comfyanonymous
a834f992f0
Slightly better fix for #7687
2025-04-20 11:33:27 -04:00
comfyanonymous
da3d136cb7
Use empty t5 of size 128 for hidream, seems to give closer results.
2025-04-19 19:49:40 -04:00
power88
6f35198397
Hidream: Allow loading hidream text encoders in CLIPLoader and DualCLIPLoader ( #7676 )
...
* Hidream: Allow partial loading text encoders
* reformat code for ruff check.
2025-04-19 19:47:30 -04:00
comfyanonymous
da12bcd594
Fix hard crash when the spiece tokenizer path is bad.
2025-04-19 15:55:43 -04:00
comfyanonymous
b16e60eafd
Set default context_img_len to 257
2025-04-17 12:42:34 -04:00
comfyanonymous
9601e9e909
Support loading WAN FLF model.
2025-04-17 12:04:48 -04:00
comfyanonymous
89aec08623
Don't hardcode length of context_img in wan code.
2025-04-17 06:25:39 -04:00
comfyanonymous
7223e38263
Make hidream work with any latent resolution.
2025-04-16 18:34:14 -04:00
comfyanonymous
f26cf7d5fa
Limit T5 to 128 tokens for HiDream: #7620
2025-04-16 18:07:55 -04:00
comfyanonymous
5ea8378fc6
Reuse code from flux model.
2025-04-16 17:43:55 -04:00
Chenlei Hu
3bcade9e24
[Type] Mark input options NotRequired ( #7614 )
2025-04-16 15:41:00 -04:00
comfyanonymous
554e371cad
Fix issue on old torch.
2025-04-16 04:53:56 -04:00
comfyanonymous
720a954e00
Basic support for hidream i1 model.
2025-04-15 17:35:05 -04:00
comfyanonymous
921181d22b
Cleanup.
2025-04-15 12:13:28 -04:00
comfyanonymous
df67f25c28
More flexible long clip support.
...
Add clip g long clip support.
Text encoder refactor.
Support llama models with different vocab sizes.
2025-04-15 10:32:21 -04:00
comfyanonymous
04d5cdb6a2
add RMSNorm to comfy.ops
2025-04-14 18:00:33 -04:00
chaObserv
c4116ffaea
Add SEEDS (stage 2 & 3 DP) sampler ( #7580 )
...
* Add seeds stage 2 & 3 (DP) sampler
* Change the name to SEEDS in comment
2025-04-12 18:36:08 -04:00
catboxanon
2f65dfe6b0
Add CublasOps support ( #7574 )
...
* CublasOps support
* Guard CublasOps behind --fast arg
2025-04-12 18:29:15 -04:00
Chargeuk
1b28367616
Dependency Aware Node Caching for low RAM/VRAM machines ( #7509 )
...
* add dependency aware cache that removed a cached node as soon as all of its decendents have executed. This allows users with lower RAM to run workflows they would otherwise not be able to run. The downside is that every workflow will fully run each time even if no nodes have changed.
* remove test code
* tidy code
2025-04-11 06:55:51 -04:00
Chenlei Hu
a8fd307f35
Deprecate InputTypeOptions.defaultInput ( #7551 )
...
* Deprecate InputTypeOptions.defaultInput
* nit
* nit
2025-04-10 06:57:06 -04:00
Jedrzej Kosinski
6227fc9edf
Add prepare_sampling wrapper allowing custom nodes to more accurately report noise_shape ( #7500 )
2025-04-09 09:43:35 -04:00
comfyanonymous
f23079e949
Support the wan fun reward loras.
2025-04-07 05:01:47 -04:00
comfyanonymous
2f866528dc
Support 512 siglip model.
2025-04-05 07:01:01 -04:00
Raphael Walker
3b53953e66
Add activations_shape info in UNet models ( #7482 )
...
* Add activations_shape info in UNet models
* activations_shape should be a list
2025-04-04 21:27:54 -04:00
comfyanonymous
522761c65d
Disable partial offloading of audio VAE.
