  comfyanonymousandGitHub
|
f74fc4d927
|
Add ImageRotate and ImageFlip nodes. (#8789)
|
2025-07-03 19:16:30 -04:00 |
|
|
comfyanonymousandGitHub
|
e9af97ba1a
|
Use torch cu129 for nvidia pytorch nightly. (#8786)
* update nightly workflow with cu129
* Remove unused file to lower standalone size.
|
2025-07-03 14:39:11 -04:00 |
|
|
comfyanonymousandGitHub
|
34c8eeec06
|
Fix ImageColorToMask not returning right mask values. (#8771)
|
2025-07-02 15:35:11 -04:00 |
|
|
comfyanonymousandGitHub
|
111f583e00
|
Fallback to regular op when fp8 op throws exception. (#8761)
|
2025-07-02 00:57:13 -04:00 |
|
|
comfyanonymousandGitHub
|
772de7c006
|
PerpNeg Guider optimizations. (#8753)
|
2025-07-01 03:09:07 -04:00 |
|
|
comfyanonymousandGitHub
|
cf49a2c5b5
|
Dual cfg node optimizations when cfg is 1.0 (#8747)
|
2025-06-30 14:18:25 -04:00 |
|
|
comfyanonymousandGitHub
|
170c7bb90c
|
Fix contiguous issue with pytorch nightly. (#8729)
|
2025-06-29 06:38:40 -04:00 |
|
|
comfyanonymousandGitHub
|
e195c1b13f
|
Make stable release workflow publish drafts. (#8723)
|
2025-06-28 19:11:16 -04:00 |
|
|
comfyanonymousandGitHub
|
396454fa41
|
Reorder the schedulers so simple is the default one. (#8722)
|
2025-06-28 18:12:56 -04:00 |
|
|
comfyanonymousandGitHub
|
a3cf272522
|
Skip custom node logic completely if disabled and no whitelisted nodes. (#8719)
|
2025-06-28 15:53:40 -04:00 |
|
|
comfyanonymousandGitHub
|
c36be0ea09
|
Fix memory estimation bug with kontext. (#8709)
|
2025-06-27 17:21:12 -04:00 |
|
|
comfyanonymousandGitHub
|
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 |
|
|
comfyanonymousandGitHub
|
bd951a714f
|
Add Flux Kontext and Omnigen 2 models to readme. (#8682)
|
2025-06-26 12:26:29 -04:00 |
|
|
comfyanonymousandGitHub
|
7d8cf4cacc
|
Update requirements.txt (#8680)
|
2025-06-26 11:39:40 -04:00 |
|
|
comfyanonymousandGitHub
|
ef5266b1c1
|
Support Flux Kontext Dev model. (#8679)
|
2025-06-26 11:28:41 -04:00 |
|
|
comfyanonymousandGitHub
|
a96e65df18
|
Disable omnigen2 fp16 on older pytorch versions. (#8672)
|
2025-06-26 03:39:09 -04:00 |
|
|
comfyanonymousandGitHub
|
93a49a45de
|
Bump minimum transformers version. (#8671)
|
2025-06-26 02:33:02 -04:00 |
|
|
comfyanonymousandGitHub
|
ec70ed6aea
|
Omnigen2 model implementation. (#8669)
|
2025-06-25 19:35:57 -04:00 |
|
|
comfyanonymousandGitHub
|
7a13f74220
|
unet -> diffusion model (#8659)
|
2025-06-25 04:52:34 -04:00 |
|
|
comfyanonymousandGitHub
|
bd9f166c12
|
Cosmos predict2 model merging nodes. (#8647)
|
2025-06-24 05:17:16 -04:00 |
|
|
comfyanonymousandGitHub
|
dd94416db2
|
Indicate that directml is not recommended in the README. (#8644)
|
2025-06-23 14:04:49 -04:00 |
|
|
comfyanonymousandGitHub
|
ae0e7c4dff
|
Resize and pad image node. (#8636)
|
2025-06-22 17:59:31 -04:00 |
|
|
comfyanonymousandGitHub
|
78f79266a9
|
Allow padding in ImageStitch node to be white. (#8631)
|
2025-06-22 00:19:41 -04:00 |
|
|
comfyanonymousandGitHub
|
1883e70b43
|
Fix exception when using a noise mask with cosmos predict2. (#8621)
* Fix exception when using a noise mask with cosmos predict2.
