!!! Important Update !!!
Don't forget to add the Node again in existing workflows
Support This Project
English | Русский
The Fast and Simple Face Swap Extension Node for ComfyUI, based on ReActor SD-WebUI Face Swap Extension
This Node goes without NSFW filter (uncensored, use it on your own responsibility)
- Support of GPEN 1024/2048 restoration models (available in the HF dataset https://huggingface.co/datasets/Gourieff/ReActor/tree/main/models/facerestore_models)
- ReActorFaceBoost Node - an attempt to improve the quality of swapped faces. The idea is to restore and scale the swapped face (according to the
face_sizeparameter of the restoration model) BEFORE pasting it to the target image (via inswapper algorithms), more information is here (PR#321)
- Some fixes and improvements
Previous versions
- Spandrel lib support for GFPGAN
- Fixes: "RAM issue", "No detection" for MaskingHelper
- You can now build a blended face model from a batch of face models you already have, just add the "Make Face Model Batch" node to your workflow and connect several models via "Load Face Model"
- Huge performance boost of the image analyzer's module! 10x speed up! Working with videos is now a pleasure!
- SWAPPED_FACE output for the Masking Helper Node
- FIX: Empty A-channel for Masking Helper IMAGE output (causing errors with some nodes) was removed
- ReActorBuildFaceModel Node got "face_model" output to provide a blended face model directly to the main Node:
Basic workflow 💾
- Face Masking feature is available now, just add the "ReActorMaskHelper" Node to the workflow and connect it as shown below:
If you don't have the "face_yolov8m.pt" Ultralytics model - you can download it from the Assets and put it into the "ComfyUI\models\ultralytics\bbox" directory
As well as "sam_vit_b_01ec64.pth" model - download (if you don't have it) and put it into the "ComfyUI\models\sams" directory;
Use this Node to gain the best results of the face swapping process:
- ReActorImageDublicator Node - rather useful for those who create videos, it helps to duplicate one image to several frames to use them with VAE Encoder (e.g. live avatars):
- ReActorFaceSwapOpt (a simplified version of the Main Node) + ReActorOptions Nodes to set some additional options such as (new) "input/source faces separate order". Yes! You can now set the order of faces in the index in the way you want ("large to small" goes by default)!
- Little speed boost when analyzing target images (unfortunately it is still quite slow in compare to swapping and restoring...)
- GPEN-BFR-512 and RestoreFormer_Plus_Plus face restoration models support
You can download models here: https://huggingface.co/datasets/Gourieff/ReActor/tree/main/models/facerestore_models
Put them into the ComfyUI\models\facerestore_models folder
- Due to popular demand - you can now blend several images with persons into one face model file and use it with "Load Face Model" Node or in SD WebUI as well;
Experiment and create new faces or blend faces of one person to gain better accuracy and likeness!
Just add the ImpactPack's "Make Image Batch" Node as the input to the ReActor's one and load images you want to blend into one model:
Result example (the new face was created from 4 faces of different actresses):
Basic workflow 💾
-
CUDA 12 Support - don't forget to run (Windows)
install.bator (Linux/MacOS)install.pyfor ComfyUI's Python enclosure or try to install ORT-GPU for CU12 manually (https://onnxruntime.ai/docs/install/#install-onnx-runtime-gpu-cuda-12x) -
Issue #173 fix
-
Separate Node for the Face Restoration postprocessing (FR #191), can be found inside ReActor's menu (RestoreFace Node)
-
(Windows) Installation can be done for Python from the System's PATH
-
Different fixes and improvements
-
Face Restore Visibility and CodeFormer Weight (Fidelity) options are now available! Don't forget to reload the Node in your existing workflow
- Input "input_image" goes first now, it gives a correct bypass and also it is right to have the main input first;
- You can now save face models as "safetensors" files (
ComfyUI\models\reactor\faces) and load them into ReActor implementing different scenarios and keeping super lightweight face models of the faces you use:
- Ability to build and save face models directly from an image:
- Both the inputs are optional, just connect one of them according to your workflow; if both is connected -
imagehas a priority. - Different fixes making this extension better.
