bigcat88
|
21c9d7b289
|
V3 controlnet nodes: ControlNetApply, SetUnionControlNetType, ControlNetInpaintingAliMamaApply
|
2025-07-11 22:34:22 +03:00 |
|
bigcat88
|
d8b91bb84e
|
put V1 nodes back
|
2025-07-10 07:58:34 +03:00 |
|
bigcat88
|
965d2f9b8f
|
use options key, remove get_io_type_V1 serialization
|
2025-07-10 06:47:52 +03:00 |
|
bigcat88
|
8f0621ca7e
|
IS_CHANGED->fingerprint_inputs , VALIDATE_INPUTS->validate_inputs
|
2025-07-09 14:02:28 +03:00 |
|
bigcat88
|
fefb24cc33
|
fixes, corrections; ported MaskPreview, WebcamCapture and LoadImageOutput nodes
|
2025-07-09 13:37:57 +03:00 |
|
kosinkadink1@gmail.com
|
5f91e2905a
|
Merge branch 'v3-definition' of https://github.com/comfyanonymous/ComfyUI into v3-definition
|
2025-07-09 03:58:16 -05:00 |
|
kosinkadink1@gmail.com
|
3aa2d19c70
|
Merge branch 'master' into v3-definition
|
2025-07-09 03:58:09 -05:00 |
|
kosinkadink1@gmail.com
|
56ccfeaa8a
|
Add fingerprint_inputs support (V3's IS_CHANGED)
|
2025-07-09 03:25:23 -05:00 |
|
kosinkadink1@gmail.com
|
82e6eeab75
|
Support validate_inputs for v3 replacing VALIDATE_INPUTS, support check_lazy_mix for v3, prep for renaming IS_CHANGED to fingerprint_inputs, reorder some class methods
|
2025-07-09 02:26:35 -05:00 |
|
kosinkadink1@gmail.com
|
a86fddcdd4
|
Fixed MultiCombo, confirmed VALIDATE_INPUTS, IS_CHANGED works
|
2025-07-09 00:26:15 -05:00 |
|
Kohaku-Blueleaf
|
181a9bf26d
|
Support Multi Image-Caption dataset in lora training node (#8819)
* initial impl of multi img/text dataset
* Update nodes_train.py
* Support Kohya-ss structure
|
2025-07-08 20:18:04 -04:00 |
|
chaObserv
|
aac10ad23a
|
Add SA-Solver sampler (#8834)
|
2025-07-08 16:17:06 -04:00 |
|
comfyanonymous
|
e740dfd806
|
Fix warning in audio save nodes. (#8818)
|
2025-07-07 03:16:00 -04:00 |
|
comfyanonymous
|
7eab7d2944
|
Remove dependency on deprecated torchaudio.save function (#8815)
|
2025-07-06 14:01:32 -04:00 |
|
Jedrzej Kosinski
|
18a7207ca4
|
Mock AutogrowDynamic type
|
2025-07-04 16:27:03 -05:00 |
|
comfyanonymous
|
f74fc4d927
|
Add ImageRotate and ImageFlip nodes. (#8789)
|
2025-07-03 19:16:30 -04:00 |
|
City
|
d9277301d2
|
Initial code for new SLG node (#8759)
|
2025-07-02 20:13:43 -04:00 |
|
comfyanonymous
|
34c8eeec06
|
Fix ImageColorToMask not returning right mask values. (#8771)
|
2025-07-02 15:35:11 -04:00 |
|
Harel Cain
|
9f1069290c
|
nodes_lt: fixes to latent conditioning at index > 0 (#8769)
|
2025-07-02 15:34:51 -04:00 |
|
Terry Jia
|
79ed752748
|
support upload 3d model to custom subfolder (#8597)
|
2025-07-01 20:43:48 -04:00 |
|
comfyanonymous
|
772de7c006
|
PerpNeg Guider optimizations. (#8753)
|
2025-07-01 03:09:07 -04:00 |
|
chaObserv
|
b22e97dcfa
|
Migrate ER-SDE from VE to VP algorithm and add its sampler node (#8744)
Apply alpha scaling in the algorithm for reverse-time SDE and add custom ER-SDE sampler node for other solver types (SDE, ODE).
