Commit Graph
1621 Commits
Author SHA1 Message Date
Jaret Burkett 07abdbedc7 Add match_target_res for Qwen Image 2.1 so reference images are scaled to the target's pixel area with their own aspect ratio, consistently across text-embedding caching, training, and sampling, and key the embedding cache on it. 2026-09-22 13:57:49 -06:00
Jaret Burkett 71bc877833 Fix support link 2026-09-22 12:52:29 -06:00
Jaret Burkett (Ostris) 8f2777a4f0 Merge pull request #1055 from vdruts/yue2-safetensors-heads
YuE2: support the safetensors-only v5/v8/v9 semantic heads, key latent cache by head
2026-09-22 12:45:25 -06:00
Jaret Burkett f073188300 Fix Qwen Image Edit Plus batch_size > 1 without cached text embeddings by splitting the batch-stacked control tensor into one control image per prompt. 2026-09-22 12:14:19 -06:00
Jaret Burkett a35d833abf Fix text encoder unload skipping models whose pipeline does not expose the text encoder (Qwen-Image-2.1, Z-Image, LTX2), so cached-embedding runs actually free the TE. 2026-09-22 12:08:29 -06:00
Jaret Burkett 543a0d74d0 Fix issue with saving device state when a text encoder is unloaded. 2026-09-22 12:03:09 -06:00
Jaret Burkett (Ostris) ae6ab90786 Merge pull request #1036 from ArcGleam/fix/qwen-edit-plus-batch-gt-1
Fix: QwenImageEditPlusModel crashes with batch_size > 1
2026-09-22 11:52:33 -06:00
Jaret Burkett (Ostris) 9b67238f6b Merge pull request #1035 from ArcGleam/fix/qwen-edit-plus-control-image-inplace-downsample
Fix in-place downsampling of reference images in QwenImageEditPlusModel
2026-09-22 11:48:08 -06:00
Jaret Burkett (Ostris) 3a39d8cfc8 Merge pull request #1021 from hitoshic1982/fix/cache-text-encoder-device-preset
Fix cache_text_encoder device preset missing in BaseModel
2026-09-22 11:46:24 -06:00
Jaret Burkett 11b65a39e5 Ignore issue review folder 2026-09-22 11:05:38 -06:00
vdruts d0ecde7779 YuE2: load safetensors semantic heads / NAR adapters (v5, v8, v9) and key the latent cache by head 2026-09-21 09:21:44 -04:00
Jaret Burkett a8dfcf7d7e Save thumbnail with alpha if there is one. 2026-09-20 15:16:15 -06:00
Jaret Burkett 086b663bba Add support for training with an alpha channel for Qwen Image 2.1 2026-09-20 14:49:53 -06:00
Jaret Burkett 31ddc709c3 Version bump 2026-09-20 11:04:32 -06:00
Jaret Burkett 474948abb4 Change default guidance to 3 for qwen image. 2026-09-20 11:04:16 -06:00
Jaret Burkett f4f5d5dd58 Change qwen image 2 to use new lokr format 2026-09-20 11:02:57 -06:00
Jaret Burkett c2622ed250 Add support for Qwen Image 2.1 2026-09-20 09:50:57 -06:00
Jaret Burkett 8fa15e3569 Move the ui model cards to their own plugin folders so plugins can add custom models in the trainer/generator/ui 2026-09-19 12:07:07 -06:00
Jaret Burkett a6e3b18e8a Added a notes section for jobs 2026-09-19 10:28:29 -06:00
Jaret Burkett cc98c3b690 Add ability to train with just music or vocals on yue2. Doesnt work as expected though 2026-09-17 20:19:32 -06:00
Jaret Burkett a9e7752178 Add MOSS music audio captioner 2026-09-17 10:45:37 -06:00
Jaret Burkett 080873bec9 Harden ace step transcription engine to detect and break out of loops. Add melbanroformer to seperate out the vocals and music for better transcriptions. Much better results. 2026-09-17 09:49:19 -06:00
Jaret Burkett 1db6083645 Show more information about LoRAs when loading loras in generate page 2026-09-17 09:35:43 -06:00
Jaret Burkett ef8110cef7 Add LoRA uploader to the lora picker on the generator 2026-09-17 05:17:34 -06:00
Jaret Burkett e65c4d0fb6 Fix issue with Krea2 patch size when training with shift 2026-09-16 13:46:39 -06:00
Jaret Burkett 410206e41c Improve speed of sage sheet decoder with yue2. Recover from tracks that fail 2026-09-16 12:24:39 -06:00
Jaret Burkett ce64e65c39 Add support for Qwen 2.5 Omni and add lora loading for captioning models 2026-09-16 10:36:19 -06:00
Jaret Burkett 2977672e4b Point omni vllm to real repo 2026-09-16 09:37:21 -06:00
Jaret Burkett db8dbd68c2 Add support for training VLLMs, omni models, and LLMs 2026-09-15 17:47:02 -06:00
Jaret Burkett 426ccb4ec4 fix file identifier parsing of some extensions that were not being recofnized in the ui 2026-09-15 12:59:54 -06:00
Jaret Burkett 6b2526a4d7 Allow Ace Step captioner to work with different output formats like yue2 2026-09-15 12:48:15 -06:00
Jaret Burkett 8bf12e476e Fixed issue that could allow deleting and uploading items outside the restricted directories. 2026-09-15 10:13:53 -06:00
Jaret Burkett 07de70940a Fix and optimize Ace Step captioner 2026-09-15 06:49:06 -06:00
Jaret Burkett 59c7de0539 Increase the repition penalty 2026-09-15 06:12:20 -06:00
Jaret Burkett f2a2a6bea0 Make audio files in dataset be thumbnails until clicked and opened inn the viewer 2026-09-15 05:32:13 -06:00
Jaret Burkett (Ostris) d673cc5205 Merge pull request #1042 from ostris/yue2
YuE2
2026-09-14 17:55:47 -06:00
Jaret Burkett 48d6f441cc Version bump 2026-09-14 17:50:36 -06:00
Jaret Burkett 213d32cad3 Train 50% of the time with and without sheet music. 2026-09-14 17:50:15 -06:00
Jaret Burkett f9b23b40bb Load sage sheet and use it on training with 50% dropout so it generates sheet music and handles without it. 2026-09-14 17:01:36 -06:00
Jaret Burkett 9ea4348d1e Normalize captions 2026-09-14 14:51:14 -06:00
Jaret Burkett 5ae240dd81 Update readme 2026-09-14 14:18:45 -06:00
Jaret Burkett b53436331c Add regularization and moden info 2026-09-14 14:14:36 -06:00
Jaret Burkett 900c0e8a67 Det the dataset dropout for yue2 2026-09-14 12:19:51 -06:00
Jaret Burkett 7bc91e91a5 Add yue2 caption options 2026-09-14 12:16:39 -06:00
Jaret Burkett 29635253cf Merge branch 'main' into yue2 2026-09-14 09:32:31 -06:00
Jaret Burkett 87f8090bb9 Force advanced editor to 2 spaces indentation 2026-09-14 09:04:30 -06:00
Jaret Burkett 1e8e9d5efe Allow to shift click samples and mass delete rows of samples 2026-09-14 08:55:07 -06:00
Jaret Burkett d44dffd7b8 Move the duration selector 2026-09-14 07:07:26 -06:00
Jaret Burkett f940e61dcd Merge branch 'main' into yue2 2026-09-14 05:21:25 -06:00
Jaret Burkett dd48f5572d Version bump 2026-09-14 05:08:00 -06:00