wangbo/ComfyUI
1
0
Fork 0
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2025-12-16 17:42:58 +08:00
Code Issues Actions 13 Packages Projects Releases Wiki Activity
3,710 Commits 53 Branches 100 Tags 1.2 GiB
dca6bdd4fa
Commit Graph

1607 Commits

Author SHA1 Message Date
comfyanonymous
8a438115fb add RMSNorm to comfy.ops 2025-04-14 18:00:33 -04:00
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
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
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
comfyanonymous
70d7242e57 Support the wan fun reward loras. 2025-04-07 05:01:47 -04:00
comfyanonymous
3bfe4e5276 Support 512 siglip model. 2025-04-05 07:01:01 -04:00
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
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
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
comfyanonymous
0a1f8869c9 Add WanFunInpaintToVideo node for the Wan fun inpaint models. 2025-03-27 11:13:27 -04:00
comfyanonymous
3661c833bc Support the WAN 2.1 fun control models. 
Use the new WanFunControlToVideo node.
 2025-03-26 19:54:54 -04:00
comfyanonymous
8edc1f44c1 Support more float8 types. 2025-03-25 05:23:49 -04:00
comfyanonymous
e471c726e5 Fallback to pytorch attention if sage attention fails. 2025-03-22 15:45:56 -04:00
comfyanonymous
d9fa9d307f Automatically set the right sampling type for lotus. 2025-03-21 14:19:37 -04:00
thot experiment
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
comfyanonymous
3872b43d4b A few fixes for the hunyuan3d models. 2025-03-20 04:52:31 -04:00
comfyanonymous
32ca0805b7 Fix orientation of hunyuan 3d model. 2025-03-19 19:55:24 -04:00
comfyanonymous
11f1b41bab Initial Hunyuan3Dv2 implementation. 
Supports the multiview, mini, turbo models and VAEs.
 2025-03-19 16:52:58 -04:00
comfyanonymous
3b19fc76e3 Allow disabling pe in flux code for some other models. 2025-03-18 05:09:25 -04:00
comfyanonymous
50614f1b79 Fix regression with clip vision. 2025-03-17 13:56:11 -04:00
comfyanonymous
6dc7b0bfe3 Add support for giant dinov2 image encoder. 2025-03-17 05:53:54 -04:00
comfyanonymous
e8e990d6b8 Cleanup code. 2025-03-16 06:29:12 -04:00
Jedrzej Kosinski
2e24a15905
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
fd5297131f
Guard the edge cases of noise term in er_sde (#7265) 2025-03-16 06:02:25 -04:00
comfyanonymous
55a1b09ddc Allow loading diffusion model files with the "Load Checkpoint" node. 2025-03-15 08:27:49 -04:00
comfyanonymous
3c3988df45 Show a better error message if the VAE is invalid. 2025-03-15 08:26:36 -04:00
comfyanonymous
a2448fc527 Remove useless code. 2025-03-14 18:10:37 -04:00
comfyanonymous
6a0daa79b6 Make the SkipLayerGuidanceDIT node work on WAN. 2025-03-14 10:55:19 -04:00
FeepingCreature
9c98c6358b
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
7aceb9f91c
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
comfyanonymous
35504e2f93 Fix. 2025-03-13 15:03:18 -04:00
comfyanonymous
299436cfed Print mac version. 2025-03-13 10:05:40 -04:00
Chenlei Hu
9b6cd9b874
[NodeDef] Add documentation on multi_select input option (#7212) 2025-03-12 17:29:39 -04:00
chaObserv
3fc688aebd
Ensure the extra_args in dpmpp sde series (#7204) 2025-03-12 17:28:59 -04:00
chaObserv
01015bff16
Add er_sde sampler (#7187) 2025-03-12 02:42:37 -04:00
comfyanonymous
ca8efab79f Support control loras on Wan. 2025-03-10 17:23:13 -04:00
comfyanonymous
9aac21f894 Fix issues with new hunyuan img2vid model and bumb version to v0.3.26 2025-03-09 05:07:22 -04:00
Jedrzej Kosinski
528d1b3563
When cached_hook_patches contain weights for hooks, only use hook_backup for unused keys (#7067) 2025-03-09 04:26:31 -04:00
comfyanonymous
7395b0c0d1 Support new hunyuan video i2v model. 
Use the new "v2 (replace)" guidance type in HunyuanImageToVideo and set
image_interleave to 4 on the "Text Encode Hunyuan Video" node.
 2025-03-08 20:34:47 -05:00
comfyanonymous
0952569493 Fix stable cascade VAE on some lowvram machines. 2025-03-08 20:24:04 -05:00
comfyanonymous
be4e760648 Add an image_interleave option to the Hunyuan image to video encode node. 
See the tooltip for what it does.
 2025-03-07 19:56:26 -05:00
comfyanonymous
11b1f27cb1 Set WAN default compute dtype to fp16. 2025-03-07 04:52:36 -05:00
comfyanonymous
70e15fd743 No need for scale_input when fp8 matrix mult is disabled. 2025-03-07 04:49:20 -05:00
comfyanonymous
e1474150de Support fp8_scaled diffusion models that don't use fp8 matrix mult. 2025-03-07 04:39:21 -05:00
JettHu
e62d72e8ca
Typo in node_typing.py (#7092) 2025-03-06 15:24:04 -05:00
comfyanonymous
dfa36e6855 Fix some things breaking when embeddings fail to apply. 2025-03-06 13:31:55 -05:00
comfyanonymous
29a70ca101 Support HunyuanVideo image to video model. 2025-03-06 03:07:15 -05:00
comfyanonymous
0bef826a98 Support llava clip vision model. 2025-03-06 00:24:43 -05:00
comfyanonymous
85ef295069 Make applying embeddings more efficient. 
Adding new tokens no longer makes a whole copy of the embeddings weight
which can be massive on certain models.
 2025-03-05 17:34:38 -05:00
Chenlei Hu
5d84607bf3
Add type hint for FileLocator (#6968) 
* Add type hint for FileLocator

