2d28b0b479
improve: add descriptions for clip loaders ( #5576 )
2024-11-11 05:37:23 -05:00
2a18e98ccf
Refactor so that zsnr can be set in the sampling_settings.
2024-11-11 04:55:56 -05:00
9c1ed58ef2
proper fix for sag.
2024-11-10 00:10:45 -05:00
dd5b57e3d7
fix for SAG with Kohya HRFix/ Deep Shrink ( #5546 )
...
now works with arbitrary downscale factors
2024-11-08 18:16:29 -05:00
75a818c720
Move mochi latent node to: latent/video.
2024-11-08 08:33:44 -05:00
ee8abf0cff
Update folder paths: "clip" -> "text_encoders"
...
You can still use models/clip but the folder might get removed eventually
on new installs of ComfyUI.
2024-11-02 15:35:38 -04:00
770ab200f2
Cleanup SkipLayerGuidanceSD3 node.
2024-10-29 10:11:46 -04:00
954683d0db
SLG first implementation for SD3.5 ( #5404 )
...
* SLG first implementation for SD3.5
* * Simplify and align with comfy style
2024-10-29 09:59:21 -04:00
5cbb01bc2f
Basic Genmo Mochi video model support.
...
To use:
"Load CLIP" node with t5xxl + type mochi
"Load Diffusion Model" node with the mochi dit file.
"Load VAE" with the mochi vae file.
EmptyMochiLatentVideo node for the latent.
euler + linear_quadratic in the KSampler node.
2024-10-26 06:54:00 -04:00
52810907e2
Add a model merge node for SD3.5 large.
2024-10-24 16:46:21 -04:00
518c0dc2fe
Add tooltips to LoraSave node.
2024-10-18 06:01:09 -04:00
7390ff3b1e
Add missing import.
2024-10-16 14:58:30 -04:00
f71cfd2687
Add an experimental node to sharpen latents.
...
Can be used with LatentApplyOperationCFG for interesting results.
2024-10-16 05:25:31 -04:00
0dbba9f751
Add some latent operation nodes.
...
This is a port of the ModelSamplerTonemapNoiseTest from the experiments
repo.
To replicate that node use LatentOperationTonemapReinhard and
LatentApplyOperationCFG together.
2024-10-15 15:00:36 -04:00
83b01f960a
Add backend option to TorchCompileModel.
...
If you want to use the cudagraphs backend you need to: --disable-cuda-malloc
If you get other backends working feel free to make a PR to add them.
2024-09-27 02:12:37 -04:00
037c3159b6
Move some nodes out of _for_testing.
2024-09-25 08:41:22 -04:00
fdf37566ef
Add batch size to EmptyLatentAudio.
2024-09-24 04:32:55 -04:00
7a415f47a9
Add an optional VAE input to the ControlNetApplyAdvanced node.
...
Deprecate the other controlnet nodes.
2024-09-22 01:24:52 -04:00
364b69e931
Make SD3 empty latent image zeros.
...
This shouldn't change anything. The reason it was not zeros is because it
did matter in early versions of the code.
2024-09-21 09:13:10 -04:00
a355f38ecc
Make the SD3 controlnet node the default one.
2024-09-21 01:32:46 -04:00
e7d4782736
add laplace scheduler [2407.03297] ( #4990 )
...
* add laplace scheduler [2407.03297]
* should be here instead lol
* better settings
2024-09-19 23:23:09 -04:00
254838f23c
add simple error check to model loading ( #4950 )
2024-09-17 03:57:17 -04:00
56e8f5e4fd
VAEDecodeAudio now does some normalization on the audio.
2024-09-16 00:30:36 -04:00
ca08597670
Make the inpaint controlnet node work with non inpaint ones.
2024-09-14 09:17:13 -04:00
f48e390032
Support AliMama SD3 and Flux inpaint controlnets.
...
Use the ControlNetInpaintingAliMamaApply node.
2024-09-14 09:05:16 -04:00
7c6eb4fb29
Set some nodes as DEPRECATED.
2024-09-12 20:27:07 -04:00
d0b7ab88ba
Add a simple experimental TorchCompileModel node.
...
It probably only works on Linux.
For maximum speed on Flux with Nvidia 40 series/ada and newer try using
this node with fp8_e4m3fn and the --fast argument.
2024-09-12 05:24:25 -04:00
e760bf5c40
Add content-type filter method to folder_paths ( #4054 )
...
* Add content-type filter method to folder_paths
* Add unit tests
* Hardcode webp content-type
* Annotate content_types as Literal["image", "video", "audio"]
2024-09-11 02:00:07 -04:00
8aabd7c8c0
SaveLora node can now save "full diff" lora format.