* Fix ruff.
|
2025-06-21 03:30:39 -04:00 |
|
|
comfyanonymousandGitHub
|
f7fb193712
|
Small flux optimization. (#8611)
|
2025-06-20 05:37:32 -04:00 |
|
|
comfyanonymousandGitHub
|
7e9267fa77
|
Make flux controlnet work with sd3 text enc. (#8599)
|
2025-06-19 18:50:05 -04:00 |
|
|
comfyanonymousandGitHub
|
91d40086db
|
Fix pytorch warning. (#8593)
|
2025-06-19 11:04:52 -04:00 |
|
|
comfyanonymousandGitHub
|
e9e9a031a8
|
Show a better error when the workflow OOMs. (#8574)
|
2025-06-18 06:55:21 -04:00 |
|
|
comfyanonymousandGitHub
|
4459a17e82
|
Add Cosmos Predict2 to README. (#8562)
|
2025-06-17 05:18:01 -04:00 |
|
|
comfyanonymousandGitHub
|
e1c6dc720e
|
Allow setting min_length with tokenizer_data. (#8547)
|
2025-06-16 13:43:52 -04:00 |
|
|
comfyanonymousandGitHub
|
7ea79ebb9d
|
Add correct eps to ltxv rmsnorm. (#8542)
|
2025-06-15 12:21:25 -04:00 |
|
|
comfyanonymousandGitHub
|
ae75a084df
|
SaveLora now saves in the same filename format as all the other nodes. (#8538)
|
2025-06-15 03:44:59 -04:00 |
|
|
comfyanonymousandGitHub
|
d6a2137fc3
|
Support Cosmos predict2 image to video models. (#8535)
Use the CosmosPredict2ImageToVideoLatent node.
|
2025-06-14 21:37:07 -04:00 |
|
|
comfyanonymousandGitHub
|
29596bd53f
|
Small cosmos attention code refactor. (#8530)
|
2025-06-14 05:02:05 -04:00 |
|
|
comfyanonymousandGitHub
|
5bf69bde35
|
Add cosmos_rflow option to ModelSamplingContinuousEDM node. (#8523)
This is for the cosmos predict2 model.
|
2025-06-13 17:47:52 -04:00 |
|
|
comfyanonymousandGitHub
|
c69af655aa
|
Uncap cosmos predict2 res and fix mem estimation. (#8518)
|
2025-06-13 07:30:18 -04:00 |
|
|
comfyanonymousandGitHub
|
251f54a2ad
|
Basic initial support for cosmos predict2 text to image 2B and 14B models. (#8517)
|
2025-06-13 07:05:23 -04:00 |
|
|
comfyanonymousandGitHub
|
40fd39c7cb
|
debug -> warning (#8506)
|
2025-06-12 17:14:59 -04:00 |
|
|
comfyanonymousandGitHub
|
d2566eb4b2
|
Add a warning for old python versions. (#8504)
|
2025-06-12 15:38:33 -04:00 |
|
|
comfyanonymousandGitHub
|
365f9ed157
|
Revert "auto register web folder from pyproject (#8478)" (#8497)
This reverts commit 9685d4f3c3.
|
2025-06-11 17:28:04 -04:00 |
|
|
comfyanonymousandGitHub
|
8a4ff747bd
|
Fix mistake in last commit. (#8496)
* Move to right place.
|
2025-06-11 15:13:29 -04:00 |
|
|
comfyanonymousandGitHub
|
af1eb58be8
|
Fix black images on some flux models in fp16. (#8495)
|
2025-06-11 15:09:11 -04:00 |
|
|
comfyanonymousandGitHub
|
6e28a46454
|
Apple most likely is never fixing the fp16 attention bug. (#8485)
|
2025-06-10 13:06:24 -04:00 |
|
|
comfyanonymousandGitHub
|
7f800d04fa
|
Enable AMD fp8 and pytorch attention on some GPUs. (#8474)
Information is from the pytorch source code.