* nit
 2025-03-05 15:35:26 -05:00
Silver
c1909f350f
Better argument handling of front-end-root (#7043) 
* Better argument handling of front-end-root

Improves handling of front-end-root launch argument. Several instances where users have set it and ComfyUI launches as normal and completely disregards the launch arg which doesn't make sense. Better to indicate to user that something is incorrect.

* Removed unused import

There was no real reason to use "Optional" typing in ther front-end-root argument.
 2025-03-05 15:34:22 -05:00
Chenlei Hu
52b3469606
[NodeDef] Explicitly add control_after_generate to seed/noise_seed (#7059) 
* [NodeDef] Explicitly add control_after_generate to seed/noise_seed

* Update comfy/comfy_types/node_typing.py

Co-authored-by: filtered <176114999+webfiltered@users.noreply.github.com>

---------

Co-authored-by: filtered <176114999+webfiltered@users.noreply.github.com>
 2025-03-05 15:33:23 -05:00
comfyanonymous
369b079ff6 Fix lowvram issue with ltxv vae. 2025-03-05 05:26:08 -05:00
comfyanonymous
9c9a7f012a Adjust ltxv memory factor. 2025-03-05 05:16:05 -05:00
comfyanonymous
93fedd92fe Support LTXV 0.9.5. 
Credits: Lightricks team.
 2025-03-05 00:13:49 -05:00
comfyanonymous
65042f7d39 Make it easier to set a custom template for hunyuan video. 2025-03-04 09:26:05 -05:00
comfyanonymous
7c7c70c400 Refactor skyreels i2v code. 2025-03-04 00:15:45 -05:00
comfyanonymous
f86c724ef2 Temporal area composition. 
New ConditioningSetAreaPercentageVideo node.
 2025-03-03 06:50:31 -05:00
comfyanonymous
9af6320ec9 Make 2d area composition nodes work on video models. 2025-03-02 08:19:16 -05:00
comfyanonymous
4dc6709307 Rename argument in last commit and document the options. 2025-03-01 02:43:49 -05:00
Chenlei Hu
4d55f16ae8
Use enum list for --fast options (#7024) 2025-03-01 02:37:35 -05:00
comfyanonymous
cf0b549d48 --fast now takes a number as argument to indicate how fast you want it. 
The idea is that you can indicate how much quality vs speed you want.