...
This isn't actually a lora format and is saving the full diff of the
weights in a format that can be used in the lora loader nodes.
2024-09-07 03:21:02 -04:00
a09b29ca11
Add an option to the SaveLora node to store the bias diff.
2024-09-07 03:03:30 -04:00
9bfee68773
LoraSave node now supports generating text encoder loras.
...
text_encoder_diff should be connected to a CLIPMergeSubtract node.
model_diff and text_encoder_diff are optional inputs so you can create
model only loras, text encoder only loras or a lora that contains both.
2024-09-07 02:30:12 -04:00
22d1241a50
Add an experimental LoraSave node to extract model loras.
...
The model_diff input should be connected to the output of a
ModelMergeSubtract node.
2024-09-04 16:38:38 -04:00
766ae119a8
CheckpointSave node name.
2024-08-19 15:06:12 -04:00
310ad09258
Add a ModelSave node.
2024-08-17 21:43:07 -04:00
a475ec2300
Cleanup HunyuanDit controlnets.
...
Use the: ControlNetApply SD3 and HunyuanDiT node.
2024-08-09 02:59:34 -04:00
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
2024-08-09 02:59:24 -04:00
f3bc40223a
Add format metadata to CLIP save to make compatible with diffusers safetensors loading ( #4233 )
2024-08-06 01:45:24 -04:00
ddb6a9f47c
Set the step in EmptySD3LatentImage to 16.
...
These models work better when the res is a multiple of 16.
2024-08-04 15:59:02 -04:00
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.
2024-08-04 04:06:00 -04:00
0eea47d580
Add ModelSamplingFlux to experiment with the shift value.
...
Default shift on Flux Schnell is 0.0
2024-08-03 03:54:38 -04:00
7cd0cdfce6
Add advanced model merge node for Flux model.
2024-08-02 23:20:53 -04:00
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
2024-08-02 10:29:03 -04:00
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.
2024-08-02 10:25:49 -04:00
c1696cd1b5
Add missing import ( #4174 )
2024-08-02 09:34:12 -04:00
a531001cc7
Add CLIPTextEncodeFlux.
2024-08-01 18:53:25 -04:00
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.
2024-07-27 16:19:50 -04:00
6225a7827c
Add CLIPTextEncodeHunyuanDiT.
...
Useful for testing what each text encoder does.
2024-07-26 13:08:06 -04:00
b2c995f623
"auto" type is only relevant to the SetUnionControlNetType node.
2024-07-22 11:30:38 -04:00
4151fbfa8a
Add error message on union controlnet ( #4081 )
2024-07-22 11:27:32 -04:00
f836e69346
Fix bug with SaveAudio node with --gpu-only
2024-07-21 16:16:45 -04:00
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.
2024-07-19 18:05:09 -04:00
ff6ca2a892
Move PAG to model_patches/unet section.
...
Move other unet model_patches nodes to model_patches/unet section.
2024-07-18 17:22:51 -04:00
60383f3b64
Move controlnet nodes to conditioning/controlnet.
2024-07-16 17:08:25 -04:00
8270c62530
Add SetUnionControlNetType to set the type of the union controlnet model.
2024-07-16 17:04:53 -04:00
8e012043a9
Add a ModelSamplingAuraFlow node to change the shift value.
...
Set the default AuraFlow shift value to 1.73 (sqrt(3)).
2024-07-11 17:57:36 -04:00
628f0b8ebc
Move audio nodes out of _for_testing.
2024-07-07 09:22:32 -04:00
01991f72ce
Fix SamplerEulerCFGpp node.
2024-07-02 12:21:08 -04:00
b82d67d5bf
Add SamplerEulerAncestralCFG++ custom sampler node ( #3901 )
...
(for eta and s_noise)
2024-07-01 17:42:17 -04:00
fbb7a1f1b6
PreviewAudio node.
2024-06-29 01:33:22 -04:00
7ecb2ec169
Audio second setting in EmptyLatentAudio.
2024-06-28 02:55:36 -04:00
264caca20e
ControlNetApplySD3 node can now be used to use SD3 controlnets.
2024-06-27 18:43:11 -04:00
4650e7d6e9
Save and load workflow from the flac files output by SaveAudio.
2024-06-27 02:07:29 -04:00
3b423afcca
Add audio widget ( #3863 )
...
* Add audio widget
* Fix audio bugs
* Add CSS
* Populate audio widget when load history
2024-06-27 00:22:55 -04:00
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.
2024-06-25 07:41:52 -04:00
eab211bb1e
Resample audio to 44100 when VAE encoding it.