Thanks to everyone who finds bugs, suggests new features and supports this project!
SD WebUI: AUTOMATIC1111 or SD.Next
- Close (stop) your SD-WebUI/Comfy Server if it's running
- (For Windows Users):
- Install Visual Studio 2022 (Community version - you need this step to build Insightface)
- OR only VS C++ Build Tools and select "Desktop Development with C++" under "Workloads -> Desktop & Mobile"
- OR if you don't want to install VS or VS C++ BT - follow this steps (sec. I)
- Go to the
extensions\sd-webui-comfyui\ComfyUI\custom_nodes - Open Console or Terminal and run
git clone https://github.com/Gourieff/comfyui-reactor-node - Go to the SD WebUI root folder, open Console or Terminal and run (Windows users)
.\venv\Scripts\activateor (Linux/MacOS)venv/bin/activate python -m pip install -U pipcd extensions\sd-webui-comfyui\ComfyUI\custom_nodes\comfyui-reactor-nodepython install.py- Please, wait until the installation process will be finished
- (From the version 0.3.0) Download additional facerestorers models from the link below and put them into the
extensions\sd-webui-comfyui\ComfyUI\models\facerestore_modelsdirectory:
https://huggingface.co/datasets/Gourieff/ReActor/tree/main/models/facerestore_models - Run SD WebUI and check console for the message that ReActor Node is running:
- Go to the ComfyUI tab and find there ReActor Node inside the menu
ReActoror by using a search:
Standalone (Portable) ComfyUI for Windows
- Do the following:
- Install Visual Studio 2022 (Community version - you need this step to build Insightface)
- OR only VS C++ Build Tools and select "Desktop Development with C++" under "Workloads -> Desktop & Mobile"
- OR if you don't want to install VS or VS C++ BT - follow this steps (sec. I)
- Choose between two options:
- (ComfyUI Manager) Open ComfyUI Manager, click "Install Custom Nodes", type "ReActor" in the "Search" field and then click "Install". After ComfyUI will complete the process - please restart the Server.
- (Manually) Go to
ComfyUI\custom_nodes, open Console and rungit clone https://github.com/Gourieff/comfyui-reactor-node
- Go to
ComfyUI\custom_nodes\comfyui-reactor-nodeand runinstall.bat - If you don't have the "face_yolov8m.pt" Ultralytics model - you can download it from the Assets and put it into the "ComfyUI\models\ultralytics\bbox" directory
As well as one or both of "Sams" models from [here](https://huggingface.co/datasets/Gourieff/ReActor/tree/main/models/sams) - download (if you don't have them) and put into the "ComfyUI\models\sams" directory 5. Run ComfyUI and find there ReActor Nodes inside the menu `ReActor` or by using a search
You can find ReActor Nodes inside the menu ReActor or by using a search (just type "ReActor" in the search field)
List of Nodes:
- ••• Main Nodes •••
- ReActorFaceSwap (Main Node)
- ReActorFaceSwapOpt (Main Node with the additional Options input)
- ReActorOptions (Options for ReActorFaceSwapOpt)
- ReActorFaceBoost (Face Booster Node)
- ReActorMaskHelper (Masking Helper)
- ••• Operations with Face Models •••
- ReActorSaveFaceModel (Save Face Model)
- ReActorLoadFaceModel (Load Face Model)
- ReActorBuildFaceModel (Build Blended Face Model)
- ReActorMakeFaceModelBatch (Make Face Model Batch)
- ••• Additional Nodes •••
- ReActorRestoreFace (Face Restoration)
- ReActorImageDublicator (Dublicate one Image to Images List)
- ImageRGBA2RGB (Convert RGBA to RGB)
Connect all required slots and run the query.
input_image- is an image to be processed (target image, analog of "target image" in the SD WebUI extension);- Supported Nodes: "Load Image", "Load Video" or any other nodes providing images as an output;
source_image- is an image with a face or faces to swap in theinput_image(source image, analog of "source image" in the SD WebUI extension);- Supported Nodes: "Load Image" or any other nodes providing images as an output;
face_model- is the input for the "Load Face Model" Node or another ReActor node to provide a face model file (face embedding) you created earlier via the "Save Face Model" Node;- Supported Nodes: "Load Face Model", "Build Blended Face Model";
IMAGE- is an output with the resulted image;- Supported Nodes: any nodes which have images as an input;
FACE_MODEL- is an output providing a source face's model being built during the swapping process;- Supported Nodes: "Save Face Model", "ReActor", "Make Face Model Batch";
Since version 0.3.0 ReActor Node has a buil-in face restoration.