At the moment:

--fast 2 enables fp16 accumulation if your pytorch supports it.
--fast 5 enables fp8 matrix mult on fp8 models and the optimization above.

--fast without a number enables all optimizations.
 2025-02-28 02:48:20 -05:00
comfyanonymous
eb4543474b Use fp16 for intermediate for fp8 weights with --fast if supported. 2025-02-28 02:17:50 -05:00
comfyanonymous
1804397952 Use fp16 if checkpoint weights are fp16 and the model supports it. 2025-02-27 16:39:57 -05:00
comfyanonymous
f4dac8ab6f Wan code small cleanup. 2025-02-27 07:22:42 -05:00
BiologicalExplosion
89253e9fe5
Support Cambricon MLU (#6964) 
Co-authored-by: huzhan <huzhan@cambricon.com>
 2025-02-26 20:45:13 -05:00
comfyanonymous
3ea3bc8546 Fix wan issues when prompt length is long. 2025-02-26 20:34:02 -05:00
comfyanonymous
0270a0b41c Reduce artifacts on Wan by doing the patch embedding in fp32. 2025-02-26 16:59:26 -05:00
comfyanonymous
c37f15f98e Add fast preview support for Wan models. 2025-02-26 08:56:23 -05:00
comfyanonymous
4bca7367f3 Don't try to use clip_fea on t2v model. 2025-02-26 08:38:09 -05:00
comfyanonymous
b6fefe686b Better wan memory estimation. 2025-02-26 07:51:22 -05:00
comfyanonymous
fa62287f1f More code reuse in wan. 
Fix bug when changing the compute dtype on wan.
 2025-02-26 05:22:29 -05:00
comfyanonymous
0844998db3 Slightly better wan i2v mask implementation. 2025-02-26 03:49:50 -05:00
comfyanonymous
4ced06b879 WIP support for Wan I2V model. 2025-02-26 01:49:43 -05:00
comfyanonymous
cb06e9669b Wan seems to work with fp16. 2025-02-25 21:37:12 -05:00
comfyanonymous
9a66bb972d Make wan work with all latent resolutions. 
Cleanup some code.
 2025-02-25 19:56:04 -05:00
comfyanonymous
ea0f939df3 Fix issue with wan and other attention implementations. 2025-02-25 19:13:39 -05:00
comfyanonymous
f37551c1d2 Change wan rope implementation to the flux one. 
Should be more compatible.
 2025-02-25 19:11:14 -05:00
comfyanonymous
63023011b9 WIP support for Wan t2v model. 2025-02-25 17:20:35 -05:00
comfyanonymous
f40076096e Cleanup some lumina te code. 2025-02-25 04:10:26 -05:00
comfyanonymous
96d891cb94 Speedup on some models by not upcasting bfloat16 to float32 on mac. 2025-02-24 05:41:32 -05:00
comfyanonymous
ace899e71a Prioritize fp16 compute when using allow_fp16_accumulation 2025-02-23 04:45:54 -05:00
comfyanonymous
aff16532d4 Remove some useless code. 2025-02-22 04:45:14 -05:00
comfyanonymous
072db3bea6 Assume the mac black image bug won't be fixed before v16. 2025-02-21 20:24:07 -05:00
comfyanonymous
a6deca6d9a Latest mac still has the black image bug. 2025-02-21 20:14:30 -05:00
comfyanonymous
41c30e92e7 Let all model memory be offloaded on nvidia. 2025-02-21 06:32:21 -05:00
comfyanonymous
12da6ef581 Apparently directml supports fp16. 2025-02-20 09:30:24 -05:00
Silver
c5be423d6b
Fix link pointing to non-exisiting docs (#6891) 
* Fix link pointing to non-exisiting docs

The current link is pointing to a path that does not exist any longer.
I changed it to point to the currect correct path for custom nodes datatypes.