|
2025-06-09 12:50:39 -04:00 |
|
|
comfyanonymousandGitHub
|
97755eed46
|
Enable fp8 ops by default on gfx1201 (#8464)
|
2025-06-08 14:15:34 -04:00 |
|
|
comfyanonymousandGitHub
|
daf9d25ee2
|
Cleaner torch version comparisons. (#8453)
|
2025-06-07 10:01:15 -04:00 |
|
|
comfyanonymousandGitHub
|
3b4b171e18
|
Alternate fix for #8435 (#8442)
|
2025-06-06 09:43:27 -04:00 |
|
|
comfyanonymousandGitHub
|
4248b1618f
|
Let chroma TE work on regular flux. (#8429)
|
2025-06-05 10:07:17 -04:00 |
|
|
comfyanonymousandGitHub
|
871749c208
|
Add batch to GetImageSize node. (#8419)
|
2025-06-04 09:40:21 -04:00 |
|
|
comfyanonymousandGitHub
|
310f4b6ef8
|
Add api nodes to readme. (#8402)
|
2025-06-03 04:26:44 -04:00 |
|
|
comfyanonymousandGitHub
|
312d511630
|
Style fix. (#8390)
|
2025-06-02 07:22:02 -04:00 |
|
|
comfyanonymousandGitHub
|
fb4754624d
|
Make the casting in lists the same as regular inputs. (#8373)
|
2025-06-01 05:39:54 -04:00 |
|
|
comfyanonymousandGitHub
|
19e45e9b0e
|
Make it easier to pass lists of tensors to models. (#8358)
|
2025-05-31 20:00:20 -04:00 |
|
|
comfyanonymousandGitHub
|
704fc78854
|
Put ROCm version in tuple to make it easier to enable stuff based on it. (#8348)
|
2025-05-30 15:41:02 -04:00 |
|
|
comfyanonymousandGitHub
|
f2289a1f59
|
Delete useless file. (#8327)
|
2025-05-29 08:29:37 -04:00 |
|
|
comfyanonymousandGitHub
|
5e5e46d40c
|
Not really tested WAN Phantom Support. (#8321)
|
2025-05-28 23:46:15 -04:00 |
|
|
comfyanonymousandGitHub
|
1c1687ab1c
|
Support HiDream SimpleTuner loras. (#8318)
|
2025-05-28 18:47:15 -04:00 |
|
|
comfyanonymousandGitHub
|
06c661004e
|
Memory estimation code can now take into account conds. (#8307)
|
2025-05-27 15:09:05 -04:00 |
|
|
comfyanonymousandGitHub
|
89a84e32d2
|
Disable initial GPU load when novram is used. (#8294)
|
2025-05-26 16:39:27 -04:00 |
|
|
comfyanonymousandGitHub
|
e5799c4899
|
Enable pytorch attention by default on AMD gfx1151 (#8282)
|
2025-05-26 04:29:25 -04:00 |
|
|
comfyanonymousandGitHub
|
a0651359d7
|
Return proper error if diffusion model not detected properly. (#8272)
|
2025-05-25 05:28:11 -04:00 |
|
|
comfyanonymousandGitHub
|
5a87757ef9
|
Better error if sageattention is installed but a dependency is missing. (#8264)
|
2025-05-24 06:43:12 -04:00 |
|
|
comfyanonymousandGitHub
|
0b50d4c0db
|
Add argument to explicitly enable fp8 compute support. (#8257)
This can be used to test if your current GPU/pytorch version supports fp8 matrix mult in combination with --fast or the fp8_e4m3fn_fast dtype.
|
2025-05-23 17:43:50 -04:00 |
|
|
comfyanonymousandGitHub
|
f85c08df06
|
Make VACE conditionings stackable. (#8240)
|
2025-05-22 19:22:26 -04:00 |
|
|
comfyanonymousandGitHub
|
4202e956a0
|
Add append feature to conditioning_set_values (#8239)
Refactor unclipconditioning node.
|
2025-05-22 08:11:13 -04:00 |
|
|
comfyanonymousandGitHub
|
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 |
|
|
comfyanonymousandGitHub
|
7e84bf5373
|
This doesn't seem to be needed on chroma. (#8209)
|
2025-05-20 05:29:23 -04:00 |
|
|
comfyanonymousandGitHub
|
e930a387d6
|
Update AMD instructions in README. (#8198)
|
2025-05-19 04:58:41 -04:00 |
|
|
comfyanonymousandGitHub
|
d8e5662822
|
Remove default delimiter. (#8183)
|
2025-05-18 04:12:12 -04:00 |
|
|
comfyanonymousandGitHub
|
62690eddec
|
Node to add pixel space noise to an image. (#8182)
|
2025-05-18 04:09:56 -04:00 |
|
|
comfyanonymousandGitHub
|
aee2908d03
|
Remove useless log. (#8166)
|
2025-05-17 06:27:34 -04:00 |
|
|
comfyanonymousandGitHub
|
dc46db7aa4
|
Make ImagePadForOutpaint return a 3 channel mask. (#8157)
|
2025-05-16 15:15:55 -04:00 |
|
|
comfyanonymousandGitHub
|
1c2d45d2b5
|
Fix typo in last PR. (#8144)
More robust model detection for future proofing.
|
2025-05-15 19:02:19 -04:00 |
|
|
comfyanonymousandGitHub
|
6a2e4bb9e0
|
Remove old hack used to fix windows pytorch 2.4 on the portable. (#8139)
Not necessary anymore.
