comfyanonymous
2618d32dfb
Python 3.10 will be EOL soon, please upgrade. ( #15874 )
...
After the Python 3.10 EOL date of October 31 2026 we will put zero effort into keeping support for python 3.10 so everyone is recommended to upgrade to a newer version.
2026-08-24 23:09:38 -04:00
comfyanonymous
b78cec879b
Increase minimum pyav version. ( #15827 )
2026-08-23 12:29:18 -04:00
comfyanonymous
9db05e0e1f
Add colorspace option and change bit_depth to a combo on CreateVideo. ( #15810 )
2026-08-22 21:07:29 -04:00
comfyanonymous
7dde56176e
Increase trellis2 memory factor a bit. ( #15796 )
2026-08-21 20:44:56 -04:00
comfyanonymous
76135e557d
Add HDR color space options to h264 codec in Save Video node. ( #15764 )
2026-08-20 20:16:31 -04:00
comfyanonymous
dcbcf8c2e1
Support HDR video saving, AV1 codec, mkv and webm. ( #15741 )
2026-08-20 19:29:20 -04:00
comfyanonymous
a3e5cce506
Add friendly errors to the dynamic vram safetensors loader. ( #15722 )
2026-08-18 19:59:52 -07:00
comfyanonymous
8e869efc87
Add support for taeh3. ( #15695 )
2026-08-17 23:20:28 -04:00
comfyanonymous
0696f61dce
Allow regular single image Empty Latent Image node to be used with H3. ( #15677 )
2026-08-16 21:34:39 -04:00
comfyanonymous
aaabf34258
Add MiniMax Music 3 to readme. ( #15656 )
2026-08-15 19:34:53 -04:00
comfyanonymous
a7365071e4
Enable dynamic vram by default on ROCm 7.14 and higher. ( #15633 )
2026-08-14 20:34:40 -04:00
comfyanonymous
03fa4e48ba
Fix minimax music not working on non dynamic vram. ( #15588 )
2026-08-13 15:47:44 -04:00
comfyanonymous
b323a345bb
Update comfy-kitchen package version to 0.2.31 ( #15564 )
2026-08-12 23:01:31 -04:00
comfyanonymous
6b30dc2068
Don't disable dynamic vram on WSL. ( #15562 )
2026-08-12 21:39:00 -04:00
comfyanonymous
725e6ec606
Support anima tunes with extra blocks. ( #15555 )
2026-08-12 16:22:50 -04:00
comfyanonymous
bd34f338ac
Fix float64 device in ltx diffusion decoder. ( #15516 )
2026-08-12 03:55:08 -04:00
comfyanonymous
024cbc5fc1
Remove potentially problematic process_tokens method. ( #15507 )
2026-08-11 16:45:52 -04:00
comfyanonymous
bbb4b04caa
Don't depend on transformers for mistral and llama tokenizers. ( #15503 )
2026-08-11 15:54:44 -04:00
comfyanonymous
d9f9d2ba12
Fix some clip vision regression. ( #15506 )
2026-08-11 15:54:15 -04:00
comfyanonymous
2a19bbf014
Fix for broken tiled audio decode. ( #15502 )
2026-08-11 14:07:32 -04:00
comfyanonymous
62b3c94bd4
Fix peak memory issue with H3. ( #15486 )
2026-08-11 02:09:29 -07:00
comfyanonymous
bf4c9a08fc
Implement comfy kitchen attention. ( #15479 )
...
Add a ModelAttentionBackend node to manually select the attention for models in the workflows. Currently supports pytorch attention or comfy kitchen attention.
Add --use-ck-attention to enable comfy kitchen attention as the default attention backend for all models (might break some).