* Update node_typing.py
 2025-02-20 07:07:07 -05:00
maedtb
5715be2ca9
Fix Hunyuan unet config detection for some models. (#6877) 
The change to support 32 channel hunyuan models is missing the `key_prefix` on the key.

This addresses a complain in the comments of acc152b674.
 2025-02-19 07:14:45 -05:00
bymyself
afc85cdeb6
Add Load Image Output node (#6790) 
* add LoadImageOutput node

* add route for input/output/temp files

* update node_typing.py

* use literal type for image_folder field

* mark node as beta
 2025-02-18 17:53:01 -05:00
Jukka Seppänen
acc152b674
Support loading and using SkyReels-V1-Hunyuan-I2V (#6862) 
* Support SkyReels-V1-Hunyuan-I2V

* VAE scaling

* Fix T2V

oops

* Proper latent scaling
 2025-02-18 17:06:54 -05:00
comfyanonymous
b07258cef2 Fix typo. 
Let me know if this slows things down on 2000 series and below.
 2025-02-18 07:28:33 -05:00
comfyanonymous
31e54b7052 Improve AMD arch detection. 2025-02-17 04:53:40 -05:00
comfyanonymous
8c0bae50c3 bf16 manual cast works on old AMD. 2025-02-17 04:42:40 -05:00
comfyanonymous
530412cb9d Refactor torch version checks to be more future proof. 2025-02-17 04:36:45 -05:00
comfyanonymous
e2919d38b4 Disable bf16 on AMD GPUs that don't support it. 2025-02-16 05:46:10 -05:00
comfyanonymous
1cd6cd6080 Disable pytorch attention in VAE for AMD. 2025-02-14 05:42:14 -05:00
comfyanonymous
d7b4bf21a2 Auto enable mem efficient attention on gfx1100 on pytorch nightly 2.7 
I'm not not sure which arches are supported yet. If you see improvements in
memory usage while using --use-pytorch-cross-attention on your AMD GPU let
me know and I will add it to the list.
 2025-02-14 04:18:14 -05:00
comfyanonymous
019c7029ea Add a way to set a different compute dtype for the model at runtime. 
Currently only works for diffusion models.
 2025-02-13 20:34:03 -05:00
comfyanonymous
8773ccf74d Better memory estimation for ROCm that support mem efficient attention. 
There is no way to check if the card actually supports it so it assumes
that it does if you use --use-pytorch-cross-attention with yours.
 2025-02-13 08:32:36 -05:00
comfyanonymous
1d5d6586f3 Fix ruff. 2025-02-12 06:49:16 -05:00
zhoufan2956
35740259de
mix_ascend_bf16_infer_err (#6794) 2025-02-12 06:48:11 -05:00
comfyanonymous
ab888e1e0b Add add_weight_wrapper function to model patcher. 
Functions can now easily be added to wrap/modify model weights.
 2025-02-12 05:55:35 -05:00
comfyanonymous
d9f0fcdb0c Cleanup. 2025-02-11 17:17:03 -05:00
HishamC
b124256817
Fix for running via DirectML (#6542) 
* Fix for running via DirectML

Fix DirectML empty image generation issue with Flux1. add CPU fallback for unsupported path. Verified the model works on AMD GPUs

