comfyanonymous
3a6dc4a71a
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
comfyanonymous
bb4e8b9038
Cleanup SkipLayerGuidanceSD3 node.
2024-10-29 10:11:46 -04:00
Dango233
831c910574
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
comfyanonymous
9f8e7912ef
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
comfyanonymous
543ee44da5
Add a model merge node for SD3.5 large.
2024-10-24 16:46:21 -04:00
comfyanonymous
86b81cbad8
Add tooltips to LoraSave node.
2024-10-18 06:01:09 -04:00
comfyanonymous
5a1e7ce230
Add missing import.
2024-10-16 14:58:30 -04:00
comfyanonymous
2fecfcd222
Add an experimental node to sharpen latents.
...
Can be used with LatentApplyOperationCFG for interesting results.
2024-10-16 05:25:31 -04:00
comfyanonymous
1f54588ac6
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
comfyanonymous
3dc1eee523
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
comfyanonymous
643a62651f
Move some nodes out of _for_testing.
2024-09-25 08:41:22 -04:00
comfyanonymous
b18a89387b
Add batch size to EmptyLatentAudio.
2024-09-24 04:32:55 -04:00
comfyanonymous
fc89499f3e
Add an optional VAE input to the ControlNetApplyAdvanced node.
...
Deprecate the other controlnet nodes.
2024-09-22 01:24:52 -04:00
comfyanonymous
841df2fab1
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
comfyanonymous
128619bf11
Make the SD3 controlnet node the default one.
2024-09-21 01:32:46 -04:00
yoinked
65b99536ee
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
Alex "mcmonkey" Goodwin
e4f4d46b62
add simple error check to model loading ( #4950 )
2024-09-17 03:57:17 -04:00
comfyanonymous
c8f7a99646
VAEDecodeAudio now does some normalization on the audio.
2024-09-16 00:30:36 -04:00
comfyanonymous
c123d2a309
Make the inpaint controlnet node work with non inpaint ones.
2024-09-14 09:17:13 -04:00
comfyanonymous
8058b19f35
Support AliMama SD3 and Flux inpaint controlnets.
...
Use the ControlNetInpaintingAliMamaApply node.
2024-09-14 09:05:16 -04:00
comfyanonymous
7549d3c2b6
Set some nodes as DEPRECATED.
2024-09-12 20:27:07 -04:00
comfyanonymous
d34cecf624
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
bymyself
2b7ef8c9f0
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
comfyanonymous
c512791552
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
comfyanonymous
c59d3956d5
Add an option to the SaveLora node to store the bias diff.
2024-09-07 03:03:30 -04:00
comfyanonymous
98c5dcbf04
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
comfyanonymous
211789cb55
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
comfyanonymous
7aec00e4a2
CheckpointSave node name.
2024-08-19 15:06:12 -04:00
comfyanonymous
f941dd54e7
Add a ModelSave node.
2024-08-17 21:43:07 -04:00
comfyanonymous
24d1c00725
Cleanup HunyuanDit controlnets.
...
Use the: ControlNetApply SD3 and HunyuanDiT node.
2024-08-09 02:59:34 -04:00
来新璐
298a7149d3
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
Silver
a4c5e04e27
Add format metadata to CLIP save to make compatible with diffusers safetensors loading ( #4233 )
2024-08-06 01:45:24 -04:00
comfyanonymous
2ba49bbd82
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
comfyanonymous
55c9c01bec
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
comfyanonymous
ad4292b964
Add ModelSamplingFlux to experiment with the shift value.
...
Default shift on Flux Schnell is 0.0
2024-08-03 03:54:38 -04:00
comfyanonymous
16ac61d4d0
Add advanced model merge node for Flux model.
2024-08-02 23:20:53 -04:00
fgdfgfthgr-fox
fccdd04ee7
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
comfyanonymous
851720f59f
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
Jairo Correa
794358e877
Add missing import ( #4174 )
2024-08-02 09:34:12 -04:00
comfyanonymous
2c3ecacc4d
Add CLIPTextEncodeFlux.
2024-08-01 18:53:25 -04:00
Silver
c82c3556f7
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
comfyanonymous
5b87251031
Add CLIPTextEncodeHunyuanDiT.
...
Useful for testing what each text encoder does.
2024-07-26 13:08:06 -04:00
comfyanonymous
e96e0fdf8b
"auto" type is only relevant to the SetUnionControlNetType node.
2024-07-22 11:30:38 -04:00
Chenlei Hu
c79f809b56
Add error message on union controlnet ( #4081 )
2024-07-22 11:27:32 -04:00
comfyanonymous
5007b1471a
Fix bug with SaveAudio node with --gpu-only
2024-07-21 16:16:45 -04:00
comfyanonymous
de738b5cb8
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
comfyanonymous
3075e778a2
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
comfyanonymous
059c99f4c5
Move controlnet nodes to conditioning/controlnet.
2024-07-16 17:08:25 -04:00
comfyanonymous
8c2e920625
Add SetUnionControlNetType to set the type of the union controlnet model.
2024-07-16 17:04:53 -04:00
comfyanonymous
1234807a19
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