2026-08-10 22:03:08 -07:00
comfyanonymous
4f3544d131
Make cu130 warning more visible. ( #15463 )
2026-08-10 23:25:01 -04:00
comfyanonymous
9eaba63e1a
Fix upscale models breaking on non dynamic vram low vram. ( #15437 )
2026-08-08 17:51:05 -04:00
comfyanonymous
dd79c643a9
Minimum officially supported pytorch is now 2.7 ( #15413 )
2026-08-08 02:12:21 -04:00
comfyanonymous
cd84f47efe
Make it easier to debug nested tensors. ( #15383 )
2026-08-07 22:14:04 -04:00
comfyanonymous
66057c4e59
Update comfy-kitchen package version to 0.2.28 ( #15407 )
2026-08-07 18:25:27 -04:00
comfyanonymous
0ab8332bfa
Update comfy-kitchen package version to 0.2.27 ( #15388 )
2026-08-07 03:33:38 -04:00
comfyanonymous
2340099d93
Fix full offload on minimax audio vae. ( #15377 )
2026-08-07 00:26:16 -04:00
comfyanonymous
88fec4b605
Skip creating useless noise in res_multistep sampler. ( #15339 )
2026-08-06 18:17:44 -04:00
comfyanonymous
7972b5ba7f
Make the desktop app more prominent in the readme. ( #15330 )
2026-08-05 14:25:15 -07:00
comfyanonymous
de23a547f1
Update the Features section with more up to date stuff. ( #15302 )
2026-08-04 19:45:30 -07:00
comfyanonymous
9a9fdb10ed
Harden some nodes against potential issues related to combos. ( #15277 )
2026-08-03 23:55:13 -04:00
comfyanonymous
e377e26304
Don't pin too much memory on Linux systems with no swap partition. ( #15266 )
2026-08-03 16:29:47 -04:00
comfyanonymous
f06a187f50
Handle case where swap memory query fails on windows. ( #15219 )
2026-08-02 01:12:12 -04:00
comfyanonymous
532a16f3b9
Disable gradients on diffusion models. ( #15218 )
2026-08-01 20:15:51 -07:00
comfyanonymous
e0951a9c7e
Let the save text node save in csv format. ( #15217 )
2026-08-01 22:27:37 -04:00
comfyanonymous
41a3e160d7
Use the actual function to check if the path is within the dir. ( #15216 )
2026-08-01 22:15:17 -04:00
comfyanonymous
e803f24ea0
Let the VAEDecodeAudio node decode nested audio. ( #15211 )
2026-08-01 16:38:42 -04:00
comfyanonymous
e8e233cdf6
Update comfy-kitchen version to 0.2.26 ( #15208 )
2026-08-01 15:10:39 -04:00
comfyanonymous
2881e61610
Store mp4 metadata at the beginning of the file when possible. ( #15195 )
2026-08-01 03:21:28 -04:00
comfyanonymous
235b466a0c
Add crf option to save video node. ( #15191 )
2026-08-01 00:27:48 -04:00
comfyanonymous
a1c421994c
Expand k, v when attention backend would fall back to math because gqa. ( #15190 )
2026-07-31 15:17:56 -07:00
comfyanonymous
8352644aa9
comfy-kitchen AMD support. ( #15160 )
2026-07-30 19:53:13 -04:00
comfyanonymous
9b3aa08967
Don't enable comfyui_detail.log by default. ( #15159 )
2026-07-30 16:15:39 -04:00
comfyanonymous
f73e8cde88
Fallback to cudnn attention on linux if flash attention doesn't work. ( #15146 )
2026-07-29 18:10:28 -07:00
comfyanonymous
4f874c5e3a
Update comfy-kitchen to fix flux kv issue. ( #15144 )
2026-07-29 14:10:01 -07:00
comfyanonymous
628cdec592
Update comfy-kitchen package version to 0.2.23 ( #15112 )
2026-07-28 17:01:53 -04:00
comfyanonymous
99f221c7f5
Go back to older rocm for portable. ( #15127 )
2026-07-28 13:46:44 -07:00
comfyanonymous
6e36e12970
Update stable portable release workflow. ( #15113 )
2026-07-27 23:31:55 -04:00
comfyanonymous
02c688429e
Update AGENTS.md ( #15096 )
2026-07-26 17:21:05 -04:00
comfyanonymous
f966a2b38c
Optimize ideogram model using comfy kitchen rms rope. ( #15080 )
2026-07-25 15:09:26 -04:00
comfyanonymous
7c59a078d6
Use comfy kitchen rope functions in ltx models. ( #15056 )
2026-07-24 15:17:31 -04:00
comfyanonymous
0cb84e7e6e
Make Ernie use comfy kitchen rms rope ( #15055 )
2026-07-23 22:06:52 -04:00
comfyanonymous
2e47082c8e
Make z image/lumina 2 models use comfy kitchen rms rope. ( #15036 )
2026-07-22 15:34:27 -04:00
comfyanonymous
947c2749dd
Use optimized rms_rope function in joyai image model. ( #15018 )
2026-07-21 20:02:45 -07:00
comfyanonymous
35c94d6023
Fix gfx1035 not being treated like RDNA2 ( #15009 )
2026-07-20 23:36:03 -04:00
comfyanonymous
6665515349
Fix wan dancer issue with batches. ( #14999 )
2026-07-19 15:13:49 -07:00
comfyanonymous
c9602625e4
Implement regular and timestep zero reference images to krea 2 for ostris and identity edit ref loras. ( #14843 )
2026-07-18 17:12:18 -07:00
comfyanonymous
4800e78518
More comfy-kitchen int8 optimizations. ( #14980 )
2026-07-18 00:53:15 -04:00
comfyanonymous
0f42ba5146
Support anima lllite control models. ( #14954 )
...
Put them in the models/model_patches folder. Use the new AnimaLLLiteApply node.
2026-07-17 07:36:21 -07:00
comfyanonymous
71b73e3b2b
Speed up anima a bit. ( #14953 )
2026-07-16 19:44:02 -07:00
comfyanonymous
6a8ff7a929
Various comfy kitchen optimizations and fixes. ( #14963 )
2026-07-16 19:43:12 -07:00
comfyanonymous
678d42c90e
Update AGENTS.md ( #14955 )
2026-07-15 20:09:59 -07:00
comfyanonymous
dff0b18fff
Fix int8 performance regression on 16xx series. ( #14941 )
2026-07-14 13:13:08 -07:00
comfyanonymous
80acfcf0fe
More optimized int8 and int4 on turing. ( #14927 )
2026-07-13 13:03:29 -07:00
comfyanonymous
c35a622acd
Fix hidream o1 regression. ( #14923 )
2026-07-13 12:52:28 -07:00
comfyanonymous
917faef771
Support PID 1.5 models. ( #14894 )
2026-07-12 09:43:30 -07:00
comfyanonymous
69ea58697b
Try to fix flash attention related issue on AMD. ( #14880 )
2026-07-11 17:16:40 -07:00
comfyanonymous
f3a36e7484
Temporarily disable auto enabling triton by default on AMD. ( #14878 )
...