* fix formating

* update casual mask calculation
 2025-02-11 17:11:32 -05:00
comfyanonymous
af4b7c91be Make --force-fp16 actually force the diffusion model to be fp16. 2025-02-11 08:33:09 -05:00
comfyanonymous
4027466c80 Make lumina model work with any latent resolution. 2025-02-10 00:24:20 -05:00
comfyanonymous
095d867147 Remove useless function. 2025-02-09 07:02:57 -05:00
Pam
caeb27c3a5
res_multistep: Fix cfgpp and add ancestral samplers (#6731) 2025-02-08 19:39:58 -05:00
comfyanonymous
3d06e1c555 Make error more clear to user. 2025-02-08 18:57:24 -05:00
catboxanon
43a74c0de1
Allow FP16 accumulation with --fast (#6453) 
Currently only applies to PyTorch nightly releases. (>=20250208)
 2025-02-08 17:00:56 -05:00
comfyanonymous
079eccc92a Don't compress http response by default. 
Remove argument to disable it.

Add new --enable-compress-response-body argument to enable it.
 2025-02-07 03:29:21 -05:00
comfyanonymous
14880e6dba Remove some useless code. 2025-02-06 05:00:37 -05:00
comfyanonymous
37cd448529 Set the shift for Lumina back to 6. 2025-02-05 14:49:52 -05:00
comfyanonymous
94f21f9301 Upcasting rope to fp32 seems to make no difference in this model. 2025-02-05 04:32:47 -05:00
comfyanonymous
60653004e5 Use regular numbers for rope in lumina model. 2025-02-05 04:17:25 -05:00
comfyanonymous
a57d635c5f Fix lumina 2 batches. 2025-02-04 21:48:11 -05:00
comfyanonymous
8ac2dddeed Lower the default shift of lumina to reduce artifacts. 2025-02-04 06:50:37 -05:00
comfyanonymous
3e880ac709 Fix on python 3.9 2025-02-04 04:20:56 -05:00
comfyanonymous
e5ea112a90 Support Lumina 2 model. 2025-02-04 04:16:30 -05:00
comfyanonymous
44e19a28d3 Use maximum negative value instead of -inf for masks in text encoders. 
This is probably more correct.
 2025-02-02 09:46:00 -05:00
Dr.Lt.Data
0a0df5f136
better guide message for sageattention (#6634) 2025-02-02 09:26:47 -05:00
KarryCharon
24d6871e47
add disable-compres-response-body cli args; add compress middleware; (#6672) 2025-02-02 09:24:55 -05:00
comfyanonymous
9e1d301129 Only use stable cascade lora format with cascade model. 2025-02-01 06:35:22 -05:00
comfyanonymous
8d8dc9a262 Allow batch of different sigmas when noise scaling. 2025-01-30 06:49:52 -05:00
filtered
222f48c0f2
Allow changing folder_paths.base_path via command line argument. (#6600) 
* Reimpl. CLI arg directly inside folder_paths.

* Update tests to use CLI arg mocking.

* Revert last-minute refactor.

* Fix test state polution.
 2025-01-29 08:06:28 -05:00
comfyanonymous
13fd4d6e45 More friendly error messages for corrupted safetensors files. 2025-01-28 09:41:09 -05:00
comfyanonymous
255edf2246 Lower minimum ratio of loaded weights on Nvidia. 2025-01-27 05:26:51 -05:00
comfyanonymous
67feb05299 Remove redundant code. 2025-01-25 19:04:53 -05:00
comfyanonymous
14ca5f5a10 Remove useless code. 2025-01-24 06:15:54 -05:00
comfyanonymous
96e2a45193 Remove useless code. 2025-01-23 05:56:23 -05:00
Chenlei Hu
dfa2b6d129
Remove unused function lcm in conds.py (#6572) 2025-01-23 05:54:09 -05:00
comfyanonymous
d6bbe8c40f Remove support for python 3.8. 2025-01-22 17:04:30 -05:00
chaObserv
e857dd48b8
Add gradient estimation sampler (#6554) 2025-01-22 05:29:40 -05:00
comfyanonymous
fb2ad645a3 Add FluxDisableGuidance node to disable using the guidance embed. 2025-01-20 14:50:24 -05:00
comfyanonymous
d8a7a32779 Cleanup old TODO. 2025-01-20 03:44:13 -05:00
Sergii Dymchenko
ebf038d4fa
Use torch.special.expm1 (#6388) 
* Use `torch.special.expm1`

This function provides greater precision than `exp(x) - 1` for small values of `x`.

