comfyanonymous
438c3a650c
Fix custom nodes import error.
...
This should fix the import errors but will break if the custom nodes actually try to use the class.
2025-11-14 03:25:38 -05:00
comfyanonymous
f60923590c
Use same code for chroma and flux blocks so that optimizations are shared. ( #10746 )
2025-11-14 01:28:05 -05:00
comfyanonymous
1ef328c007
Better instructions for the portable. ( #10743 )
2025-11-13 21:32:39 -05:00
rattus
94c298f962
flux: reduce VRAM usage ( #10737 )
...
Cleanup a bunch of stack tensors on Flux. This take me from B=19 to B=22
for 1600x1600 on RTX5090.
2025-11-13 16:02:03 -08:00
ric-yu
2fde9597f4
feat: add create_time dict to prompt field in /history and /queue ( #10741 )
2025-11-13 15:11:52 -08:00
Alexander Piskun
f91078b1ff
add PR template for API-Nodes ( #10736 )
2025-11-13 10:05:26 -08:00
contentis
3b3ef9a77a
Quantized Ops fixes ( #10715 )
...
* offload support, bug fixes, remove mixins
* add readme
2025-11-12 18:26:52 -05:00
comfyanonymous
8b0b93df51
Update Python 3.14 compatibility notes in README ( #10730 )
2025-11-12 17:04:41 -05:00
rattus
1c7eaeca10
qwen: reduce VRAM usage ( #10725 )
...
Clean up a bunch of stacked and no-longer-needed tensors on the QWEN
VRAM peak (currently FFN).
With this I go from OOMing at B=37x1328x1328 to being able to
succesfully run B=47 (RTX5090).
2025-11-12 16:20:53 -05:00
rattus
18e7d6dba5
mm/mp: always unload re-used but modified models ( #10724 )
...
The partial unloader path in model re-use flow skips straight to the
actual unload without any check of the patching UUID. This means that
if you do an upscale flow with a model patch on an existing model, it
will not apply your patchings.
Fix by delaying the partial_unload until after the uuid checks. This
is done by making partial_unload a model of partial_load where extra_mem
is -ve.
2025-11-12 16:19:53 -05:00
Qiacheng Li
e1d85e7577
Update README.md for Intel Arc GPU installation, remove IPEX ( #10729 )
...
IPEX is no longer needed for Intel Arc GPUs. Removing instruction to setup ipex.
2025-11-12 15:21:05 -05:00
comfyanonymous
1199411747
Don't pin tensor if not a torch.nn.parameter.Parameter ( #10718 )
2025-11-11 19:33:30 -05:00
comfyanonymous
5ebcab3c7d
Update CI workflow to remove dead macOS runner. ( #10704 )
...
* Update CI workflow to remove dead macOS runner.
* revert
* revert
2025-11-10 15:35:29 -05:00
rattus
c350009236
ops: Put weight cast on the offload stream ( #10697 )
...
This needs to be on the offload stream. This reproduced a black screen
with low resolution images on a slow bus when using FP8.
2025-11-09 22:52:11 -05:00
comfyanonymous
dea899f221
Unload weights if vram usage goes up between runs. ( #10690 )
2025-11-09 18:51:33 -05:00
comfyanonymous
e632e5de28
Add logging for model unloading. ( #10692 )
2025-11-09 18:06:39 -05:00
comfyanonymous
2abd2b5c20
Make ScaleROPE node work on Flux. ( #10686 )
2025-11-08 15:52:02 -05:00
comfyanonymous
a1a70362ca
Only unpin tensor if it was pinned by ComfyUI ( #10677 )
2025-11-07 11:15:05 -05:00
rattus
cf97b033ee
mm: guard against double pin and unpin explicitly ( #10672 )
...
As commented, if you let cuda be the one to detect double pin/unpinning
it actually creates an asyc GPU error.
2025-11-06 21:20:48 -05:00
comfyanonymous
eb1c42f649
Tell users they need to upload their logs in bug reports. ( #10671 )
2025-11-06 20:24:28 -05:00
comfyanonymous
e05c907126
Clarify release cycle. ( #10667 )
2025-11-06 04:11:30 -05:00
comfyanonymous
09dc24c8a9
Pinned mem also seems to work on AMD. ( #10658 )
2025-11-05 19:11:15 -05:00
comfyanonymous
1d69245981
Enable pinned memory by default on Nvidia. ( #10656 )
...
Removed the --fast pinned_memory flag.
You can use --disable-pinned-memory to disable it. Please report if it
causes any issues.
