d197549522
Merge remote-tracking branch 'upstream/master' into pixal3d
2026-08-13 23:42:48 +03:00
e01fb4c56b
Add MiniMaxH3AddGuide for anchoring image and audio guides at any frame ( #15439 )
2026-08-13 15:55:36 -04:00
ddbaa87528
minimax: early detect qkv vs q,k,v ( #15581 )
...
avoid a commit charge surge on non-dynamic windows due to double linear
creation.
2026-08-13 13:08:08 -04:00
efd4e951a0
Implement Minimax Music 3 + Core Support for Cuda Graphs ( #15570 )
2026-08-13 12:10:08 -04:00
bd34f338ac
Fix float64 device in ltx diffusion decoder. ( #15516 )
2026-08-12 03:55:08 -04:00
57ce8e1a27
Add support for LTX 2.5 ( #15499 )
...
---------
Co-authored-by: kijai <40791699+kijai@users.noreply.github.com>
2026-08-11 13:47:39 -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
2a68ce33b4
Optimize MiniMax-H3 VAE ( #15446 )
2026-08-09 14:24:48 -04:00
93cb5edb98
Fix audio carry to wrappers ( #15390 )
2026-08-07 08:30:21 -07:00
2340099d93
Fix full offload on minimax audio vae. ( #15377 )
2026-08-07 00:26:16 -04:00
a464ac3358
feat: Support Wan-Animate2 (CORE-358) ( #15362 )
2026-08-06 21:08:16 -04:00
bdcb886a47
Fix sampler issues for audio with minimax, support more samplers. ( #15243 )
2026-08-06 13:36:34 -07:00
15989f87ca
Speedup LTX and Wan ( #15138 )
2026-08-05 21:15:48 -04:00
bbda83647d
Support int8_convrot VAE ( #15334 )
2026-08-05 21:12:23 -04:00
16e3f3034f
fix(minimax): cast raw parameters to input device in H3 VAEs ( #15268 )
2026-08-03 19:06:12 -04:00
57500fc5bc
feat: Support MiniMax-H3 (CORE-375) ( #15224 )
2026-08-02 22:28:29 -04:00
a1c421994c
Expand k, v when attention backend would fall back to math because gqa. ( #15190 )
2026-07-31 15:17:56 -07:00
87e34c5c17
Merge remote-tracking branch 'upstream/master' into pixal3d
2026-07-30 13:42:56 +03:00
e651b7bef5
Fix LTXAV crash when sampling without an audio latent ( #15132 )
2026-07-28 20:24:08 -07:00
c38171ddb9
Support Pruna LTX VAE ( #15129 )
2026-07-28 18:25:55 -04:00
a3572c4832
Allow using float fps for LTXVEmptyLatentAudio ( #15106 )
2026-07-27 13:04:14 -07:00
806e092ed4
Fix MageFlow on cards that don't support bf16 ( #15081 )
2026-07-25 21:01:51 -04:00
f966a2b38c
Optimize ideogram model using comfy kitchen rms rope. ( #15080 )
2026-07-25 15:09:26 -04:00
45ffd5430b
feat: Support MageFlow (CORE-372) ( #15026 )
2026-07-24 23:14:01 -04:00
f8a3fd9d79
upscalers: convert latent_upsampler model to DynamicVram ( #15063 )
...
These were alll non-dynamic (some non-ModelPatcher) code path calling
FreeMemory for management requiring up-front memory freeing. Convert it
to dynamic to avoid legacy free behaviour mixing into otherwise
dynamic workflows.
2026-07-24 13:34:40 -07:00
7c59a078d6
Use comfy kitchen rope functions in ltx models. ( #15056 )
2026-07-24 15:17:31 -04:00
0cb84e7e6e
Make Ernie use comfy kitchen rms rope ( #15055 )
2026-07-23 22:06:52 -04:00
2e47082c8e
Make z image/lumina 2 models use comfy kitchen rms rope. ( #15036 )
2026-07-22 15:34:27 -04:00
947c2749dd
Use optimized rms_rope function in joyai image model. ( #15018 )
2026-07-21 20:02:45 -07:00
ac3a7a654f
Add native Uni3C Controlnet support for Wan models (CORE-365) ( #14946 )
...
* Add native Uni3C controlnet support for Wan models
* Dispatch double_block patches in all Wan model variants
* Remove unused grid_sizes assignment in CameraWanModel, WanModel_S2V, HumoWanModel, and AnimateWanModel
2026-07-21 15:44:14 +03:00
36feff8863
Smaller fixes and adjustments
2026-07-20 16:52:30 +03:00
b7c6a61515
Merge branch 'master' into pixal3d
2026-07-19 22:42:12 +02:00
c9602625e4
Implement regular and timestep zero reference images to krea 2 for ostris and identity edit ref loras. ( #14843 )
2026-07-18 17:12:18 -07:00
0f42ba5146
Support anima lllite control models. ( #14954 )
...
Put them in the models/model_patches folder. Use the new AnimaLLLiteApply node.
2026-07-17 07:36:21 -07:00
550af28f45
Merge branch 'master' into pixal3d
...
# Conflicts:
# comfy/sd.py
# comfy_extras/nodes_save_3d.py
2026-07-17 14:24:51 +03:00
71b73e3b2b
Speed up anima a bit. ( #14953 )
2026-07-16 19:44:02 -07:00
03978e1e81
[feat]Add JoyImageEdit native model support ( #14428 )
2026-07-15 23:48:28 -04:00
c35a622acd
Fix hidream o1 regression. ( #14923 )
2026-07-13 12:52:28 -07:00
917faef771
Support PID 1.5 models. ( #14894 )
2026-07-12 09:43:30 -07:00
69ea58697b
Try to fix flash attention related issue on AMD. ( #14880 )
2026-07-11 17:16:40 -07:00
92ddf07ba1
Try to fix some issues with the seedvr VAE. ( #14877 )
2026-07-10 19:54:28 -04:00
8e2e54e2b8
Add SeedVR2 support (CORE-6) ( #14424 )
2026-07-10 15:07:42 +08:00
b481bc15af
Support gqa on all attention backends, drop support for pytorch 2.4 ( #14772 )
2026-07-07 22:57:52 -04:00
d635cc412d
Miscellanous cleanup
2026-07-02 16:34:16 +03:00
2bbf53e8fc
Linting
2026-07-01 21:21:11 +03:00
f3c8db510f
Refactor NAF model usage
2026-07-01 01:36:14 +03:00
eec0692bcb
Cleanup model code
2026-07-01 00:25:01 +03:00
3aae4bf741
Optimize NAF memory use
2026-06-30 21:47:43 +03:00
1f7acd9354
Optimize VAE
2026-06-27 00:06:19 +03:00
kijai
Barish Ozbay
rattus
comfyanonymous
Alexis Rolland
rivadart
kijai
彼彼
John Pollock