Found with TorchFix https://github.com/pytorch-labs/torchfix/

* Use non-alias
 2025-01-19 04:54:32 -05:00
catboxanon
b1a02131c9
Remove comfy.samplers self-import (#6506) 2025-01-18 17:49:51 -05:00
comfyanonymous
507199d9a8 Uni pc sampler now works with audio and video models. 2025-01-18 05:27:58 -05:00
comfyanonymous
2f3ab40b62 Add warning when using old pytorch versions. 2025-01-17 18:47:27 -05:00
comfyanonymous
0aa2368e46 Fix some cosmos fp8 issues. 2025-01-16 17:45:37 -05:00
comfyanonymous
cca96a85ae Fix cosmos VAE failing with videos longer than 121 frames. 2025-01-16 16:30:06 -05:00
comfyanonymous
31831e6ef1 Code refactor. 2025-01-16 07:23:54 -05:00
comfyanonymous
88ceb28e20 Tweak hunyuan memory usage factor. 2025-01-16 06:31:03 -05:00
comfyanonymous
23289a6a5c Clean up some debug lines. 2025-01-16 04:24:39 -05:00
comfyanonymous
9d8b6c1f46 More accurate memory estimation for cosmos and hunyuan video. 2025-01-16 03:48:40 -05:00
comfyanonymous
6320d05696 Slightly lower hunyuan video memory usage. 2025-01-16 00:23:01 -05:00
comfyanonymous
25683b5b02 Lower cosmos diffusion model memory usage. 2025-01-15 23:46:42 -05:00
comfyanonymous
4758fb64b9 Lower cosmos VAE memory usage by a bit. 2025-01-15 22:57:52 -05:00
comfyanonymous
008761166f Optimize first attention block in cosmos VAE. 2025-01-15 21:48:46 -05:00
comfyanonymous
cba58fff0b Remove unsafe embedding load for very old pytorch. 2025-01-15 04:32:23 -05:00
comfyanonymous
2feb8d0b77 Force safe loading of files in torch format on pytorch 2.4+ 
If this breaks something for you make an issue.
 2025-01-15 03:50:27 -05:00
Pam
c78a45685d
Rewrite res_multistep sampler and implement res_multistep_cfg_pp sampler. (#6462) 2025-01-14 18:20:06 -05:00
comfyanonymous
3aaabb12d4 Implement Cosmos Image/Video to World (Video) diffusion models. 
Use CosmosImageToVideoLatent to set the input image/video.
 2025-01-14 05:14:10 -05:00
comfyanonymous
1f1c7b7b56 Remove useless code. 2025-01-13 03:52:37 -05:00
comfyanonymous
90f349f93d Add res_multistep sampler from the cosmos code. 
This sampler should work with all models.
 2025-01-12 03:10:07 -05:00
Jedrzej Kosinski
6c9bd11fa3
Hooks Part 2 - TransformerOptionsHook and AdditionalModelsHook (#6377) 
* Add 'sigmas' to transformer_options so that downstream code can know about the full scope of current sampling run, fix Hook Keyframes' guarantee_steps=1 inconsistent behavior with sampling split across different Sampling nodes/sampling runs by referencing 'sigmas'

* Cleaned up hooks.py, refactored Hook.should_register and add_hook_patches to use target_dict instead of target so that more information can be provided about the current execution environment if needed

* Refactor WrapperHook into TransformerOptionsHook, as there is no need to separate out Wrappers/Callbacks/Patches into different hook types (all affect transformer_options)

* Refactored HookGroup to also store a dictionary of hooks separated by hook_type, modified necessary code to no longer need to manually separate out hooks by hook_type

* In inner_sample, change "sigmas" to "sampler_sigmas" in transformer_options to not conflict with the "sigmas" that will overwrite "sigmas" in _calc_cond_batch

