5c295fd9c6
Merge branch 'master' into minimax-h3-latent-noise-masks
2026-08-13 14:44:53 -06:00
e01fb4c56b
Add MiniMaxH3AddGuide for anchoring image and audio guides at any frame ( #15439 )
2026-08-13 15:55:36 -04:00
62b3c94bd4
Fix peak memory issue with H3. ( #15486 )
2026-08-11 02:09:29 -07:00
bf4c9a08fc
Implement comfy kitchen attention. ( #15479 )
...
Add a ModelAttentionBackend node to manually select the attention for models in the workflows. Currently supports pytorch attention or comfy kitchen attention.
Add --use-ck-attention to enable comfy kitchen attention as the default attention backend for all models (might break some).
2026-08-10 22:03:08 -07:00
28aa924e81
Allow fractional mask values for MiniMax-H3
2026-08-08 16:38:13 -06:00
877b5b8862
Merge branch 'master' into minimax-h3-latent-noise-masks
2026-08-07 14:30:07 -04:00
93cb5edb98
Fix audio carry to wrappers ( #15390 )
2026-08-07 08:30:21 -07:00
3c4749976b
Support per-token video and audio latent noise masks on MiniMax-H3
...
Video masks snap to the 2x2 latent patch grid, audio masks to whole
latent frames, both rounded to binary.
2026-08-06 16:22:29 -06:00
bdcb886a47
Fix sampler issues for audio with minimax, support more samplers. ( #15243 )
2026-08-06 13:36:34 -07:00
57500fc5bc
feat: Support MiniMax-H3 (CORE-375) ( #15224 )
2026-08-02 22:28:29 -04:00
drozbay
comfyanonymous
Jukka Seppänen