comfyanonymous and GitHub
8d38ea3bbf
Fix bf16 precision issue with qwen image embeddings. ( #9441 )
2025-08-20 02:58:54 -04:00
comfyanonymous and GitHub
7cd2c4bd6a
Qwen rotary embeddings should now match reference code. ( #9437 )
2025-08-20 00:45:27 -04:00
comfyanonymous and GitHub
ed43784b0d
WIP Qwen edit model: The diffusion model part. ( #9383 )
2025-08-17 16:45:39 -04:00
comfyanonymous and GitHub
0f2b8525bc
Qwen image model refactor. ( #9375 )
2025-08-16 17:51:28 -04:00
comfyanonymous and GitHub
1702e6df16
Implement wan2.2 camera model. ( #9357 )
...
Use the old WanCameraImageToVideo node.
2025-08-15 17:29:58 -04:00
comfyanonymous and GitHub
c308a8840a
Add FluxKontextMultiReferenceLatentMethod node. ( #9356 )
...
This node is only useful if someone trains the kontext model to properly
use multiple reference images via the index method.
The default is the offset method which feeds the multiple images like if
they were stitched together as one. This method works with the current
flux kontext model.
2025-08-15 15:50:39 -04:00
comfyanonymous and GitHub
ad19a069f6
Make SLG nodes work on Qwen Image model. ( #9345 )
2025-08-14 23:16:01 -04:00
comfyanonymous and GitHub
9df8792d4b
Make last PR not crash comfy on old pytorch. ( #9324 )
2025-08-13 15:12:41 -04:00
contentis and GitHub
3da5a07510
SDPA backend priority ( #9299 )
2025-08-13 14:53:27 -04:00
comfyanonymous and GitHub
560d38f34c
Wan2.2 fun control support. ( #9292 )
2025-08-12 23:26:33 -04:00
comfyanonymous and GitHub
d044a24398
Fix default shift and any latent size for qwen image model. ( #9186 )
2025-08-05 06:12:27 -04:00
comfyanonymous and GitHub
c012400240
Initial support for qwen image model. ( #9179 )
2025-08-04 22:53:25 -04:00
comfyanonymous and GitHub
1e638a140b
Tiny wan vae optimizations. ( #9136 )
2025-08-01 05:25:38 -04:00
chaObserv and GitHub
61b08d4ba6
Replace manual x * sigmoid(x) with torch silu in VAE nonlinearity ( #9057 )
2025-07-30 19:25:56 -04:00
comfyanonymous and GitHub
da9dab7edd
Small wan camera memory optimization. ( #9111 )
2025-07-30 05:55:26 -04:00
comfyanonymous and GitHub
dca6bdd4fa
Make wan2.2 5B i2v take a lot less memory. ( #9102 )
2025-07-29 19:44:18 -04:00
comfyanonymous and GitHub
c60dc4177c
Remove unecessary clones in the wan2.2 VAE. ( #9083 )
2025-07-28 14:48:19 -04:00
comfyanonymous and GitHub
a88788dce6
Wan 2.2 support. ( #9080 )
2025-07-28 08:00:23 -04:00
comfyanonymous and GitHub
0621d73a9c
Remove useless code. ( #9059 )
2025-07-26 04:44:19 -04:00
comfyanonymous and GitHub
e6e5d33b35
Remove useless code. ( #9041 )
...
This is only needed on old pytorch 2.0 and older.
2025-07-25 04:58:28 -04:00
Harel Cain and GitHub
9bc2798f72
LTXV VAE decoder: switch default padding mode ( #8930 )
2025-07-16 13:54:38 -04:00
comfyanonymous and GitHub
938d3e8216
Remove windows line endings. ( #8866 )
2025-07-11 02:37:51 -04:00
josephrocca and GitHub
974254218a
Un-hardcode chroma patch_size ( #8840 )
2025-07-08 15:56:59 -04:00
comfyanonymous and GitHub
9093301a49
Don't add tiny bit of random noise when VAE encoding. ( #8705 )
...
Shouldn't change outputs but might make things a tiny bit more
deterministic.