Just download the models you want (see Installation instruction) and select one of them to restore the resulting face(s) during the faceswap. It will enhance face details and make your result more accurate.
By default ReActor detects faces in images from "large" to "small".
You can change this option by adding ReActorFaceSwapOpt node with ReActorOptions.
And if you need to specify faces, you can set indexes for source and input images.
Index of the first detected face is 0.
You can set indexes in the order you need.
E.g.: 0,1,2 (for Source); 1,0,2 (for Input).
This means: the second Input face (index = 1) will be swapped by the first Source face (index = 0) and so on.
You can specify the gender to detect in images.
ReActor will swap a face only if it meets the given condition.
Since version 0.4.0 you can save face models as "safetensors" files (stored in ComfyUI\models\reactor\faces) and load them into ReActor implementing different scenarios and keeping super lightweight face models of the faces you use.
To make new models appear in the list of the "Load Face Model" Node - just refresh the page of your ComfyUI web application.
(I recommend you to use ComfyUI Manager - otherwise you workflow can be lost after you refresh the page if you didn't save it before that).
I. (For Windows users) If you still cannot build Insightface for some reasons or just don't want to install Visual Studio or VS C++ Build Tools - do the following:
- (ComfyUI Portable) From the root folder check the version of Python:
run CMD and typepython_embeded\python.exe -V - Download prebuilt Insightface package for Python 3.10 or for Python 3.11 (if in the previous step you see 3.11) or for Python 3.12 (if in the previous step you see 3.12) and put into the stable-diffusion-webui (A1111 or SD.Next) root folder (where you have "webui-user.bat" file) or into ComfyUI root folder if you use ComfyUI Portable
- From the root folder run:
- (SD WebUI) CMD and
.\venv\Scripts\activate - (ComfyUI Portable) run CMD
- (SD WebUI) CMD and
- Then update your PIP:
- (SD WebUI)
python -m pip install -U pip - (ComfyUI Portable)
python_embeded\python.exe -m pip install -U pip
- (SD WebUI)
- Then install Insightface:
- (SD WebUI)
pip install insightface-0.7.3-cp310-cp310-win_amd64.whl(for 3.10) orpip install insightface-0.7.3-cp311-cp311-win_amd64.whl(for 3.11) orpip install insightface-0.7.3-cp312-cp312-win_amd64.whl(for 3.12) - (ComfyUI Portable)
python_embeded\python.exe -m pip install insightface-0.7.3-cp310-cp310-win_amd64.whl(for 3.10) orpython_embeded\python.exe -m pip install insightface-0.7.3-cp311-cp311-win_amd64.whl(for 3.11) orpython_embeded\python.exe -m pip install insightface-0.7.3-cp312-cp312-win_amd64.whl(for 3.12)
- (SD WebUI)
- Enjoy!
This error may occur if there's smth wrong with the model file inswapper_128.onnx
Try to download it manually from here
and put it to the ComfyUI\models\insightface replacing existing one
This means that input points have been changed with the latest update
Remove the current ReActor Node from your workflow and add it again
- Close ComfyUI if it runs
- Go to the ComfyUI root folder, open CMD there and run:
python_embeded\python.exe -m pip uninstall -y opencv-python opencv-contrib-python opencv-python-headlesspython_embeded\python.exe -m pip install opencv-python==4.7.0.72
- That's it!
