8be711715c
Make unload_all_models account for all devices
2025-04-19 17:35:54 -05:00
b5cccf1325
Merge branch 'master' into worksplit-multigpu
2025-04-18 15:39:34 -05:00
dbcfd092a2
Set default context_img_len to 257
2025-04-17 12:42:34 -04:00
c14429940f
Support loading WAN FLF model.
2025-04-17 12:04:48 -04:00
0d720e4367
Don't hardcode length of context_img in wan code.
2025-04-17 06:25:39 -04:00
2a54a904f4
Merge branch 'master' into worksplit-multigpu
2025-04-16 19:26:48 -05:00
1fc00ba4b6
Make hidream work with any latent resolution.
2025-04-16 18:34:14 -04:00
9899d187b1
Limit T5 to 128 tokens for HiDream: #7620
2025-04-16 18:07:55 -04:00
ed6f92c975
Merge branch 'master' into worksplit-multigpu
2025-04-16 16:53:57 -05:00
f00f340a56
Reuse code from flux model.
2025-04-16 17:43:55 -04:00
cce1d9145e
[Type] Mark input options NotRequired ( #7614 )
2025-04-16 15:41:00 -04:00
adc66c0698
Merge branch 'master' into worksplit-multigpu
2025-04-16 14:23:56 -05:00
b4dc03ad76
Fix issue on old torch.
2025-04-16 04:53:56 -04:00
9ad792f927
Basic support for hidream i1 model.
2025-04-15 17:35:05 -04:00
6fc5dbd52a
Cleanup.
2025-04-15 12:13:28 -04:00
3e8155f7a3
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
8a438115fb
add RMSNorm to comfy.ops
2025-04-14 18:00:33 -04:00
e51d9ba5fc
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
1714a4c158
Add CublasOps support ( #7574 )
...
* CublasOps support
* Guard CublasOps behind --fast arg
2025-04-12 18:29:15 -04:00
ed945a1790
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
98bdca4cb2
Deprecate InputTypeOptions.defaultInput ( #7551 )
...
* Deprecate InputTypeOptions.defaultInput
* nit
* nit
2025-04-10 06:57:06 -04:00
ccd5c01e5a
Merge branch 'master' into worksplit-multigpu
2025-04-09 09:17:12 -05:00
e346d8584e
Add prepare_sampling wrapper allowing custom nodes to more accurately report noise_shape ( #7500 )
2025-04-09 09:43:35 -04:00
2fa9affcc1
Merge branch 'master' into worksplit-multigpu
2025-04-08 22:52:17 -05:00
70d7242e57
Support the wan fun reward loras.
2025-04-07 05:01:47 -04:00
3bfe4e5276
Support 512 siglip model.
2025-04-05 07:01:01 -04:00
89e4ea0175
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
3a100b9a55
Disable partial offloading of audio VAE.
2025-04-04 21:24:56 -04:00
2222cf67fd
MLU memory optimization ( #7470 )
...
Co-authored-by: huzhan <huzhan@cambricon.com>
2025-04-02 19:24:04 -04:00
301e26b131
Add option to store TE in bf16 ( #7461 )
2025-04-01 13:48:53 -04:00
a3100c8452
Remove useless code.
2025-03-29 20:12:56 -04:00
2d17d8910c
Don't error if wan concat image has extra channels.
2025-03-28 08:49:29 -04:00
407a5a656f
Rollback core of last commit due to weird behavior
2025-03-28 02:48:11 -05:00
9ce9ff8ef8
Allow chained MultiGPU Work Unit nodes to affect max_gpus present on ModelPatcher clone
2025-03-28 15:29:44 +08:00
63567c0ce8
Merge branch 'master' into worksplit-multigpu
2025-03-27 22:36:46 -05:00
0a1f8869c9
Add WanFunInpaintToVideo node for the Wan fun inpaint models.
2025-03-27 11:13:27 -04:00
a786ce5ead
Merge branch 'master' into worksplit-multigpu
2025-03-26 22:26:26 -05:00
3661c833bc
Support the WAN 2.1 fun control models.
...
Use the new WanFunControlToVideo node.
2025-03-26 19:54:54 -04:00
8edc1f44c1
Support more float8 types.
2025-03-25 05:23:49 -04:00
e471c726e5
Fallback to pytorch attention if sage attention fails.
2025-03-22 15:45:56 -04:00
d9fa9d307f
Automatically set the right sampling type for lotus.
2025-03-21 14:19:37 -04:00
83e839a89b
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
3872b43d4b
A few fixes for the hunyuan3d models.
2025-03-20 04:52:31 -04:00
32ca0805b7
Fix orientation of hunyuan 3d model.
2025-03-19 19:55:24 -04:00
11f1b41bab
Initial Hunyuan3Dv2 implementation.
...
Supports the multiview, mini, turbo models and VAEs.
2025-03-19 16:52:58 -04:00
4879b47648
Merge branch 'master' into worksplit-multigpu
2025-03-18 22:19:32 -05:00
3b19fc76e3
Allow disabling pe in flux code for some other models.
2025-03-18 05:09:25 -04:00
219d3cd0d0
Merge branch 'master' into worksplit-multigpu
2025-03-17 14:26:35 -05:00
50614f1b79
Fix regression with clip vision.
2025-03-17 13:56:11 -04:00
6dc7b0bfe3
Add support for giant dinov2 image encoder.
2025-03-17 05:53:54 -04:00
Jedrzej Kosinski
comfyanonymous
Chenlei Hu
chaObserv
catboxanon
Chargeuk
Raphael Walker
BiologicalExplosion
BVH
thot experiment