2025-06-27 14:14:56 -04:00
comfyanonymous and GitHub
ef5266b1c1
Support Flux Kontext Dev model. ( #8679 )
2025-06-26 11:28:41 -04:00
comfyanonymous and GitHub
ec70ed6aea
Omnigen2 model implementation. ( #8669 )
2025-06-25 19:35:57 -04:00
comfyanonymous and GitHub
f7fb193712
Small flux optimization. ( #8611 )
2025-06-20 05:37:32 -04:00
comfyanonymous and GitHub
7e9267fa77
Make flux controlnet work with sd3 text enc. ( #8599 )
2025-06-19 18:50:05 -04:00
comfyanonymous and GitHub
91d40086db
Fix pytorch warning. ( #8593 )
2025-06-19 11:04:52 -04:00
comfyanonymous and GitHub
7ea79ebb9d
Add correct eps to ltxv rmsnorm. ( #8542 )
2025-06-15 12:21:25 -04:00
comfyanonymous and GitHub
29596bd53f
Small cosmos attention code refactor. ( #8530 )
2025-06-14 05:02:05 -04:00
Kohaku-Blueleaf and GitHub
520eb77b72
LoRA Trainer: LoRA training node in weight adapter scheme ( #8446 )
2025-06-13 19:25:59 -04:00
comfyanonymous and GitHub
c69af655aa
Uncap cosmos predict2 res and fix mem estimation. ( #8518 )
2025-06-13 07:30:18 -04:00
comfyanonymous and GitHub
251f54a2ad
Basic initial support for cosmos predict2 text to image 2B and 14B models. ( #8517 )
2025-06-13 07:05:23 -04:00
comfyanonymous and GitHub
8a4ff747bd
Fix mistake in last commit. ( #8496 )
...
* Move to right place.
2025-06-11 15:13:29 -04:00
comfyanonymous and GitHub
af1eb58be8
Fix black images on some flux models in fp16. ( #8495 )
2025-06-11 15:09:11 -04:00
comfyanonymous and GitHub
4248b1618f
Let chroma TE work on regular flux. ( #8429 )
2025-06-05 10:07:17 -04:00
drhead and GitHub
08b7cc7506
use fused multiply-add pointwise ops in chroma ( #8279 )
2025-05-30 18:09:54 -04:00
comfyanonymous and GitHub
5e5e46d40c
Not really tested WAN Phantom Support. ( #8321 )
2025-05-28 23:46:15 -04:00
comfyanonymous and GitHub
5a87757ef9
Better error if sageattention is installed but a dependency is missing. ( #8264 )
2025-05-24 06:43:12 -04:00
drhead and GitHub
30b2eb8a93
create arange on-device ( #8255 )
2025-05-23 16:15:06 -04:00
comfyanonymous and GitHub
f85c08df06
Make VACE conditionings stackable. ( #8240 )
2025-05-22 19:22:26 -04:00
comfyanonymous and GitHub
87f9130778
Revert "This doesn't seem to be needed on chroma. ( #8209 )" ( #8210 )
...
This reverts commit 7e84bf5373
2025-05-20 05:39:55 -04:00
comfyanonymous and GitHub
7e84bf5373
This doesn't seem to be needed on chroma. ( #8209 )
2025-05-20 05:29:23 -04:00
c820ef950d
Add Wan-FUN Camera Control models and Add WanCameraImageToVideo node ( #8013 )
...
* support wan camera models
* fix by ruff check
* change camera_condition type; make camera_condition optional
* support camera trajectory nodes
* fix camera direction
---------
Co-authored-by: Qirui Sun <sunqr0667@126.com >
2025-05-15 19:00:43 -04:00
comfyanonymous and GitHub
4a9014e201
Hunyuan Custom initial untested implementation. ( #8101 )
2025-05-13 15:53:47 -04:00
comfyanonymous and GitHub
640c47e7de
Fix torch warning about deprecated function. ( #8075 )
...
Drop support for torch versions below 2.2 on the audio VAEs.
2025-05-12 14:32:01 -04:00
blepping and GitHub
42da274717
Use normal ComfyUI attention in ACE-Steps model ( #8023 )
...
* Use normal ComfyUI attention in ACE-Steps model
* Let optimized_attention handle output reshape for ACE
2025-05-09 13:51:02 -04:00
comfyanonymous and GitHub
fd08e39588
Make torchaudio not a hard requirement. ( #7987 )
...
Some platforms can't install it apparently so if it's not there it should
only break models that actually use it.
2025-05-07 21:37:12 -04:00
comfyanonymous and GitHub
cc33cd3422
Experimental lyrics strength for ACE. ( #7984 )
2025-05-07 19:22:07 -04:00
