Jaret Burkett 259d68d440 Added a flushg during sampling to prevent spikes on low vram qwen

2025-08-12 12:57:18 -06:00

..

chroma

Fix issue with the way chroma handled gradient checkpointing.

2025-05-28 08:41:47 -06:00

f_light

Added initial support for f-lite model

2025-05-01 11:15:18 -06:00

flux_kontext

fix: Guidance incorrect shape

2025-07-18 12:49:18 +02:00

hidream

Added initial support for Hidream E1 training

2025-07-27 15:12:56 -06:00

omnigen2

Allow control image for omnigen training and sampling

2025-07-09 13:54:55 -06:00

qwen_image

Added a flushg during sampling to prevent spikes on low vram qwen

2025-08-12 12:57:18 -06:00

wan22

Refactor qwen5b model code to be qwen 5b specific

2025-08-06 10:54:56 -06:00

__init__.py

Refactor qwen5b model code to be qwen 5b specific

2025-08-06 10:54:56 -06:00