V. "ModuleNotFoundError: No module named 'basicsr'" or "subprocess-exited-with-error" during future-0.18.3 installation
-
Download https://github.com/Gourieff/Assets/raw/main/comfyui-reactor-node/future-0.18.3-py3-none-any.whl
-
Put it to ComfyUI root And run:
python_embeded\python.exe -m pip install future-0.18.3-py3-none-any.whl -
Then:
python_embeded\python.exe -m pip install basicsr
Try to clone with --depth=1 (last commit only):
git clone --depth=1 https://github.com/Gourieff/comfyui-reactor-node
Then retrieve the rest (if you need):
git fetch --unshallow
Just put .bat or .sh script from this Repo to the ComfyUI\custom_nodes directory and run it when you need to check for updates
This software is meant to be a productive contribution to the rapidly growing AI-generated media industry. It will help artists with tasks such as animating a custom character or using the character as a model for clothing etc.
The developers of this software are aware of its possible unethical applications and are committed to take preventative measures against them. We will continue to develop this project in the positive direction while adhering to law and ethics.
Users of this software are expected to use this software responsibly while abiding the local law. If face of a real person is being used, users are suggested to get consent from the concerned person and clearly mention that it is a deepfake when posting content online. Developers and Contributors of this software are not responsible for actions of end-users.
By using this extension you are agree not to create any content that:
- violates any laws;
- causes any harm to a person or persons;
- propagates (spreads) any information (both public or personal) or images (both public or personal) which could be meant for harm;
- spreads misinformation;
- targets vulnerable groups of people.
This software utilizes the pre-trained models buffalo_l and inswapper_128.onnx, which are provided by InsightFace. These models are included under the following conditions:
From insighface license: The InsightFace’s pre-trained models are available for non-commercial research purposes only. This includes both auto-downloading models and manually downloaded models.
Users of this software must strictly adhere to these conditions of use. The developers and maintainers of this software are not responsible for any misuse of InsightFace’s pre-trained models.
Please note that if you intend to use this software for any commercial purposes, you will need to train your own models or find models that can be used commercially.
inswapper_128.onnx
MD5:a3a155b90354160350efd66fed6b3d80
SHA256:e4a3f08c753cb72d04e10aa0f7dbe3deebbf39567d4ead6dce08e98aa49e16af
1k3d68.onnx
MD5:6fb94fcdb0055e3638bf9158e6a108f4
SHA256:df5c06b8a0c12e422b2ed8947b8869faa4105387f199c477af038aa01f9a45cc
2d106det.onnx
MD5:a3613ef9eb3662b4ef88eb90db1fcf26
SHA256:f001b856447c413801ef5c42091ed0cd516fcd21f2d6b79635b1e733a7109dbf
det_10g.onnx
MD5:4c10eef5c9e168357a16fdd580fa8371
SHA256:5838f7fe053675b1c7a08b633df49e7af5495cee0493c7dcf6697200b85b5b91
genderage.onnx
MD5:81c77ba87ab38163b0dec6b26f8e2af2
SHA256:4fde69b1c810857b88c64a335084f1c3fe8f01246c9a191b48c7bb756d6652fb
w600k_r50.onnx
MD5:80248d427976241cbd1343889ed132b3
SHA256:4c06341c33c2ca1f86781dab0e829f88ad5b64be9fba56e56bc9ebdefc619e43
Please check hashsums if you download these models from unverified (or untrusted) sources
Click to expand
| file | source | license |
|---|---|---|
| buffalo_l.zip | DeepInsight |  |
| codeformer-v0.1.0.pth | sczhou | |
| GFPGANv1.3.pth | TencentARC |  |
| GFPGANv1.4.pth | TencentARC | |
| inswapper_128.onnx | DeepInsight | |
| inswapper_128_fp16.onnx | Hillobar | |
BasicSR - @XPixelGroup
facexlib - @xinntao
@s0md3v, @henryruhs - the original Roop App
@ssitu - the first version of ComfyUI_roop extension
If you encounter any errors when you use ReActor Node - don't rush to open an issue, first try to remove current ReActor node in your workflow and add it again
ReActor Node gets updates from time to time, new functions appear and old node can work with errors or not work at all