* Refactored 'registered' to be HookGroup instead of a list of Hooks, made AddModelsHook operational and compliant with should_register result, moved TransformerOptionsHook handling out of ModelPatcher.register_all_hook_patches, support patches in TransformerOptionsHook properly by casting any patches/wrappers/hooks to proper device at sample time

* Made hook clone code sane, made clear ObjectPatchHook and SetInjectionsHook are not yet operational

* Fix performance of hooks when hooks are appended via Cond Pair Set Props nodes by properly caching between positive and negative conds, make hook_patches_backup behave as intended (in the case that something pre-registers WeightHooks on the ModelPatcher instead of registering it at sample time)

* Filter only registered hooks on self.conds in CFGGuider.sample

* Make hook_scope functional for TransformerOptionsHook

* removed 4 whitespace lines to satisfy Ruff,

* Add a get_injections function to ModelPatcher

* Made TransformerOptionsHook contribute to registered hooks properly, added some doc strings and removed a so-far unused variable

* Rename AddModelsHooks to AdditionalModelsHook, rename SetInjectionsHook to InjectionsHook (not yet implemented, but at least getting the naming figured out)

* Clean up a typehint
 2025-01-11 12:20:23 -05:00
comfyanonymous
ee8a7ab69d Fast latent preview for Cosmos. 2025-01-11 04:41:24 -05:00
comfyanonymous
2ff3104f70 WIP support for Nvidia Cosmos 7B and 14B text to world (video) models. 2025-01-10 09:14:16 -05:00
comfyanonymous
129d8908f7 Add argument to skip the output reshaping in the attention functions. 2025-01-10 06:27:37 -05:00
comfyanonymous
ff838657fa Cleaner handling of attention mask in ltxv model code. 2025-01-09 07:12:03 -05:00
comfyanonymous
2307ff6746 Improve some logging messages. 2025-01-08 19:05:22 -05:00
comfyanonymous
d0f3752e33 Properly calculate inner dim for t5 model. 
This is required to support some different types of t5 models.
 2025-01-07 17:33:03 -05:00
comfyanonymous
4209edf48d Make a few more samplers deterministic. 2025-01-07 02:12:32 -05:00
Chenlei Hu
d055325783
Document get_attr and get_model_object (#6357) 
* Document get_attr and get_model_object

* Update model_patcher.py

* Update model_patcher.py

* Update model_patcher.py
 2025-01-06 20:12:22 -05:00
comfyanonymous
916d1e14a9 Make ancestral samplers more deterministic. 2025-01-06 03:04:32 -05:00
Jedrzej Kosinski
c496e53519
In inner_sample, change "sigmas" to "sampler_sigmas" in transformer_options to not conflict with the "sigmas" that will overwrite "sigmas" in _calc_cond_batch (#6360) 2025-01-06 01:36:47 -05:00
comfyanonymous
d45ebb63f6 Remove old unused function. 2025-01-04 07:20:54 -05:00
comfyanonymous
9e9c8a1c64 Clear cache as often on AMD as Nvidia. 
I think the issue this was working around has been solved.

If you notice that this change slows things down or causes stutters on
your AMD GPU with ROCm on Linux please report it.
 2025-01-02 08:44:16 -05:00
Andrew Kvochko
0f11d60afb
Fix temporal tiling for decoder, remove redundant tiles. (#6306) 
This commit fixes the temporal tile size calculation, and removes
a redundant tile at the end of the range when its elements are
completely covered by the previous tile.