2025-11-05 18:08:13 -05:00
comfyanonymous
97f198e421
Fix qwen controlnet regression. ( #10657 )
2025-11-05 18:07:35 -05:00
Alexander Piskun
bda0eb2448
feat(API-nodes): move Rodin3D nodes to new client; removed old api client.py ( #10645 )
2025-11-05 02:16:00 -08:00
comfyanonymous
c4a6b389de
Lower ltxv mem usage to what it was before previous pr. ( #10643 )
...
Bring back qwen behavior to what it was before previous pr.
2025-11-04 22:47:35 -05:00
contentis
4cd881866b
Use single apply_rope function across models ( #10547 )
2025-11-04 20:10:11 -05:00
comfyanonymous
265adad858
ComfyUI version v0.3.68
2025-11-04 19:42:23 -05:00
comfyanonymous
7f3e4d486c
Limit amount of pinned memory on windows to prevent issues. ( #10638 )
2025-11-04 17:37:50 -05:00
rattus
a389ee01bb
caching: Handle None outputs tuple case ( #10637 )
2025-11-04 14:14:10 -08:00
ComfyUI Wiki
9c71a66790
chore: update workflow templates to v0.2.11 ( #10634 )
2025-11-04 10:51:53 -08:00
comfyanonymous
af4b7b5edb
More fp8 torch.compile regressions fixed. ( #10625 )
2025-11-03 22:14:20 -05:00
comfyanonymous
0f4ef3afa0
This seems to slow things down slightly on Linux. ( #10624 )
2025-11-03 21:47:14 -05:00
comfyanonymous
6b88478f9f
Bring back fp8 torch compile performance to what it should be. ( #10622 )
2025-11-03 19:22:10 -05:00
comfyanonymous
e199c8cc67
Fixes ( #10621 )
2025-11-03 17:58:24 -05:00
comfyanonymous
0652cb8e2d
Speed up torch.compile ( #10620 )
2025-11-03 17:37:12 -05:00
comfyanonymous
958a17199a
People should update their pytorch versions. ( #10618 )
2025-11-03 17:08:30 -05:00
ComfyUI Wiki
e974e554ca
chore: update embedded docs to v0.3.1 ( #10614 )
2025-11-03 10:59:44 -08:00
Alexander Piskun
4e2110c794
feat(Pika-API-nodes): use new API client ( #10608 )
2025-11-03 00:29:08 -08:00
Alexander Piskun
e617cddf24
convert nodes_openai.py to V3 schema ( #10604 )
2025-11-03 00:28:13 -08:00
Alexander Piskun
1f3f7a2823
convert nodes_hypernetwork.py to V3 schema ( #10583 )
2025-11-03 00:21:47 -08:00
EverNebula
88df172790
fix(caching): treat bytes as hashable ( #10567 )
2025-11-03 00:16:40 -08:00
Alexander Piskun
6d6a18b0b7
fix(api-nodes-cloud): stop using sub-folder and absolute path for output of Rodin3D nodes ( #10556 )
2025-11-03 00:04:56 -08:00
comfyanonymous
97ff9fae7e
Clarify help text for --fast argument ( #10609 )
...
Updated help text for the --fast argument to clarify potential risks.
2025-11-02 13:14:04 -05:00
rattus
135fa49ec2
Small speed improvements to --async-offload ( #10593 )
...
* ops: dont take an offload stream if you dont need one
* ops: prioritize mem transfer
The async offload streams reason for existence is to transfer from
RAM to GPU. The post processing compute steps are a bonus on the side
stream, but if the compute stream is running a long kernel, it can
stall the side stream, as it wait to type-cast the bias before
transferring the weight. So do a pure xfer of the weight straight up,
then do everything bias, then go back to fix the weight type and do
weight patches.
2025-11-01 18:48:53 -04:00
comfyanonymous
44869ff786
Fix issue with pinned memory. ( #10597 )
2025-11-01 17:25:59 -04:00
Alexander Piskun
20182a393f
convert StabilityAI to use new API client ( #10582 )
2025-11-01 12:14:06 -07:00
Alexander Piskun
5f109fe6a0
added 12s-20s as available output durations for the LTXV API nodes ( #10570 )
2025-11-01 12:13:39 -07:00
comfyanonymous
c58c13b2ba
Fix torch compile regression on fp8 ops. ( #10580 )
2025-11-01 00:25:17 -04:00
comfyanonymous
7f374e42c8
ScaleROPE now works on Lumina models. ( #10578 )
2025-10-31 15:41:40 -04:00
