Commit Graph

  • 4df3b0463f Save job pid to the database and sing sigint to kill it when stopping so it stops immediatly. Jaret Burkett 2026-03-26 09:10:37 -06:00
  • 489b194231 Fix CPU/CUDA device mismatch in Klein edit control image encoding (#742) 科林 KELIN 2026-03-26 01:45:38 +08:00
  • 89d2090962 Fixed race condition that would occasionally set the dataset path to the first one when editing a job Jaret Burkett 2026-03-25 11:22:42 -06:00
  • 3f7a3d8d87 Shorten stal action to 3 months Jaret Burkett 2026-03-25 10:42:18 -06:00
  • 45647c15d3 Added github actions to close stale issues automatically. Hopefully it doesnt break things Jaret Burkett 2026-03-25 10:25:56 -06:00
  • 899ee528f9 Update git ignore Jaret Burkett 2026-03-25 10:16:36 -06:00
  • 5d5a8ef9da Fixed issue with deleting datasets and jobs with newer version of node.js. Bumped minimum version of node js to 20 Jaret Burkett 2026-03-25 10:04:36 -06:00
  • dfde30f231 Fix issue with ltx2 custom te repo path Jaret Burkett 2026-03-25 09:50:18 -06:00
  • b8000dbcbc Bump version Jaret Burkett 2026-03-25 08:18:42 -06:00
  • 54f4732c9b Fix the bug in temporal_compression data loader (#754) Rodrigo Reis 2026-03-25 11:16:44 -03:00
  • 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. Jaret Burkett 2026-03-24 12:20:09 -06:00
  • 4ad14d211a Add an import config button (#733) Rasmus Lerdorf 2026-03-23 17:41:27 -04:00
  • 7a0bbca5b1 Fix random_noise_multiplier (#738) Remix 2026-03-23 21:22:16 +00:00
  • 99a4a5887b Fix Qwen attention mask crash with diffusers >=0.37 (#748) Rayane 2026-03-23 21:43:08 +01:00
  • 295094b4b5 Fixed new breaking change in diffusers with with qwen image Jaret Burkett 2026-03-23 14:10:55 -06:00
  • 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. Jaret Burkett 2026-03-23 20:08:33 +00:00
  • 561e6f201c Fixed an issue with ltx 2.3 i2v training Jaret Burkett 2026-03-23 12:41:18 -06:00
  • 330059d8a1 version bump Jaret Burkett 2026-03-23 11:01:16 -06:00
  • e91827f9be Change gemma repo to lightricks one that is not gated Jaret Burkett 2026-03-23 11:00:32 -06:00
  • 253cb31362 Fix issue with video and images with no audio on ltx models Jaret Burkett 2026-03-22 22:09:23 -06:00
  • 4a3d317e2b Fix issue with using the default text encoder with ltx 2.3 Jaret Burkett 2026-03-22 18:53:59 -06:00
  • 859635e95b Add support for training LTX 2.3 (#745) Jaret Burkett 2026-03-22 17:56:59 -06:00
  • 7e1fdc3844 Remove the 0.1 floor for amplification Jaret Burkett 2026-03-22 09:01:58 -06:00
  • 0f075fc45e Adjust signal amplification target. Allow signal amplification strength in config. Jaret Burkett 2026-03-22 08:30:13 -06:00
  • dcd98dc0d5 Add signal amplification Jaret Burkett 2026-03-21 07:44:18 -06:00
  • 35b1cde3cb Fixed issue on z-image that prevented training at a larger batch size Jaret Burkett 2026-03-10 15:43:25 -06:00
  • 4909b809c7 Fixed issue with audio loss multiplier. Jaret Burkett 2026-03-10 15:16:09 -06:00
  • 06ef3d343a add ability to use batch noise correction during training Jaret Burkett 2026-03-10 09:05:57 -06:00
  • b04c64e0f8 Add a dino version of DFE Jaret Burkett 2026-03-04 08:20:37 -07:00
  • 9dee42fc09 Updated supporters Jaret Burkett 2026-03-03 08:04:37 -07:00
  • 35978df8a3 Adjust defaults for ui graph to get and show all losses Jaret Burkett 2026-03-02 10:27:15 -07:00
  • 57d407cfd4 Add support for training lodestones/Zeta-Chroma Jaret Burkett 2026-03-01 12:52:29 -07:00
  • 40f995f616 Add method to do continuious lora merging in for low vram full finetuning. Jaret Burkett 2026-02-26 09:00:41 -07:00
