Kohaku-Blueleaf cdcf4119b3 [Trainer] training with proper offloading (#12189) ...

* Fix bypass dtype/device moving

* Force offloading mode for training

* training context var

* offloading implementation in training node

* fix wrong input type

* Support bypass load lora model, correct adapter/offloading handling

2026-02-10 21:45:19 -05:00

..

ace

Make ace step 1.5 base model work properly with default workflow. (#12337)

2026-02-06 19:14:56 -05:00

anima

Support the Anima model. (#12012)

2026-01-21 19:44:28 -05:00

audio

Enable Runtime Selection of Attention Functions (#9639)

2025-09-12 18:07:38 -04:00

aura

Enable Runtime Selection of Attention Functions (#9639)

2025-09-12 18:07:38 -04:00

cascade

Enable Runtime Selection of Attention Functions (#9639)

2025-09-12 18:07:38 -04:00

chroma

Implement the Ovis image model. (#11030)

2025-12-01 20:56:17 -05:00

chroma_radiance

New Year ruff cleanup. (#11595)

2026-01-01 22:06:14 -05:00

cosmos

Some fixes to previous pr. (#12339)

2026-02-06 20:14:52 -05:00

flux

[Trainer] training with proper offloading (#12189)

2026-02-10 21:45:19 -05:00

genmo

Enable Runtime Selection of Attention Functions (#9639)

2025-09-12 18:07:38 -04:00

hidream

Enable Runtime Selection of Attention Functions (#9639)

2025-09-12 18:07:38 -04:00

hunyuan3d

Enable Runtime Selection of Attention Functions (#9639)

2025-09-12 18:07:38 -04:00

hunyuan3dv2_1

Fix issue on old torch. (#9791)

2025-09-10 00:23:47 -04:00

hunyuan_video

Reduce RAM usage, fix VRAM OOMs, and fix Windows shared memory spilling with adaptive model loading (#11845)

2026-02-01 01:01:11 -05:00

hydit

Change cosmos and hydit models to use the native RMSNorm. (#7934)

2025-05-04 06:26:20 -04:00

kandinsky5

Fix qwen scaled fp8 not working with kandinsky. Make basic t2i wf work. (#11162)

2025-12-06 17:50:10 -08:00

lightricks

LTX2: Refactor forward function for better VRAM efficiency and fix spatial inpainting (#12046)

2026-01-23 15:26:38 -05:00

lumina

Only enable fp16 on z image models that actually support it. (#12065)

2026-01-24 22:32:28 -05:00

mmaudio/vae

Implement the mmaudio VAE. (#10300)

2025-10-11 22:57:23 -04:00

models

Flux 2 (#10879)

2025-11-25 10:50:19 -05:00

modules

Disable sage attention on ace step 1.5 (#12297)

2026-02-04 22:15:30 -05:00

omnigen

Enable Runtime Selection of Attention Functions (#9639)

2025-09-12 18:07:38 -04:00

pixart

Remove windows line endings. (#8866)

2025-07-11 02:37:51 -04:00

qwen_image

qwen_image: propagate attention mask. (#11966)

2026-01-22 20:02:31 -05:00

wan

wan-vae: Switch off feature cache for single frame (#12090)

2026-01-26 19:40:19 -05:00

common_dit.py

add RMSNorm to comfy.ops

2025-04-14 18:00:33 -04:00

util.py

New Year ruff cleanup. (#11595)

2026-01-01 22:06:14 -05:00