I get freezing issues on my test machine.
2026-07-10 18:37:59 -07:00
comfyanonymous
92ddf07ba1
Try to fix some issues with the seedvr VAE. ( #14877 )
2026-07-10 19:54:28 -04:00
comfyanonymous
e2a6e30d89
Fix black image on turing when using int4 models. ( #14864 )
2026-07-09 23:17:06 -04:00
comfyanonymous
b7a648ca20
Try to fix the model reloading issue some people have. ( #14822 )
2026-07-09 16:39:01 -07:00
comfyanonymous
73e84d5ec8
Support convrot int4 models. ( #14859 )
...
linear_dtype in comfy_quant metadata can be used to set if the int4 op does
the matrix multiplication in int8 or int4, the default is int4 on GPUs that
support it with fallback to int8 for GPUs that don't.
2026-07-09 18:57:09 -04:00
comfyanonymous
d0008a8958
Fix qwen3vl reference images when used as a text encode models. ( #14845 )
...
Should not affect use as a text generation model.
2026-07-09 01:50:25 -04:00
comfyanonymous
ffbecfffb9
Fix crash when using UNetSelfAttentionMultiply ( #14823 )
2026-07-07 21:17:31 -07:00
comfyanonymous
b481bc15af
Support gqa on all attention backends, drop support for pytorch 2.4 ( #14772 )
2026-07-07 22:57:52 -04:00
comfyanonymous
6880614319
Update AGENTS.md ( #14819 )
2026-07-07 18:36:13 -07:00
comfyanonymous
7cf4e78335
Delete symlink that breaks our updates. ( #14803 )
2026-07-06 22:24:05 -04:00
comfyanonymous
439bd807f8
Skip unloading dynamic model patchers in current workflow. ( #14799 )
2026-07-06 14:35:12 -07:00
comfyanonymous
000c6b784e
Small speedup for text model sampling. ( #14773 )
2026-07-05 18:39:24 -07:00
comfyanonymous
b7ba504e06
Try to make coderabbit enforce AGENTS.md ( #14759 )
2026-07-04 14:25:24 -04:00
comfyanonymous
de1b8f3e8d
Update AGENTS.md ( #14738 )
2026-07-03 13:08:24 -07:00
comfyanonymous
1e04ced089
Update AGENTS.md ( #14733 )
2026-07-03 02:08:47 -04:00
comfyanonymous
35c1470935
Update AGENTS.md ( #14726 )
2026-07-02 15:05:55 -04:00
comfyanonymous
92594ca84c
Update AGENTS.md with more stuff. ( #14725 )
2026-07-01 21:55:13 -04:00
comfyanonymous
dd17debce5
Add some more stuff to AGENTS.md ( #14704 )
2026-07-01 01:51:51 -04:00
comfyanonymous
50e5270b86
Add AGENTS.md ( #14696 )
2026-06-30 17:40:33 -04:00
comfyanonymous
d395813bcd
Fix memory leak related to int8. ( #14697 )
2026-06-30 14:08:59 -07:00
comfyanonymous
7851410511
Better and faster int8 lora applying. ( #14685 )
2026-06-29 21:52:08 -04:00
comfyanonymous
79c555ce6b
Fix int8 mm being skipped on offloaded lora weights. ( #14669 )
2026-06-28 23:52:36 -04:00
comfyanonymous
a95e461916
int8 support on turing GPUs. ( #14662 )
2026-06-27 15:53:11 -07:00
comfyanonymous
470ac36a0a
Fix int8 loras causing lower quality requant with wrong settings. ( #14650 )
...
* Update comfy-kitchen
* Support requantizing with same settings as orig quant.
2026-06-26 16:41:29 -07:00
comfyanonymous
7cb784e0f4
Faster int8. ( #14641 )
2026-06-25 15:25:47 -07:00
comfyanonymous
1a510f0423
Support int8 models. ( #14636 )
2026-06-25 11:23:58 -07:00
comfyanonymous
64e1d740b8
Add advanced krea 2 model merging node. ( #14621 )
2026-06-24 20:37:30 -07:00
comfyanonymous
b910f4fa2a
More accurate memory usage factor for krea 2. ( #14594 )
2026-06-23 16:50:48 +08:00
comfyanonymous
833bfb572e
Please try native formats instead of disabling dynamic vram. ( #14577 )
2026-06-22 21:06:19 -07:00
comfyanonymous
0d8b7510bd
Update extra model paths example. ( #14570 )
2026-06-20 19:28:09 -07:00
comfyanonymous
e00b55631a
Small anima optimization. ( #14557 )
2026-06-20 08:05:28 +08:00
comfyanonymous