comfyanonymous/ComfyUI
1
0
Fork 0
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2026-02-06 00:00:06 +00:00
Code Issues Packages Projects Releases Wiki Activity
4,311 Commits 90 Branches 117 Tags
de357a01f8d2f06609e768eb07f9491c02da58db
Commit Graph

1857 Commits

Author SHA1 Message Date
Dr.Lt.Data
fe26f30cb6 Merge branch 'master' into dr-support-pip-cm 2025-10-26 12:52:08 +09:00
comfyanonymous
f6bbc1ac84 Fix mistake. (#10484) 2025-10-25 23:07:29 -04:00
comfyanonymous
098a352f13 Add warning for torch-directml usage (#10482) 
Added a warning message about the state of torch-directml.
 2025-10-25 20:05:22 -04:00
Dr.Lt.Data
3c4b429251 Merge branch 'master' into dr-support-pip-cm 2025-10-25 10:42:34 +09:00
comfyanonymous
426cde37f1 Remove useless function (#10472) 2025-10-24 19:56:51 -04:00
Dr.Lt.Data
0432bccbcf Merge branch 'master' into dr-support-pip-cm 2025-10-24 12:17:46 +09:00
comfyanonymous
1bcda6df98 WIP way to support multi multi dimensional latents. (#10456) 2025-10-23 21:21:14 -04:00
Dr.Lt.Data
aaf06ace12 Merge branch 'master' into dr-support-pip-cm 2025-10-23 06:54:58 +09:00
comfyanonymous
9cdc64998f Only disable cudnn on newer AMD GPUs. (#10437) 2025-10-21 19:15:23 -04:00
Dr.Lt.Data
a1a6f4d7fe Merge branch 'master' into dr-support-pip-cm 2025-10-21 07:26:53 +09:00
comfyanonymous
2c2aa409b0 Log message for cudnn disable on AMD. (#10418) 2025-10-20 15:43:24 -04:00
Dr.Lt.Data
ee54914a52 Merge branch 'master' into dr-support-pip-cm 2025-10-20 06:35:52 +09:00
comfyanonymous
b4f30bd408 Pytorch is stupid. (#10398) 2025-10-19 01:25:35 -04:00
comfyanonymous
dad076aee6 Speed up chroma radiance. (#10395) 2025-10-18 23:19:52 -04:00
comfyanonymous
0cf33953a7 Fix batch size above 1 giving bad output in chroma radiance. (#10394) 2025-10-18 23:15:34 -04:00
Dr.Lt.Data
8f59e2a341 Merge branch 'master' into dr-support-pip-cm 2025-10-19 11:39:42 +09:00
comfyanonymous
5b80addafd Turn off cuda malloc by default when --fast autotune is turned on. (#10393) 2025-10-18 22:35:46 -04:00
Dr.Lt.Data
7d5e73ea94 Merge branch 'master' into dr-support-pip-cm 2025-10-19 09:37:12 +09:00
comfyanonymous
9da397ea2f Disable torch compiler for cast_bias_weight function (#10384) 
* Disable torch compiler for cast_bias_weight function

* Fix torch compile.
 2025-10-17 20:03:28 -04:00
Dr.Lt.Data
6626f7c5c4 Merge branch 'master' into dr-support-pip-cm 2025-10-17 12:42:54 +09:00
comfyanonymous
b1293d50ef workaround also works on cudnn 91200 (#10375) 2025-10-16 19:59:56 -04:00
comfyanonymous
19b466160c Workaround for nvidia issue where VAE uses 3x more memory on torch 2.9 (#10373) 2025-10-16 18:16:03 -04:00
Dr.Lt.Data
0802f3a635 Merge branch 'master' into dr-support-pip-cm 2025-10-16 12:06:19 +09:00
Faych
afa8a24fe1 refactor: Replace manual patches merging with merge_nested_dicts (#10360) 2025-10-15 17:16:09 -07:00
Jedrzej Kosinski
493b81e48f Fix order of inputs nested merge_nested_dicts (#10362) 2025-10-15 16:47:26 -07:00
Dr.Lt.Data
19ad129d37 Merge branch 'master' into dr-support-pip-cm 2025-10-16 06:40:04 +09:00
comfyanonymous
1c10b33f9b gfx942 doesn't support fp8 operations. (#10348) 2025-10-15 00:21:11 -04:00
Dr.Lt.Data
5fbc8a1b80 Merge branch 'master' into dr-support-pip-cm 2025-10-15 06:43:20 +09:00
comfyanonymous
3374e900d0 Faster workflow cancelling. (#10301) 2025-10-13 23:43:53 -04:00
Dr.Lt.Data
b180f47d0e Merge branch 'master' into dr-support-pip-cm 2025-10-14 12:34:58 +09:00
comfyanonymous
dfff7e5332 Better memory estimation for the SD/Flux VAE on AMD. (#10334) 2025-10-13 22:37:19 -04:00
comfyanonymous
e4ea393666 Fix loading old stable diffusion ckpt files on newer numpy. (#10333) 2025-10-13 22:18:58 -04:00
comfyanonymous
c8674bc6e9 Enable RDNA4 pytorch attention on ROCm 7.0 and up. (#10332) 2025-10-13 21:19:03 -04:00
Dr.Lt.Data
2b47f4a38e Merge branch 'master' into dr-support-pip-cm 2025-10-14 07:36:42 +09:00
rattus128
95ca2e56c8 WAN2.2: Fix cache VRAM leak on error (#10308) 
Same change pattern as 7e8dd275c2
applied to WAN2.2

