comfyanonymous ed43784b0d WIP Qwen edit model: The diffusion model part. (#9383)		2025-08-17 16:45:39 -04:00
..
ace	Fix torch warning about deprecated function. (#8075)	2025-05-12 14:32:01 -04:00
audio	Fix torch warning about deprecated function. (#8075)	2025-05-12 14:32:01 -04:00
aura
cascade
chroma	Un-hardcode chroma patch_size (#8840)	2025-07-08 15:56:59 -04:00
cosmos	Replace manual x * sigmoid(x) with torch silu in VAE nonlinearity (#9057)	2025-07-30 19:25:56 -04:00
flux	Add FluxKontextMultiReferenceLatentMethod node. (#9356)	2025-08-15 15:50:39 -04:00
genmo
hidream
hunyuan3d	Make last PR not crash comfy on old pytorch. (#9324)	2025-08-13 15:12:41 -04:00
hunyuan_video	Hunyuan Custom initial untested implementation. (#8101)	2025-05-13 15:53:47 -04:00
hydit
lightricks	LTXV VAE decoder: switch default padding mode (#8930)	2025-07-16 13:54:38 -04:00
lumina	Change lumina to native RMSNorm. (#7935)	2025-05-04 06:39:23 -04:00
models	Don't add tiny bit of random noise when VAE encoding. (#8705)	2025-06-27 14:14:56 -04:00
modules	Make last PR not crash comfy on old pytorch. (#9324)	2025-08-13 15:12:41 -04:00
omnigen	Omnigen2 model implementation. (#8669)	2025-06-25 19:35:57 -04:00
pixart	Remove windows line endings. (#8866)	2025-07-11 02:37:51 -04:00
qwen_image	WIP Qwen edit model: The diffusion model part. (#9383)	2025-08-17 16:45:39 -04:00
wan	Implement wan2.2 camera model. (#9357)	2025-08-15 17:29:58 -04:00
common_dit.py
util.py