Co-authored-by: Andrew Kvochko <a.kvochko@lightricks.com>
 2025-01-01 16:29:01 -05:00
comfyanonymous
79eea51a1d Fix and enforce all ruff W rules. 2025-01-01 03:08:33 -05:00
blepping
c0338a46a4
Fix unknown sampler error handling in calculate_sigmas function (#6280) 
Modernize calculate_sigmas function
 2024-12-31 17:33:50 -05:00
Jedrzej Kosinski
1c99734e5a
Add missing model_options param (#6296) 2024-12-31 14:46:55 -05:00
filtered
67758f50f3
Fix custom node type-hinting examples (#6281) 
* Fix import in comfy_types doc / sample

* Clarify docstring
 2024-12-31 03:41:09 -05:00
comfyanonymous
b7572b2f87 Fix and enforce no trailing whitespace. 2024-12-31 03:16:37 -05:00
blepping
a90aafafc1
Add kl_optimal scheduler (#6206) 
* Add kl_optimal scheduler

* Rename kl_optimal_schedule to kl_optimal_scheduler to be more consistent
 2024-12-30 05:09:38 -05:00
comfyanonymous
d9b7cfac7e Fix and enforce new lines at the end of files. 2024-12-30 04:14:59 -05:00
Jedrzej Kosinski
3507870535
Add 'sigmas' to transformer_options so that downstream code can know about the full scope of current sampling run, fix Hook Keyframes' guarantee_steps=1 inconsistent behavior with sampling split across different Sampling nodes/sampling runs by referencing 'sigmas' (#6273) 2024-12-30 03:42:49 -05:00
comfyanonymous
a618f768e0 Auto reshape 2d to 3d latent for single image generation on video model. 2024-12-29 02:26:49 -05:00
comfyanonymous
b504bd606d Add ruff rule for empty line with trailing whitespace. 2024-12-28 05:23:08 -05:00
comfyanonymous
d170292594 Remove some trailing white space. 2024-12-27 18:02:30 -05:00
filtered
9cfd185676
Add option to log non-error output to stdout (#6243) 
* nit

* Add option to log non-error output to stdout

- No change to default behaviour
- Adds CLI argument: --log-stdout
- With this arg present, any logging of a level below logging.ERROR will be sent to stdout instead of stderr
 2024-12-27 14:40:05 -05:00
comfyanonymous
4b5bcd8ac4 Closer memory estimation for hunyuan dit model. 2024-12-27 07:37:00 -05:00
comfyanonymous
ceb50b2cbf Closer memory estimation for pixart models. 2024-12-27 07:30:09 -05:00
comfyanonymous
160ca08138 Use python 3.9 in launch test instead of 3.8 
Fix ruff check.
 2024-12-26 20:05:54 -05:00
Huazhong Ji
c4bfdba330
Support ascend npu (#5436) 
* support ascend npu

Co-authored-by: YukMingLaw <lymmm2@163.com>
Co-authored-by: starmountain1997 <guozr1997@hotmail.com>
Co-authored-by: Ginray <ginray0215@gmail.com>
 2024-12-26 19:36:50 -05:00
comfyanonymous
ee9547ba31 Improve temporal VAE Encode (Tiled) math. 2024-12-26 07:18:49 -05:00
comfyanonymous
19a64d6291 Cleanup some mac related code. 2024-12-25 05:32:51 -05:00
comfyanonymous
b486885e08 Disable bfloat16 on older mac. 2024-12-25 05:18:50 -05:00
comfyanonymous
0229228f3f Clean up the VAE dtypes code. 2024-12-25 04:50:34 -05:00
comfyanonymous
99a1fb6027 Make fast fp8 take a bit less peak memory. 2024-12-24 18:05:19 -05:00
comfyanonymous
73e04987f7 Prevent black images in VAE Decode (Tiled) node. 
Overlap should be minimum 1 with tiling 2 for tiled temporal VAE decoding.
 2024-12-24 07:36:30 -05:00
comfyanonymous
5388df784a Add temporal tiling to VAE Encode (Tiled) node. 2024-12-24 07:10:09 -05:00
comfyanonymous
bc6dac4327 Add temporal tiling to VAE Decode (Tiled) node. 
You can now do tiled VAE decoding on the temporal direction for videos.
 2024-12-23 20:03:37 -05:00
comfyanonymous
15564688ed Add a try except block so if torch version is weird it won't crash. 2024-12-23 03:22:48 -05:00