Silver
ea9c851501
Merge branch 'master' into chroma-support
2025-04-20 22:08:13 +02:00
comfyanonymous
2c735c13b4
Slightly better fix for #7687
2025-04-20 11:33:27 -04:00
comfyanonymous
fd27494441
Use empty t5 of size 128 for hidream, seems to give closer results.
2025-04-19 19:49:40 -04:00
power88
f43e1d7f41
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
636d4bfb89
Fix hard crash when the spiece tokenizer path is bad.
2025-04-19 15:55:43 -04:00
silveroxides
a9f208ddce
sync chroma-support with upstream via syncbranch patch
2025-04-18 13:29:09 +02:00
comfyanonymous
dbcfd092a2
Set default context_img_len to 257
2025-04-17 12:42:34 -04:00
comfyanonymous
c14429940f
Support loading WAN FLF model.
2025-04-17 12:04:48 -04:00
comfyanonymous
0d720e4367
Don't hardcode length of context_img in wan code.
2025-04-17 06:25:39 -04:00
Silver
7e98854b14
Merge branch 'comfyanonymous:master' into chroma-support
2025-04-17 11:09:24 +02:00
comfyanonymous
1fc00ba4b6
Make hidream work with any latent resolution.
2025-04-16 18:34:14 -04:00
comfyanonymous
9899d187b1
Limit T5 to 128 tokens for HiDream: #7620
2025-04-16 18:07:55 -04:00
comfyanonymous
f00f340a56
Reuse code from flux model.
2025-04-16 17:43:55 -04:00
Chenlei Hu
cce1d9145e
[Type] Mark input options NotRequired ( #7614 )
2025-04-16 15:41:00 -04:00
silveroxides
c791e957a6
refactor for upstream sync
2025-04-16 15:58:37 +02:00
comfyanonymous
b4dc03ad76
Fix issue on old torch.
2025-04-16 04:53:56 -04:00
comfyanonymous
9ad792f927
Basic support for hidream i1 model.
2025-04-15 17:35:05 -04:00
comfyanonymous
6fc5dbd52a
Cleanup.
2025-04-15 12:13:28 -04:00
comfyanonymous
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
comfyanonymous
8a438115fb
add RMSNorm to comfy.ops
2025-04-14 18:00:33 -04:00
Silver
7b39ea680a
Merge branch 'comfyanonymous:master' into chroma-support
2025-04-13 03:08:02 +02:00
chaObserv
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
catboxanon
1714a4c158
Add CublasOps support ( #7574 )
...
* CublasOps support
* Guard CublasOps behind --fast arg
2025-04-12 18:29:15 -04:00
silveroxides
cd3d2d5c62
remove unused imports
2025-04-11 16:22:04 +02:00
silveroxides
2c2481955d
reduce code duplication
2025-04-11 16:18:57 +02:00
Silver
fc978a7ad8
Merge branch 'comfyanonymous:master' into chroma-support
2025-04-11 13:07:36 +02:00
Chargeuk
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
Silver
1c76711441
Merge branch 'comfyanonymous:master' into chroma-support
2025-04-10 18:16:10 +02:00
Chenlei Hu
98bdca4cb2
Deprecate InputTypeOptions.defaultInput ( #7551 )
...
* Deprecate InputTypeOptions.defaultInput
* nit
* nit
2025-04-10 06:57:06 -04:00
Jedrzej Kosinski
e346d8584e
Add prepare_sampling wrapper allowing custom nodes to more accurately report noise_shape ( #7500 )
2025-04-09 09:43:35 -04:00
silveroxides
3d375a153e
fix mistake
2025-04-08 12:56:02 +02:00
silveroxides
e1af413722
Adjust memory usage factor and remove unnecessary code
2025-04-08 12:48:25 +02:00
Silver
c4f6874dc1
Merge branch 'comfyanonymous:master' into chroma-support
2025-04-07 19:21:09 +02:00
comfyanonymous
70d7242e57
Support the wan fun reward loras.
2025-04-07 05:01:47 -04:00
silveroxides
cb6ece9a18
set modelType.FLOW, will cause beta scheduler to work properly
2025-04-06 09:52:32 +02:00
Silver
de3f3ea28b
Merge branch 'comfyanonymous:master' into chroma-support
2025-04-06 07:31:00 +02:00
comfyanonymous
3bfe4e5276
Support 512 siglip model.
2025-04-05 07:01:01 -04:00
Silver
1ca0353b96
Merge branch 'comfyanonymous:master' into chroma-support
2025-04-05 12:58:40 +02:00
Raphael Walker
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
comfyanonymous
3a100b9a55
Disable partial offloading of audio VAE.
2025-04-04 21:24:56 -04:00
Silver
7012015928
Merge branch 'comfyanonymous:master' into chroma-support
2025-04-03 04:09:39 +02:00
BiologicalExplosion
2222cf67fd
MLU memory optimization ( #7470 )
...
Co-authored-by: huzhan <huzhan@cambricon.com>
2025-04-02 19:24:04 -04:00
BVH
301e26b131
Add option to store TE in bf16 ( #7461 )
2025-04-01 13:48:53 -04:00
Silver
cb3e388e8f
Merge branch 'comfyanonymous:master' into chroma-support
2025-04-01 16:42:40 +02:00
comfyanonymous
a3100c8452
Remove useless code.
2025-03-29 20:12:56 -04:00
comfyanonymous
2d17d8910c
Don't error if wan concat image has extra channels.
2025-03-28 08:49:29 -04:00
silveroxides
2378c63ba9
update model_base.py
2025-03-27 18:43:58 +01:00
Silver
bf339e8265
Update supported_models.py
2025-03-27 18:29:51 +01:00
comfyanonymous
0a1f8869c9
Add WanFunInpaintToVideo node for the Wan fun inpaint models.
2025-03-27 11:13:27 -04:00
Silver
b7da8e2bc1
Add lora conversion if statement in lora.py
2025-03-27 03:08:24 +01:00