  • de7d22c9be Version bump Jaret Burkett 2026-02-19 11:58:15 -07:00
  • 1c74ca5d22 Add audio_loss_multiplier to scale audio loss to larger values if desired. Jaret Burkett 2026-02-19 11:57:44 -07:00
  • 3632656cda make DFE work with more VAEs Jaret Burkett 2026-02-18 09:46:37 -07:00
  • a055947d56 Add signal_correction_noise_scale to config to scale the signal correction strength Jaret Burkett 2026-02-07 12:04:21 -07:00
  • 454722cc97 Add signal correction noise Jaret Burkett 2026-02-07 09:49:55 -07:00
  • e82cf6eec2 Fixed issue that prevented full fine-tuning of flux2 models when using gradient checkpointing Jaret Burkett 2026-02-06 16:18:43 -07:00
  • 1422789452 Improved the method to augment random noise Jaret Burkett 2026-02-06 15:44:10 -07:00
  • 115f0a3670 Fixed error with wan models when caching text embeddings Jaret Burkett 2026-02-06 14:26:53 -07:00
  • 5c37db04f9 Added ability to activate experimental blank stabilization during training to zero out latents with blank prompts. Jaret Burkett 2026-02-04 13:00:03 -07:00
  • 42acb0d4be Build out an audio player card in preperation for audio datasets and samples. Jaret Burkett 2026-02-03 08:15:55 -07:00
  • 50664c2421 Version bump Jaret Burkett 2026-01-28 12:55:32 -07:00
  • 1ce2428722 Shrink text embeds to max token length for LTX-2. Drastically reduces cached text embedding sizes Jaret Burkett 2026-01-28 12:54:49 -07:00
  • ea912d2d7b Increase default sample steps from 25 to 30 for z_image Jaret Burkett 2026-01-27 09:39:21 -07:00
  • 2db090144a Add support for Z-Image Jaret Burkett 2026-01-27 09:34:46 -07:00
  • 9ef6f1a828 Increase client body size to 100 gb Jaret Burkett 2026-01-24 12:44:17 -07:00
  • f29272ee90 Update diffusers version with dgx Jaret Burkett 2026-01-19 14:06:38 -07:00
  • a6da9e37ac Add support for FLUX.2 klein base models Jaret Burkett 2026-01-17 17:46:25 -07:00
  • 0efed794b4 Fix issue where flux2 would ignore single control image on training Jaret Burkett 2026-01-17 20:26:35 +00:00
  • e132dbae76 Add number of repeats for a dataset in the ui Jaret Burkett 2026-01-15 08:03:31 -07:00
  • e40d7ac605 Ignore i2v on ltx is training on images Jaret Burkett 2026-01-14 18:46:27 -07:00
  • 9848de7946 Fix issue with ltx cached latents if there is no audio. Jaret Burkett 2026-01-14 17:27:01 -07:00
  • 73dedbf662 Do caching of latents, first frame and audio when caching latents for LTX2 Jaret Burkett 2026-01-14 11:05:23 -07:00
  • 64fe29b182 Support img 2 vid training for ltx-2 Jaret Burkett 2026-01-13 19:04:56 -07:00
  • 5b5aadadb8 Add LTX-2 Support (#644) Jaret Burkett 2026-01-13 04:55:30 -07:00
  • 6870ab490f Add 4 bit ARA for qwen image 2512 Jaret Burkett 2026-01-01 20:16:56 -07:00
  • 926097aa4c Added 3bit ARA for qwen image 2512 Jaret Burkett 2026-01-01 06:51:49 -07:00
  • 4d5a649a7d Added initial support for Qwen-Image-2512 Jaret Burkett 2025-12-31 06:11:56 -07:00
  • 0d5c181843 Fixed issue where the control images would sometimes be ignored on qwen_image_edit_2511 Jaret Burkett 2025-12-30 16:40:49 +00:00
  • 356449ec3f bump diffusers version Jaret Burkett 2025-12-26 11:18:23 -07:00
  • 90fc99f486 Separate dependencies for DGX OS devices (#610) raziel2001au 2025-12-27 01:32:26 +10:00
  • a767b82b60 Fixed issue with new logger when ooming Jaret Burkett 2025-12-25 16:57:34 +00:00
  • 8edf1e44c5 Added 3 bit accuracy recovery adapter for qwen image edit 2511 Jaret Burkett 2025-12-24 05:33:47 -07:00
  • ed36edd85b Bumped docker OS, python version, torch version Jaret Burkett 2025-12-23 19:44:20 -07:00