If this suffers an exception (such as a VRAM oom) it will leave the
encode() and decode() methods which skips the cleanup of the WAN
feature cache. The comfy node cache then ultimately keeps a reference
this object which is in turn reffing large tensors from the failed
execution.

The feature cache is currently setup at a class variable on the
encoder/decoder however, the encode and decode functions always clear
it on both entry and exit of normal execution.

Its likely the design intent is this is usable as a streaming encoder
where the input comes in batches, however the functions as they are
today don't support that.

So simplify by bringing the cache back to local variable, so that if
it does VRAM OOM the cache itself is properly garbage when the
encode()/decode() functions dissappear from the stack.
 2025-10-13 15:23:11 -04:00
comfyanonymous
e693e4db6a Always set diffusion model to eval() mode. (#10331) 2025-10-13 14:57:27 -04:00
Dr.Lt.Data
5f50b86114 Merge branch 'master' into dr-support-pip-cm 2025-10-13 06:42:04 +09:00
comfyanonymous
a125cd84b0 Improve AMD performance. (#10302) 
I honestly have no idea why this improves things but it does.
 2025-10-12 00:28:01 -04:00
comfyanonymous
84e9ce32c6 Implement the mmaudio VAE. (#10300) 2025-10-11 22:57:23 -04:00
Dr.Lt.Data
4e7f2eeae2 Merge branch 'master' into dr-support-pip-cm 2025-10-10 08:15:03 +09:00
comfyanonymous
f1dd6e50f8 Fix bug with applying loras on fp8 scaled without fp8 ops. (#10279) 2025-10-09 19:02:40 -04:00
comfyanonymous
139addd53c More surgical fix for #10267 (#10276) 2025-10-09 16:37:35 -04:00
Dr.Lt.Data
05cd5348b6 Merge branch 'master' into dr-support-pip-cm 2025-10-09 10:49:23 +09:00
comfyanonymous
6e59934089 Refactor model sampling sigmas code. (#10250) 2025-10-08 17:49:02 -04:00
Dr.Lt.Data
6b20418ad1 Merge branch 'master' into dr-support-pip-cm 2025-10-07 14:30:16 +09:00
comfyanonymous
8aea746212 Implement gemma 3 as a text encoder. (#10241) 
Not useful yet.
 2025-10-06 22:08:08 -04:00
comfyanonymous
195e0b0639 Remove useless code. (#10223) 2025-10-05 15:41:19 -04:00
Dr.Lt.Data
8634b19bc7 Merge branch 'master' into dr-support-pip-cm 2025-10-04 07:09:43 +09:00
Finn-Hecker
93d859cfaa Fix type annotation syntax in MotionEncoder_tc __init__ (#10186) 
## Summary
Fixed incorrect type hint syntax in `MotionEncoder_tc.__init__()` parameter list.

## Changes
- Line 647: Changed `num_heads=int` to `num_heads: int` 
- This corrects the parameter annotation from a default value assignment to proper type hint syntax

## Details
The parameter was using assignment syntax (`=`) instead of type annotation syntax (`:`), which would incorrectly set the default value to the `int` class itself rather than annotating the expected type.
 2025-10-03 14:32:19 -07:00
Dr.Lt.Data
28092933c1 Merge branch 'master' into dr-support-pip-cm 2025-10-02 12:49:48 +09:00