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
doctorpangloss
4f6615e939
Merge branch 'develop'
2025-11-10 11:51:58 -08:00
doctorpangloss
83fddf4cb5
fix tagging
2025-11-10 11:51:49 -08:00
doctorpangloss
37048fc1a2
fix issues with zooming in editor, simplify, improve list inputs and outputs
2025-11-10 11:23:34 -08:00
Benjamin Berman
cc5f16caeb
tweak
2025-11-10 10:06:14 -08:00
Benjamin Berman
0d9232f02c
wip python eval nodes
2025-11-10 09:47:27 -08:00
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
doctorpangloss
8700c4fadf
wip eval nodes, test tracing with full integration test, fix dockerfile barfing on flash_attn 2.8.3
2025-11-07 16:50:55 -08:00
doctorpangloss
69d8f1b120
Tracing tests
2025-11-07 14:27:31 -08:00
doctorpangloss
2f520a4cb4
Workflow templates constraint
2025-11-07 14:27:25 -08:00
Benjamin Berman
1294221929
Version 0.3.0 workflow templates and later are not compatible with 0.3.66
2025-11-07 14:02:58 -08:00
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
doctorpangloss
243f34f282
Improve OpenAPI contract in distributed context, propagating validation and execution errors correctly.
2025-11-06 12:54:35 -08:00
Benjamin Berman
be255c2691
wip align openapi and api methods for error handling
2025-11-06 11:11:46 -08:00
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
doctorpangloss
152524e8b1
Fix docker image containing random text files in it
2025-11-04 19:22:26 -08:00
doctorpangloss
7f7bcd5d8f
Fix tests (no rerelease necessary)
2025-11-04 18:33:31 -08:00
doctorpangloss
cb97b94ad9
Unclear why this is throwing linting errors
2025-11-04 18:15:54 -08:00
doctorpangloss
4b336543db
Update README.md
2025-11-04 17:43:22 -08:00
doctorpangloss
98ae55b059
Improvements to compatibility with custom nodes, distributed
...
backends and other changes
- remove uv.lock since it will not be used in most cases for installation
- add cli args to prevent some custom nodes from installing packages at runtime
- temp directories can now be shared between workers without being deleted
- propcache yanked is now in the dependencies
- fix configuration arguments loading in some tests
2025-11-04 17:40:19 -08:00
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