  • 57a2ab1299 Add initial support for Qwen Image Edit 2511 Jaret Burkett 2025-12-23 10:53:48 -07:00
  • 9883055684 Fix issue where ui could break if caption is read as a non string. Jaret Burkett 2025-12-23 09:47:19 -07:00
  • 87edca1b2b Added initial support to initiate lora training from an existing lora Jaret Burkett 2025-12-22 12:49:15 -07:00
  • 91342853c1 Add support for DGX OS (#567) raziel2001au 2025-12-21 00:20:07 +10:00
  • 8864ba915e Remove easy-dwpose from the default requierments Jaret Burkett 2025-12-20 07:16:20 -07:00
  • 113bbd0e3e Fixed an issue with the new version of nextjs with client body size Jaret Burkett 2025-12-18 19:18:35 -07:00
  • ba00eea7d9 Add loss graph to the ui Jaret Burkett 2025-12-18 10:08:59 -07:00
  • 3b6c1ade18 Update supporters Jaret Burkett 2025-12-17 15:20:55 -07:00
  • cd0e691040 Fix NextJS vulnerability (#594) apolinário 2025-12-17 18:03:13 +01:00
  • 26f4f02453 Add support for Z-Image-De-Turbo Jaret Burkett 2025-12-04 10:03:13 -07:00
  • 2d30dc5d52 Bump version Jaret Burkett 2025-12-02 21:29:19 -07:00
  • 6c85184441 Set zit training adapter to default to v2 Jaret Burkett 2025-12-02 16:46:05 -07:00
  • e6c5aead3b Fix issue that prevented ramtorch layer offloading with z_image Jaret Burkett 2025-12-02 16:14:34 -07:00
  • d42f5af2fc Fixed issue with DOP when using Z-Image Jaret Burkett 2025-11-28 09:36:21 -07:00
  • 08a39754a4 Fixed issue that prevented caching text embeddings on z-image Jaret Burkett 2025-11-28 09:19:39 -07:00
  • 4e62c38df5 Add support for training Z-Image Turbo with a de-distill training adapter Jaret Burkett 2025-11-28 08:08:53 -07:00
  • 21bb8a2bf4 Merge pull request #525 from ostris/flux2 Jaret Burkett 2025-11-25 07:53:36 -08:00
  • 01cf480233 Add FLUX.2 official weights Jaret Burkett 2025-11-25 08:52:19 -07:00
  • dadbeda197 Update test weights Jaret Burkett 2025-11-23 10:51:50 -07:00
  • 0b5f3475e2 Merge branch 'main' into flux2 Jaret Burkett 2025-11-23 08:18:35 -07:00
  • 50e5d99545 Fix issue where text encoder was not fully unloaded in some instances Jaret Burkett 2025-11-19 09:01:00 -07:00
  • 26e4b71b57 Fix issue with parsing image info for sample info on some windows machines. Jaret Burkett 2025-11-19 08:45:05 -07:00
  • cd607c4902 Fix a bug that can happen if you remove a gpu from your machine. Jaret Burkett 2025-11-19 08:28:48 -07:00
  • af8e9ea149 Add initial support for FLUX.2 Jaret Burkett 2025-11-18 11:17:38 -07:00
  • 323b4aaf5a Do not copy pin memory if it fails, just move Jaret Burkett 2025-11-17 18:04:00 +00:00
  • 2e7b2d9926 Added Differential Guidance training target Jaret Burkett 2025-11-10 09:38:25 -07:00
  • 9b89bab8fe Version bump Jaret Burkett 2025-11-09 10:11:25 -07:00
  • 6f308fc46e When soing guidance loss, make CFG zero an optional target instead of a forced one. Jaret Burkett 2025-11-04 09:16:15 -07:00
  • c984369294 Fixed resizing of control image resolution for Qwen Image Edit 2509 when using match_target_res Jaret Burkett 2025-10-30 06:30:01 -06:00
  • 42e5e3cd1c Adjust DFE to handle 5 dimension latent spaces Jaret Burkett 2025-10-27 07:48:44 -06:00
  • 8c12977891 Fixed adafactor eps Jaret Burkett 2025-10-26 05:47:25 -06:00
  • 80418209b8 Fixe a variable that could nt be declared when doing blank prompt preservation Jaret Burkett 2025-10-23 16:19:56 -06:00
  • ee206cfa18 Added blank prompt preservation Jaret Burkett 2025-10-22 14:55:13 -06:00
  • ca57ffc270 When having less than 3 sample images, add spacing to the grid so images are not huge Jaret Burkett 2025-10-22 13:52:38 -06:00