patientx
3ca065a755
fix
2025-09-05 23:11:57 +03:00
patientx
0488fe3748
rmsnorm patch second try
2025-09-05 23:10:27 +03:00
patientx
8966009181
added rmsnorm patch for torch's older than 2.4
2025-09-05 22:43:39 +03:00
patientx
f9d7fcb696
Merge branch 'comfyanonymous:master' into master
2025-09-05 22:09:30 +03:00
comfyanonymous
2ee7879a0b
Fix lowvram issues with hunyuan3d 2.1 ( #9735 )
2025-09-05 14:57:35 -04:00
patientx
c7c7269f48
Merge branch 'comfyanonymous:master' into master
2025-09-05 17:11:07 +03:00
comfyanonymous
c9ebe70072
Some changes to the previous hunyuan PR. ( #9725 )
2025-09-04 20:39:02 -04:00
Yousef R. Gamaleldin
261421e218
Add Hunyuan 3D 2.1 Support ( #8714 )
2025-09-04 20:36:20 -04:00
patientx
d79e93a0a9
Merge branch 'comfyanonymous:master' into master
2025-09-04 12:41:48 +03:00
comfyanonymous
72855db715
Fix potential rope issue. ( #9710 )
2025-09-03 22:20:13 -04:00
patientx
991209d11d
Merge branch 'comfyanonymous:master' into master
2025-09-03 00:05:33 +03:00
comfyanonymous
e3018c2a5a
uso -> uxo/uno as requested. ( #9688 )
2025-09-02 16:12:07 -04:00
patientx
b30a38dca0
Merge branch 'comfyanonymous:master' into master
2025-09-02 22:46:44 +03:00
comfyanonymous
3412d53b1d
USO style reference. ( #9677 )
...
Load the projector.safetensors file with the ModelPatchLoader node and use
the siglip_vision_patch14_384.safetensors "clip vision" model and the
USOStyleReferenceNode.
2025-09-02 15:36:22 -04:00
patientx
47c6fb34c9
Merge branch 'comfyanonymous:master' into master
2025-09-02 09:46:42 +03:00
contentis
e2d1e5dad9
Enable Convolution AutoTuning ( #9301 )
2025-09-01 20:33:50 -04:00
comfyanonymous
27e067ce50
Implement the USO subject identity lora. ( #9674 )
...
Use the lora with FluxContextMultiReferenceLatentMethod node set to "uso"
and a ReferenceLatent node with the reference image.
2025-09-01 18:54:02 -04:00
patientx
9cb469282e
Merge branch 'comfyanonymous:master' into master
2025-08-31 11:24:57 +03:00
chaObserv
32a627bf1f
SEEDS: update noise decomposition and refactor ( #9633 )
...
- Update the decomposition to reflect interval dependency
- Extract phi computations into functions
- Use torch.lerp for interpolation
2025-08-31 00:01:45 -04:00
patientx
c6b0bf480f
Merge branch 'comfyanonymous:master' into master
2025-08-29 09:31:05 +03:00
comfyanonymous
e80a14ad50
Support wan2.2 5B fun control model. ( #9611 )
...
Use the Wan22FunControlToVideo node.
2025-08-28 22:13:07 -04:00
patientx
c8af694267
Merge pull request #279 from sfinktah/sfink-cudnn-benchmark
...
Added env_var for cudnn.benchmark
2025-08-28 23:17:05 +03:00
patientx
1db0a73a2a
Merge branch 'comfyanonymous:master' into master
2025-08-28 09:06:22 +03:00
comfyanonymous
4aa79dbf2c
Adjust flux mem usage factor a bit. ( #9588 )
2025-08-27 23:08:17 -04:00
patientx
fc93a6f534
Merge branch 'comfyanonymous:master' into master
2025-08-28 02:22:15 +03:00
Gangin Park
3aad339b63
Add DPM++ 2M SDE Heun (RES) sampler ( #9542 )
2025-08-27 19:07:31 -04:00
comfyanonymous
491755325c
Better s2v memory estimation. ( #9584 )
2025-08-27 19:02:42 -04:00
Christopher Anderson
cf22cbd8d5
Added env_var for cudnn.benchmark
2025-08-28 09:00:08 +10:00
comfyanonymous
496888fd68
Improve s2v performance when generating videos longer than 120 frames. ( #9582 )
2025-08-27 16:06:40 -04:00
comfyanonymous
b5ac6ed7ce
Fixes to make controlnet type models work on qwen edit and kontext. ( #9581 )
2025-08-27 15:26:28 -04:00
Kohaku-Blueleaf
b20ba1f27c
Fix #9537 ( #9576 )
2025-08-27 12:45:02 -04:00
patientx
eeab23fc0b
Merge branch 'comfyanonymous:master' into master
2025-08-27 10:07:57 +03:00
comfyanonymous
88aee596a3
WIP Wan 2.2 S2V model. ( #9568 )
2025-08-27 01:10:34 -04:00
patientx
c1aef0126d
Merge pull request #276 from sfinktah/sfink-cudnn-benchmark-env
...
Deleted torch.backends.cudnn.benchmark line, defaults are fine
2025-08-26 19:34:35 +03:00
patientx
1efeba7066
Merge branch 'comfyanonymous:master' into master
2025-08-26 10:41:38 +03:00
comfyanonymous
914c2a2973
Implement wav2vec2 as an audio encoder model. ( #9549 )
...
This is useless on its own but there are multiple models that use it.
2025-08-25 23:26:47 -04:00
Christopher Anderson
110cb0a9d9
Deleted torch.backends.cudnn.benchmark line, defaults are fine
2025-08-26 08:43:31 +10:00
Christopher Anderson
1b9a3b12c2
had to move cudnn disablement up much higher
2025-08-25 14:11:54 +10:00
Christopher Anderson
cd3d60254b
argggh, white space hell
2025-08-25 09:52:58 +10:00
Christopher Anderson
184fa5921f
worst PR ever, really.
2025-08-25 09:42:27 +10:00
Christopher Anderson
33c43b68c3
worst PR ever
2025-08-25 09:38:22 +10:00
Christopher Anderson
2a06dc8e87
Merge remote-tracking branch 'origin/sfink-cudnn-env' into sfink-cudnn-env
...
# Conflicts:
# comfy/customzluda/zluda.py
2025-08-25 09:34:32 +10:00
Christopher Anderson
3504eeeb4a
rebased onto upstream master (woops)
2025-08-25 09:32:34 +10:00
Christopher Anderson
7eda4587be
Added env var TORCH_BACKENDS_CUDNN_ENABLED, defaults to 1.
2025-08-25 09:31:12 +10:00
Christopher Anderson
954644ef83
Added env var TORCH_BACKENDS_CUDNN_ENABLED, defaults to 1.
2025-08-25 08:56:48 +10:00
Rando717
053a6b95e5
Update zluda.py (MEM_BUS_WIDTH)
...
Added more cards, mostly RDNA(1) and Radeon Pro.
Reasoning: Every time zluda.py gets update I have to manually add 256 for my RX 5700, otherwise it default to 128. Also, manual local edits fails at git pull.
2025-08-24 18:39:40 +02:00
patientx
c92a07594b
Update zluda.py
2025-08-24 12:01:20 +03:00
patientx
dba9d20791
Update zluda.py
2025-08-24 10:23:30 +03:00
patientx
cdc04b5a8a
Merge branch 'comfyanonymous:master' into master
2025-08-23 07:47:07 +03:00
comfyanonymous
41048c69b4
Fix Conditioning masks on 3d latents. ( #9506 )
2025-08-22 23:15:44 -04:00
