Jaret Burkett d4ffbcad70 flux3: drop dead gate_type path, reject flow-map packages, note refreshed base checkpoint

2026-10-14 13:03:00 -06:00

..

anima

Move the offload and quantization to the base model

2026-08-28 08:37:56 -06:00

boogu_image

Move the offload and quantization to the base model

2026-08-28 08:37:56 -06:00

chroma

Performance fixes and bug fixes

2026-08-28 22:21:09 -06:00

ernie_image

Performance fixes and bug fixes

2026-08-28 22:21:09 -06:00

example_model

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

f_light

Performance fixes and bug fixes

2026-08-28 22:21:09 -06:00

flux2

Performance fixes and bug fixes

2026-08-28 22:21:09 -06:00

flux3

flux3: drop dead gate_type path, reject flow-map packages, note refreshed base checkpoint

2026-10-14 13:03:00 -06:00

flux_kontext

Performance fixes and bug fixes

2026-08-28 22:21:09 -06:00

hidream

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

ideogram4

Move the offload and quantization to the base model

2026-08-28 08:37:56 -06:00

iris3b

Add support for Iris-3B

2026-10-09 05:13:39 -06:00

krea2

Fix issue with Krea2 patch size when training with shift

2026-09-16 13:46:39 -06:00

ltx2

Fix issue where we gave the wrong dtype hidden states

2026-09-03 08:43:15 -06:00

mageflow

Move the offload and quantization to the base model

2026-08-28 08:37:56 -06:00

ming_image

Update ming image repo to new one

2026-09-24 08:40:16 -06:00

minimax_h3

Add support to train on Fast H3 v2 8 step directly with training adapter

2026-09-24 18:40:17 -06:00

nucleus_image

Performance fixes and bug fixes

2026-08-28 22:21:09 -06:00

omnigen2

Move the offload and quantization to the base model

2026-08-28 08:37:56 -06:00

prx_pixel_t2i

Move the offload and quantization to the base model

2026-08-28 08:37:56 -06:00

qwen_image

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

qwen_image_2

Add support for Qwen Image 2 Turbo with training adapter

2026-10-09 21:09:09 -06:00

wan22

Performance fixes and bug fixes

2026-08-28 22:21:09 -06:00

z_image

Stability improvements to model offloading. Added D-OPSD bleed loss as well.

2026-08-29 11:23:47 -06:00

zeta_chroma

Performance fixes and bug fixes

2026-08-28 22:21:09 -06:00

__init__.py

Merge in from main

2026-10-14 11:27:16 -06:00

ui.tsx

Merge in from main

2026-10-14 11:27:16 -06:00