2025-04-04 21:24:56 -04:00
BiologicalExplosion
933ba105ff
MLU memory optimization ( #7470 )
...
Co-authored-by: huzhan <huzhan@cambricon.com>
2025-04-02 19:24:04 -04:00
BVH
d7ab5c10ce
Add option to store TE in bf16 ( #7461 )
2025-04-01 13:48:53 -04:00
comfyanonymous
c32dd8bce5
Remove useless code.
2025-03-29 20:12:56 -04:00
comfyanonymous
beab5d686d
Don't error if wan concat image has extra channels.
2025-03-28 08:49:29 -04:00
comfyanonymous
85a32a621d
Add WanFunInpaintToVideo node for the Wan fun inpaint models.
2025-03-27 11:13:27 -04:00
comfyanonymous
368daba9c7
Support the WAN 2.1 fun control models.
...
Use the new WanFunControlToVideo node.
2025-03-26 19:54:54 -04:00
comfyanonymous
0097c4d380
Support more float8 types.
2025-03-25 05:23:49 -04:00
comfyanonymous
f12158c8b0
Fallback to pytorch attention if sage attention fails.
2025-03-22 15:45:56 -04:00
comfyanonymous
07e9574b4b
Automatically set the right sampling type for lotus.
2025-03-21 14:19:37 -04:00
thot experiment
337c6bcd15
Native LotusD Implementation ( #7125 )
...
* draft pass at a native comfy implementation of Lotus-D depth and normal est
* fix model_sampling kludges
* fix ruff
---------
Co-authored-by: comfyanonymous <121283862+comfyanonymous@users.noreply.github.com>
2025-03-21 14:04:15 -04:00
comfyanonymous
5100ca7361
A few fixes for the hunyuan3d models.
2025-03-20 04:52:31 -04:00
comfyanonymous
a3c96c7cf6
Fix orientation of hunyuan 3d model.
2025-03-19 19:55:24 -04:00
comfyanonymous
2f17e6734c
Initial Hunyuan3Dv2 implementation.
...
Supports the multiview, mini, turbo models and VAEs.
2025-03-19 16:52:58 -04:00
comfyanonymous
35324c6a52
Allow disabling pe in flux code for some other models.
2025-03-18 05:09:25 -04:00
comfyanonymous
fd7a7c66e8
Fix regression with clip vision.
2025-03-17 13:56:11 -04:00
comfyanonymous
69c6ac42da
Add support for giant dinov2 image encoder.
2025-03-17 05:53:54 -04:00
comfyanonymous
7761e410ec
Cleanup code.
2025-03-16 06:29:12 -04:00
Jedrzej Kosinski
b7246311db
Call unpatch_hooks at the start of ModelPatcher.partially_unload ( #7253 )
...
* Call unpatch_hooks at the start of ModelPatcher.partially_unload
* Only call unpatch_hooks in partially_unload if lowvram is possible
2025-03-16 06:02:45 -04:00
chaObserv
193e847c21
Guard the edge cases of noise term in er_sde ( #7265 )
2025-03-16 06:02:25 -04:00
comfyanonymous
83d3e0cce5
Allow loading diffusion model files with the "Load Checkpoint" node.
2025-03-15 08:27:49 -04:00
comfyanonymous
3f02ca182d
Show a better error message if the VAE is invalid.
2025-03-15 08:26:36 -04:00
comfyanonymous
46c332a93f
Remove useless code.
2025-03-14 18:10:37 -04:00
comfyanonymous
95649bd3bb
Make the SkipLayerGuidanceDIT node work on WAN.
2025-03-14 10:55:19 -04:00
FeepingCreature
1434c8d833
Tolerate missing @torch.library.custom_op ( #7234 )
...
This can happen on Pytorch versions older than 2.4.
2025-03-14 09:51:26 -04:00
FeepingCreature
d466fbcae5
Add --use-flash-attention flag. ( #7223 )
...
* Add --use-flash-attention flag.
This is useful on AMD systems, as FA builds are still 10% faster than Pytorch cross-attention.
2025-03-14 03:22:41 -04:00
