00
Jaret Burkett f1bc6508ad Fix issue with qwen image edit models. 2026-07-17 09:14:04 -06:00
Jaret Burkett 6696117a94 Fix issue where the log lone for samples would double up sometimes 2026-07-17 08:11:32 -06:00
Jaret Burkett 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