|
2025-07-01 02:38:52 -04:00 |
|
chaObserv
|
f02de13316
|
Add TCFG node (#8730)
|
2025-07-01 02:33:07 -04:00 |
|
comfyanonymous
|
cf49a2c5b5
|
Dual cfg node optimizations when cfg is 1.0 (#8747)
|
2025-06-30 14:18:25 -04:00 |
|
Jedrzej Kosinski
|
3758c65107
|
Extracted resources to separate file
|
2025-06-28 16:46:45 -07:00 |
|
Jedrzej Kosinski
|
0e7ff98e1d
|
Introduced Resources to ComfyNodeV3
|
2025-06-28 15:47:02 -07:00 |
|
chaObserv
|
5b4eb021cb
|
Perpneg guider with updated pre and post-cfg (#8698)
|
2025-06-28 18:13:13 -04:00 |
|
Jedrzej Kosinski
|
2999212480
|
Moved ui preview-related classes out of io.py and into ui.py, refactored UIImages and related into PreviewImage and related
|
2025-06-28 13:53:25 -07:00 |
|
Jedrzej Kosinski
|
cef73c75fb
|
Fix recognizing ComfyNodeV3 class by using issubclass, removed override decorator as it was only introduced in py3.12
|
2025-06-27 14:00:20 -07:00 |
|
Jedrzej Kosinski
|
aefd845a21
|
Multitype refactor progress
|
2025-06-26 15:41:49 -07:00 |
|
Jedrzej Kosinski
|
6ef4ad2a4c
|
Merge branch 'master' into v3-definition-wip
|
2025-06-26 12:45:20 -07:00 |
|
Jedrzej Kosinski
|
6d64658c79
|
Added get_value and set_value to NodeState, small cleanup
|
2025-06-26 12:44:08 -07:00 |
|
comfyanonymous
|
ef5266b1c1
|
Support Flux Kontext Dev model. (#8679)
|
2025-06-26 11:28:41 -04:00 |
|
comfyanonymous
|
ec70ed6aea
|
Omnigen2 model implementation. (#8669)
|
2025-06-25 19:35:57 -04:00 |
|
comfyanonymous
|
bd9f166c12
|
Cosmos predict2 model merging nodes. (#8647)
|
2025-06-24 05:17:16 -04:00 |
|
comfyanonymous
|
ae0e7c4dff
|
Resize and pad image node. (#8636)
|
2025-06-22 17:59:31 -04:00 |
|
comfyanonymous
|
78f79266a9
|
Allow padding in ImageStitch node to be white. (#8631)
|
2025-06-22 00:19:41 -04:00 |
|
Jedrzej Kosinski
|
6cf5db512a
|
Small refactor of V3TestNode
|
2025-06-19 04:55:05 -05:00 |
|
Jedrzej Kosinski
|
fe9a47ae50
|
Added V3 LoRA Loader node for test purposes, made NodeStateLocal more versatile with dict-like behavior and not throwing errors when nonexisting parameter is requested, returning None instead
|
2025-06-19 02:17:36 -05:00 |
|
Jedrzej Kosinski
|
ef3f45807f
|
Added multitype support for Widget Inputs via the types argument, MultiType.Input io_types renamed to types
|
2025-06-19 01:22:03 -05:00 |
|
Jedrzej Kosinski
|
11d87760ca
|
Renamed Hidden->HiddenHolder, HiddenEnum->Hidden for ease of usage, cls.hidden will only have values given for corresponding entries in the schema's hidden entry, fixed v3 node check in execution.get_input_data, some cleanup of whitespace and commented out code
|
2025-06-19 00:10:28 -05:00 |
|
Jedrzej Kosinski
|
f9aec12ef1
|
Refactored v3 code so that v3_01 becomes v3, v3_01 is deleted since no longer necessary
|
2025-06-18 23:29:32 -05:00 |
|
Jedrzej Kosinski
|
38721fdb64
|
Added hidden and state to passed-in clone of node class
|
2025-06-17 20:35:32 -05:00 |
|
Jedrzej Kosinski
|
1ef0693e65
|
Merge branch 'master' into v3-definition
|
2025-06-17 04:48:27 -05:00 |
|
Jedrzej Kosinski
|
1711e44e99
|
Added new Custom and ComfyTypeIO helpers, use ComfyTypeIO class to simplify defining basic types
|
2025-06-17 04:47:55 -05:00 |
|
comfyanonymous
|
ae75a084df
|
SaveLora now saves in the same filename format as all the other nodes. (#8538)
|
2025-06-15 03:44:59 -04:00 |
|
comfyanonymous
|
d6a2137fc3
|
Support Cosmos predict2 image to video models. (#8535)
Use the CosmosPredict2ImageToVideoLatent node.
|
2025-06-14 21:37:07 -04:00 |
|
Kohaku-Blueleaf
|
520eb77b72
|
LoRA Trainer: LoRA training node in weight adapter scheme (#8446)
|
2025-06-13 19:25:59 -04:00 |
|
comfyanonymous
|
5bf69bde35
|
Add cosmos_rflow option to ModelSamplingContinuousEDM node. (#8523)
This is for the cosmos predict2 model.
|
2025-06-13 17:47:52 -04:00 |
|
kosinkadink1@gmail.com
|
54e0d6b161
|
Add comfytype decorator, convert all relevant v3_01 types to follow new convention, make v1 test node have xyz be optional
|
2025-06-13 04:06:06 -07:00 |
|