766ae119a8
CheckpointSave node name.
6 months ago
310ad09258
Add a ModelSave node.
6 months ago
a475ec2300
Cleanup HunyuanDit controlnets.
...
Use the: ControlNetApply SD3 and HunyuanDiT node.
7 months ago
06eb9fb426
feat: add support for HunYuanDit ControlNet ( #4245 )
...
* add support for HunYuanDit ControlNet
* fix hunyuandit controlnet
* fix typo in hunyuandit controlnet
* fix typo in hunyuandit controlnet
* fix code format style
* add control_weight support for HunyuanDit Controlnet
* use control_weights in HunyuanDit Controlnet
* fix typo
7 months ago
f3bc40223a
Add format metadata to CLIP save to make compatible with diffusers safetensors loading ( #4233 )
7 months ago
ddb6a9f47c
Set the step in EmptySD3LatentImage to 16.
...
These models work better when the res is a multiple of 16.
7 months ago
56f3c660bf
ModelSamplingFlux now takes a resolution and adjusts the shift with it.
...
If you want to sample Flux dev exactly how the reference code does use
the same resolution as your image in this node.
7 months ago
0eea47d580
Add ModelSamplingFlux to experiment with the shift value.
...
Default shift on Flux Schnell is 0.0
7 months ago
7cd0cdfce6
Add advanced model merge node for Flux model.
7 months ago
bfb52de866
Lower SAG scale step for finer control ( #4158 )
...
* Lower SAG step for finer control
Since the introduction of cfg++ which uses very low cfg value, a step of 0.1 in SAG might be too high for finer control. Even SAG of 0.1 can be too high when cfg is only 0.6, so I change the step to 0.01.
* Lower PAG step as well.
* Update nodes_sag.py
7 months ago
eca962c6da
Add FluxGuidance node.
...
This lets you adjust the guidance on the dev model which is a parameter
that is passed to the diffusion model.
7 months ago
c1696cd1b5
Add missing import ( #4174 )
7 months ago
a531001cc7
Add CLIPTextEncodeFlux.
7 months ago
9300058026
Add dpmpp_2s_ancestral as custom sampler ( #4101 )
...
Adding dpmpp_2s_ancestral as custom sampler node to enable its use with eta and s_noise when using custom sampling.
7 months ago
6225a7827c
Add CLIPTextEncodeHunyuanDiT.
...
Useful for testing what each text encoder does.
7 months ago
b2c995f623
"auto" type is only relevant to the SetUnionControlNetType node.
7 months ago
4151fbfa8a
Add error message on union controlnet ( #4081 )
7 months ago
f836e69346
Fix bug with SaveAudio node with --gpu-only
7 months ago
6ab8cad22e
Implement beta sampling scheduler.
...
It is based on: https://arxiv.org/abs/2407.12173
Add "beta" to the list of schedulers and the BetaSamplingScheduler node.
7 months ago
ff6ca2a892
Move PAG to model_patches/unet section.
...
Move other unet model_patches nodes to model_patches/unet section.
7 months ago
60383f3b64
Move controlnet nodes to conditioning/controlnet.
7 months ago
8270c62530
Add SetUnionControlNetType to set the type of the union controlnet model.
7 months ago
8e012043a9
Add a ModelSamplingAuraFlow node to change the shift value.
...
Set the default AuraFlow shift value to 1.73 (sqrt(3)).
8 months ago
628f0b8ebc
Move audio nodes out of _for_testing.
8 months ago
01991f72ce
Fix SamplerEulerCFGpp node.
8 months ago
b82d67d5bf
Add SamplerEulerAncestralCFG++ custom sampler node ( #3901 )
...
(for eta and s_noise)
8 months ago
fbb7a1f1b6
PreviewAudio node.
8 months ago
7ecb2ec169
Audio second setting in EmptyLatentAudio.
8 months ago
264caca20e
ControlNetApplySD3 node can now be used to use SD3 controlnets.
8 months ago
4650e7d6e9
Save and load workflow from the flac files output by SaveAudio.
8 months ago
3b423afcca
Add audio widget ( #3863 )
...
* Add audio widget
* Fix audio bugs
* Add CSS
* Populate audio widget when load history
8 months ago
69d710e40f
Implement my alternative take on CFG++ as the euler_pp sampler.
...
Add euler_ancestral_pp which is the ancestral version of euler with the
same modification.
8 months ago
eab211bb1e
Resample audio to 44100 when VAE encoding it.
8 months ago
73ca780019
Add SamplerEulerCFG++ node.
...
This node should match the DDIM implementation of CFG++ when "regular" is
selected.
"alternative" is a slightly different take on CFG++
8 months ago
887a6341ed
Proper ModelMergeSD3_2B node.
8 months ago
45e10cac19
feat: add gits scheduler ( #3769 )
8 months ago
0d6a57938e
Support loading diffusers SD3 model format with UNETLoader node.
8 months ago
bb1969cab7
Initial support for the stable audio open model.
8 months ago
0eaa34ec5b
Fix regular empty latent image not working with SD3 and custom sampler.
9 months ago
c8b5e08dc3
Default shift value on SD3 is 3.0
9 months ago
32be358213
Save SD3 modelspec.architecture in CheckpointSave node.
9 months ago
1c34d338d7
Update EmptySD3LatentImage to use 1024 resolution by default.
9 months ago
8c4a9befa7
SD3 Support.
9 months ago
6cd8ffc465
Reshape the empty latent image to the right amount of channels if needed.
9 months ago
20447e9ec9
Fix alpha in PorterDuffImageComposite. ( #3411 )
...
There were two bugs in PorterDuffImageComposite.
The first one is the fact that it uses the mask input directly as alpha, missing the conversion (`1-a`). The fix is similar to c16f5744
9 months ago
e2c585f3be
Fix to allow use of PerpNegGuider with cfg_function_post hooks (like PAG) ( #3618 )
9 months ago
91542d4f8b
Import spandrel_extra_arches if present.
...
I will not add this dependency to the default ones because models in the
spandrel_extra_arches package are non commercial and therefore not
compatible with free software licenses like the one ComfyUI uses.
If you don't mind this you can install it manually yourself.
9 months ago
0920e0e5fe
Remove some unused imports.
9 months ago
16a493a190
Keep compatibility with some custom nodes.
9 months ago
9a151b7def
Fix issue and unpin spandrel package.
9 months ago
comfyanonymous
来新璐
Silver
fgdfgfthgr-fox
Jairo Correa
Chenlei Hu
Peter Crabtree
Zhenyu Zhou
Denys Smirnov