2024-06-24 16:55:20 -04:00
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++
2024-06-23 13:21:18 -04:00
887a6341ed
Proper ModelMergeSD3_2B node.
2024-06-21 08:41:31 -04:00
45e10cac19
feat: add gits scheduler ( #3769 )
2024-06-20 08:12:15 -04:00
0d6a57938e
Support loading diffusers SD3 model format with UNETLoader node.
2024-06-19 22:21:18 -04:00
bb1969cab7
Initial support for the stable audio open model.
2024-06-15 12:14:56 -04:00
0eaa34ec5b
Fix regular empty latent image not working with SD3 and custom sampler.
2024-06-12 10:32:34 -04:00
c8b5e08dc3
Default shift value on SD3 is 3.0
2024-06-12 02:24:39 -04:00
32be358213
Save SD3 modelspec.architecture in CheckpointSave node.
2024-06-12 01:02:07 -04:00
1c34d338d7
Update EmptySD3LatentImage to use 1024 resolution by default.
2024-06-11 07:37:22 -04:00
8c4a9befa7
SD3 Support.
2024-06-10 14:06:23 -04:00
6cd8ffc465
Reshape the empty latent image to the right amount of channels if needed.
2024-06-08 02:35:08 -04:00
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
2024-06-04 16:37:11 -04:00
e2c585f3be
Fix to allow use of PerpNegGuider with cfg_function_post hooks (like PAG) ( #3618 )
2024-06-01 12:36:08 -04:00
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.
2024-05-28 01:42:11 -04:00
0920e0e5fe
Remove some unused imports.
2024-05-27 19:08:27 -04:00
16a493a190
Keep compatibility with some custom nodes.
2024-05-26 15:37:41 -04:00
9a151b7def
Fix issue and unpin spandrel package.
2024-05-26 13:44:47 -04:00
8cfd677cc0
Replace chainner_models with Spandrel package ( #2146 )
...
* Replace chainner_models with Spandrel
* Update to latest spandrel
* Use spandrel_foss instead
* update spandrel to new FOSS-compliant version
2024-05-26 13:44:17 -04:00
b02bcced05
Fix FreeU not working when shape is tensor.
2024-05-23 11:48:04 -04:00
91590adf04
Add webcam node ( #3497 )
...
* Add webcam node
* unused import
2024-05-17 13:16:08 -04:00
ec6f16adb6
Fix SAG.
2024-05-14 18:02:27 -04:00
2de3b69b30
Support saving some more modelspec types.
2024-05-13 21:54:11 -04:00
e1489ad257
Fix issue with lowvram mode breaking model saving.
2024-05-11 21:55:20 -04:00
3787b4f246
Use get_model_object in Deep Shrink node ( #3408 )
2024-05-06 18:39:39 -04:00
565eb6d176
Add a SplitSigmasDenoise node as an alternative to SplitSigmas.
2024-05-05 05:24:36 -04:00
94d5a12801
Don't load the model in SDTurboScheduler
2024-05-01 16:57:10 -04:00
eecd69b53a
Add a SamplerLCMUpscale node.
...
This sampler is an LCM sampler that upscales the latent during sampling.
It can be used to generate at a higher resolution with an LCM model very
quickly.
To try it use it with a basic 5 step LCM workflow with scale_ratio 1.5 or
2.0
2024-04-29 20:00:47 -04:00
059773a6df
Add some nodes to multiply the attention in UNet and Clip models.
2024-04-28 13:03:43 -04:00
10fcd09f4a
Add a denoise value to AlignYourStepsScheduler.
2024-04-27 00:48:41 -04:00
16eabdf70d
Free more vram for upscale models.
2024-04-25 17:04:19 -04:00
b8218522f1
Increase sigma_min/sigma_max range for custom schedulers ( #3317 )
2024-04-23 09:40:10 -04:00
d09b5ef4ef
Free some memory before loading upscale models.
2024-04-22 18:51:15 -04:00
4ee9aad6ca
Speed up Sharpen node.
2024-04-21 09:02:06 -04:00
644a3ae58d
Implement Align Your Steps as a AlignYourStepsScheduler node.
2024-04-20 04:34:12 -04:00
133dc3351b
Faster blur.
2024-04-19 03:52:02 -04:00
Dr.Lt.Data
comfyanonymous
DenOfEquity
Dango233
yoinked
Alex "mcmonkey" Goodwin
bymyself
来新璐
Silver
fgdfgfthgr-fox
Jairo Correa
Chenlei Hu
Peter Crabtree
Zhenyu Zhou
Denys Smirnov
Joey Ballentine
pythongosssss
Pam