Jedrzej Kosinski
7a81095476
Merge branch 'master' into v3-dynamic-combo
2025-11-19 00:17:09 -08:00
comfyanonymous
17027f2a6a
Add a way to disable the final norm in the llama based TE models. ( #10794 )
2025-11-18 22:36:03 -05:00
comfyanonymous
b5c8be8b1d
ComfyUI 0.3.70
2025-11-18 19:37:20 -05:00
Alexander Piskun
24fdb92edf
feat(api-nodes): add new Gemini model ( #10789 )
2025-11-18 14:26:44 -08:00
comfyanonymous
d526974576
Fix hunyuan 3d 2.0 ( #10792 )
2025-11-18 16:46:19 -05:00
Jedrzej Kosinski
910e0690a3
MatchType does not need any DynamicInput/Output features on backend; will increase compatibility with dynamic types
2025-11-18 07:15:20 -08:00
Jukka Seppänen
e1ab6bb394
EasyCache: Fix for mismatch in input/output channels with some models ( #10788 )
...
Slices model input with output channels so the caching tracks only the noise channels, resolves channel mismatch with models like WanVideo I2V
Also fix for slicing deprecation in pytorch 2.9
2025-11-18 07:00:21 -08:00
Jedrzej Kosinski
ffe77c2959
Make execution.validate_inputs properly validate required dynamic inputs, renamed dynamic_data to dynamic_paths for clarity
2025-11-18 06:20:09 -08:00
Jedrzej Kosinski
85edfc8e6b
Remove array support from build_nested_inputs, properly handle missing expected values
2025-11-18 05:17:18 -08:00
Jedrzej Kosinski
8653d8b0bf
Add nested combo to DCTestNode
2025-11-18 05:16:20 -08:00
Jedrzej Kosinski
bbc3ecd1b1
Create test nodes for Autogrow to collab with frontend development
2025-11-18 04:43:52 -08:00
Alexander Piskun
048f49adbd
chore(api-nodes): adjusted PR template; set min python version for pylint to 3.10 ( #10787 )
2025-11-18 03:59:27 -08:00
Jedrzej Kosinski
712e61d535
satisfy ruff
2025-11-18 03:46:15 -08:00
Jedrzej Kosinski
e28063811f
Prepare Autogrow support for the love of the game
2025-11-18 03:33:28 -08:00
Jedrzej Kosinski
47128ee279
frontend will no longer namespace dynamic inputs widgets so reflect that in code, refactor build_nested_inputs
2025-11-18 01:41:25 -08:00
comfyanonymous
47bfd5a33f
Native block swap custom nodes considered harmful. ( #10783 )
2025-11-18 00:26:44 -05:00
Jedrzej Kosinski
122c9d5362
Fix cringe arrows
2025-11-17 20:24:41 -08:00
Jedrzej Kosinski
f8d0925444
Work with latest frontend commits
2025-11-17 19:42:55 -08:00
ComfyUI Wiki
fdf49a2861
Fix the portable download link for CUDA 12.6 ( #10780 )
2025-11-17 22:04:06 -05:00
Jedrzej Kosinski
75cc2194ff
Add nesting of inputs on DynamicCombo during execution
2025-11-17 18:49:24 -08:00
comfyanonymous
f41e5f398d
Update README with new portable download link ( #10778 )
2025-11-17 19:59:19 -05:00
comfyanonymous
27cbac865e
Add release workflow for NVIDIA cu126 ( #10777 )
2025-11-17 19:04:04 -05:00
Jedrzej Kosinski
159e2d02c9
Refactor hidden_values for v3 in execution.py to be more general v3_data, add helper functions for dynamic behavior, preparing for restructuring dynamic type into object (not finished yet)
2025-11-17 15:50:49 -08:00
comfyanonymous
3d0003c24c
ComfyUI version 0.3.69
2025-11-17 17:17:24 -05:00
Jedrzej Kosinski
ff392b1fb3
Fix v3 schema validation code after changes
2025-11-17 12:23:46 -08:00
Jedrzej Kosinski
3e36b0a599
Modifying behavior of get_dynamic in V3 + serialization so can be used in execution code
2025-11-17 12:20:42 -08:00
comfyanonymous
7d6103325e
Change ROCm nightly install command to 7.1 ( #10764 )
2025-11-16 03:01:14 -05:00
Kosinkadink
09b9054750
Fix imports for v3 returning everything when doing io/ui/IO/UI instead of what is in __all__ of _io.py and _ui.py
2025-11-15 23:27:21 -08:00
Kosinkadink
a89903e425
Add get_all function to inputs for id validation purposes
2025-11-15 23:26:32 -08:00
Kosinkadink
8a0a00442b
Add missing input params to DynamicCombo.Input
2025-11-15 22:07:11 -08:00
Kosinkadink
68153f6c04
Support validation of inputs and outputs
2025-11-15 21:59:28 -08:00
Kosinkadink
676de9e618
add dynamic combo test node
2025-11-15 21:07:30 -08:00
Kosinkadink
4aaf0452e1
Send DynamicCombo.Option inputs in the same format as normal v1 inputs
2025-11-15 21:00:43 -08:00
Alexander Piskun
2d4a08b717
Revert "chore(api-nodes): mark OpenAIDalle2 and OpenAIDalle3 nodes as deprecated ( #10757 )" ( #10759 )
...
This reverts commit 9a02382568
2025-11-15 12:37:34 -08:00
Alexander Piskun
9a02382568
chore(api-nodes): mark OpenAIDalle2 and OpenAIDalle3 nodes as deprecated ( #10757 )
2025-11-15 11:18:49 -08:00
comfyanonymous
bd01d9f7fd
Add left padding support to tokenizers. ( #10753 )
2025-11-15 06:54:40 -05:00
comfyanonymous
443056c401
Fix custom nodes import error. ( #10747 )
...
This should fix the import errors but will break if the custom nodes actually try to use the class.
2025-11-14 03:26:05 -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
Jedrzej Kosinski
13aa23dff4
Make sure other unfinished dynamic types are not accidentally used
2025-11-13 15:49:41 -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
Jedrzej Kosinski
59381ecbd2
Add get_dynamic function, not yet filled out correctly
2025-11-12 23:24:39 -08:00
Jedrzej Kosinski
e3ba819d2c
Initial work on DynamicCombo
2025-11-12 18:46:15 -08:00
Jedrzej Kosinski
33bbf75eeb
Mark Switch node as Beta
2025-11-12 17:44:42 -08:00
Jedrzej Kosinski
ef4179e894
Merge branch 'master' into v3-match-type
2025-11-12 23:25:58 -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