|
2025-05-15 08:21:47 -04:00 |
|
|
comfyanonymousandGitHub
|
08368f8e00
|
Update comment on ROCm pytorch attention in README. (#8123)
|
2025-05-14 17:54:50 -04:00 |
|
|
comfyanonymousandGitHub
|
4a9014e201
|
Hunyuan Custom initial untested implementation. (#8101)
|
2025-05-13 15:53:47 -04:00 |
|
|
comfyanonymousandGitHub
|
a814f2e8cc
|
Fix issue with old pytorch RMSNorm. (#8095)
|
2025-05-13 07:54:28 -04:00 |
|
|
comfyanonymousandGitHub
|
481732a0ed
|
Support official ACE Step loras. (#8094)
|
2025-05-13 07:32:16 -04:00 |
|
|
comfyanonymousandGitHub
|
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 |
|
|
comfyanonymousandGitHub
|
577de83ca9
|
ACE VAE works in fp16. (#8055)
|
2025-05-11 04:58:00 -04:00 |
|
|
comfyanonymousandGitHub
|
d42613686f
|
Fix issue with fp8 ops on some models. (#8045)
_scaled_mm errors when an input is non contiguous.
|
2025-05-10 07:52:56 -04:00 |
|
|
comfyanonymousandGitHub
|
8ab15c863c
|
Add --mmap-torch-files to enable use of mmap when loading ckpt/pt (#8021)
|
2025-05-09 04:52:47 -04:00 |
|
|
comfyanonymousandGitHub
|
924d771e18
|
Add ACE Step to README. (#8005)
|
2025-05-08 08:40:57 -04:00 |
|
|
comfyanonymousandGitHub
|
a692c3cca4
|
Make ACE VAE tiling work. (#8004)
|
2025-05-08 07:25:45 -04:00 |
|
|
comfyanonymousandGitHub
|
5d3cc85e13
|
Make japanese hiragana and katakana characters work with ACE. (#7997)
|
2025-05-08 03:32:36 -04:00 |
|
|
comfyanonymousandGitHub
|
c7c025b8d1
|
Adjust memory estimation code for ACE VAE. (#7990)
|
2025-05-08 01:22:23 -04:00 |
|
|
comfyanonymousandGitHub
|
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 |
|
|
comfyanonymousandGitHub
|
56b6ee6754
|
Detection code to make ltxv models without config work. (#7986)
|
2025-05-07 21:28:24 -04:00 |
|
|
comfyanonymousandGitHub
|
cc33cd3422
|
Experimental lyrics strength for ACE. (#7984)
|
2025-05-07 19:22:07 -04:00 |
|
|
comfyanonymousandGitHub
|
b9980592c4
|
Refuse to load api nodes on old pyav version. (#7981)
|
2025-05-07 17:27:16 -04:00 |
|
|
comfyanonymousandGitHub
|
16417b40d9
|
Initial ACE-Step model implementation. (#7972)
|
2025-05-07 08:33:34 -04:00 |
|
|
comfyanonymousandGitHub
|
271c9c5b9e
|
Better mem estimation for the LTXV 13B model. (#7963)
|
2025-05-06 09:52:37 -04:00 |
|
|
comfyanonymousandGitHub
|
a4e679765e
|
Change chroma to use Flux shift. (#7961)
|
2025-05-06 09:00:01 -04:00 |
|
|
comfyanonymousandGitHub
|
094e9ef126
|
Add a way to disable api nodes: --disable-api-nodes (#7960)
|
2025-05-06 04:53:53 -04:00 |
|
|
comfyanonymousandGitHub
|
d9c80a85e5
|
This should not be a warning. (#7946)
|
2025-05-05 07:49:07 -04:00 |
|
|
comfyanonymousandGitHub
|
80a44b97f5
|
Change lumina to native RMSNorm. (#7935)
|
2025-05-04 06:39:23 -04:00 |
|
|
comfyanonymousandGitHub
|
9187a09483
|
Change cosmos and hydit models to use the native RMSNorm. (#7934)
|
2025-05-04 06:26:20 -04:00 |
|
|
comfyanonymousandGitHub
|
3041e5c354
|
Switch mochi and wan modes to use pytorch RMSNorm. (#7925)
* Switch genmo model to native RMSNorm.
* Switch WAN to native RMSNorm.
|
2025-05-03 19:07:55 -04:00 |
|
|
comfyanonymousandGitHub
|
486ad8fdc5
|
Fix updater issue with newer portable. (#7917)
|
2025-05-03 00:28:10 -04:00 |
|
|
comfyanonymousandGitHub
|
ff99861650
|
Make clipsave work with more TE models. (#7908)
|
2025-05-02 05:15:32 -04:00 |
|