Dawn-Lcg b90cccdfb1 Fix: QwenImageEditPlusModel crashes with batch_size > 1 ...

Pass only the current sample's caption to encode_prompt, and right-pad
per-sample embeddings before concatenating.

2026-09-10 20:31:30 +08:00

..

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 offload and quantization to the base model

2026-08-28 08:37:56 -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

flux_kontext

Performance fixes and bug fixes

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

hidream

Fix quantization issues

2026-08-28 10:48:34 -06:00

ideogram4

Move the offload and quantization to the base model

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

krea2

Move the offload and quantization to the base model

2026-08-28 08:37:56 -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

minimax_h3

Migrate to a new DTO for latents to carry more information that a normal tensor such as audio.

2026-08-30 10:30:21 -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: QwenImageEditPlusModel crashes with batch_size > 1

2026-09-10 20:31:30 +08:00

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

Add initial support for Minimax H3 VSA sparse attention

2026-08-30 08:24:43 -06:00