^{Support This Project}

---

English | Русский

ReActor for Stable Diffusion

The Fast and Simple FaceSwap Extension with a lot of improvements and without NSFW filter (uncensored, use it on your own responsibility)

---

What's new | Installation | Features | Usage | API | Troubleshooting | Updating | ComfyUI | Disclaimer

Click to expand

0.7.0 _^BETA2

• X/Y/Z is improved! One more parameter is ready: you can now select several face models to create a variation of swaps to choose the best one!

To use "Face Model" axis - you should enable ReActor and choose any face model as the Source:

Full size demo image: xyz_demo_2.png

0.7.0 _^BETA1

• X/Y/Z Script support (up to 3 axes: CodeFormer Weight, Restorer Visibility, Face Mask Correction)

Full size demo image: xyz_demo.png

Don't forget to enable ReActor and set any source (to prevent "no source" error)

0.7.0 _^ALPHA1

• You can now blend faces to build blended face models ("Tools->Face Models->Blend") - due to popular demand

• CUDA 12 Support in the Installer script for 1.17.0 ORT-GPU library
• New tab "Detection" with "Threshold" and "Max Faces" parameters

0.6.1 _^BETA3

• 'Force Upscale' option inside the 'Upscale' tab: ReActor will run the Upscaler even if there's no face is detected (FR #116)
• ReActor shows filenames of source images in-process when the multiple images mode or the folder mode (random as well) is selected

0.6.1 _^BETA2

• 'Save original' option works fine now when you select 'Multiple Images' or 'Source Folder'
• Random Mode for 'Source Folder'

0.6.0

• New Logo
• Adaptation to A1111 1.7.0 (appropriate GFPGAN loader)
• New URL for the main model file
• UI reworked
• You can now load several source images (with reference faces) or set the path to the folder containing faces images

0.5.1

• You can save face models as "safetensors" files (stored in <sd-web-ui-folder>\models\reactor\faces) and load them into ReActor, keeping super lightweight face models of the faces you use;
• "Face Mask Correction" option - if you encounter some pixelation around face contours, this option will be useful;

A1111 WebUI / WebUI-Forge | SD.Next | Google Colab SD WebUI

If you use AUTOMATIC1111 SD WebUI or SD WebUI Forge:

1. (For Windows Users):

• Install Visual Studio 2022 (Community version, for example - you need this step to build some of dependencies): https://visualstudio.microsoft.com/downloads/
• OR only VS C++ Build Tools (if you don't need the whole Visual Studio) and select "Desktop Development with C++" under "Workloads -> Desktop & Mobile": https://visualstudio.microsoft.com/visual-cpp-build-tools/
• OR if you don't want to install VS or VS C++ BT - follow this steps (sec. VIII)

2. In web-ui, go to the "Extensions" tab, load "Available" extensions and type "ReActor" in the search field or use this URL https://github.com/Gourieff/sd-webui-reactor in the "Install from URL" tab - and click "Install"
3. Please, wait for several minutes until the installation process will be finished (be patient, don't interrupt the process)
4. Check the last message in your SD-WebUI Console:

• If you see the message "--- PLEASE, RESTART the Server! ---" - so, do it, stop the Server (CTRL+C or CMD+C) and start it again - or just go to the "Installed" tab, click "Apply and restart UI"
• If you see the message "Done!", just reload the UI

5. Enjoy!

If you use SD.Next:

1. Close (stop) your SD WebUI Server if it's running
2. (For Windows Users) See the 1st step for Automatic1111 (if you followed this steps (sec. VIII) instead - go to the Step 5)
3. Go to (Windows)automatic\venv\Scripts or (MacOS/Linux)automatic/venv/bin, run Terminal or Console (cmd) for that folder and type activate
4. Run pip install insightface==0.7.3
5. Run SD.Next, go to the "Extensions" tab and use this URL https://github.com/Gourieff/sd-webui-reactor in the "Install from URL" tab and click "Install"
6. Please, wait for several minutes until the installation process will be finished (be patient, don't interrupt the process)
7. Check the last message in your SD.Next Console:

• If you see the message "--- PLEASE, RESTART the Server! ---" - stop the Server (CTRL+C or CMD+C) or just close your console

8. Go to the automatic\extensions\sd-webui-reactor directory - if you see there models\insightface folder with the file inswapper_128.onnx, just move the file to the automatic\models\insightface folder
9. Run your SD.Next WebUI and enjoy!

If you use Cagliostro Colab UI:

1. In active WebUI, go to the "Extensions" tab, load "Available" extensions and type "ReActor" in the search field or use this URL https://github.com/Gourieff/sd-webui-reactor in the "Install from URL" tab - and click "Install"
2. Please, wait for several minutes until the installation process will be finished (be patient, don't interrupt the process)
3. When you see the message "--- PLEASE, RESTART the Server! ---" (in your Colab Notebook Start UI section "Start Cagliostro Colab UI") - just go to the "Installed" tab and click "Apply and restart UI"
4. Enjoy!

• Very fast and accurate face replacement (face swap) in images
• Multiple faces support
• Gender detection
• Ability to save original images (made before swapping)
• Face restoration of a swapped face
• Upscaling of a resulting image
• Saving ans loading Safetensors Face Models
• Facial Mask Correction to avoid any pixelation around face contours
• Ability to set the Postprocessing order
• 100% compatibility with different SD WebUIs: Automatic1111, SD.Next, Cagliostro Colab UI
• Fast performance even with CPU, ReActor for SD WebUI is absolutely not picky about how powerful your GPU is
• CUDA acceleration support since version 0.5.0
• API support: both SD WebUI built-in and external (via POST/GET requests)
• ComfyUI support
• Mac M1/M2 support
• Console log level control
• NSFW filter free (this extension is aimed at highly developed intellectual people, not at perverts; our society must be oriented on its way towards the highest standards, not the lowest - this is the essence of development and evolution; so, my position is - that mature-minded people are clever enough to understand for themselves what is good and what is bad and take full responsibility for personal actions; for others - no "filters" will help until they do understand how Universe works)

Using this software you are agree with disclaimer

1. Under "ReActor" drop-down menu, import an image containing a face;
2. Turn on the "Enable" checkbox;
3. That's it, now the generated result will have the face you selected.

ReActor detects faces in images in the following order:
left->right, top->bottom

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.

Use the "Restore Face" option. You can also try the "Upscaler" option or for more finer control, use an upscaler from the "Extras" tab. You can also set the postproduction order (from 0.1.0 version):

The old logic was the opposite (Upscale -> then Restore), resulting in worse face quality (and big texture differences) after upscaling.

Select the face numbers you wish to swap using the "Comma separated face number(s)" option for swap-source and result images. You can use different index order.

This means NSFW filter detected that your image is NSFW.

You can choose to activate the swap on the source image or on the generated image, or on both using the checkboxes. Activating on source image allows you to start from a given base and apply the diffusion process to it.

ReActor works with Inpainting - but only the masked part will be swapped.
Please use with the "Only masked" option for "Inpaint area" if you enabled "Upscaler". Otherwise use the upscale option via the Extras tab or via the Script loader (below the screen) with "SD upscale" or "Ultimate SD upscale".

From the version 0.5.0 you can use ReActor via the Extras Tab. It gives a superfast perfomance and ability to swap face2image avoiding SD pipeline that can cause smushing of original image's details

You can use ReActor with the built-in Webui API or via an external API.

Please follow this page for the detailed instruction.

Please, check the path where "inswapper_128.onnx" model is stored. It must be inside the folder stable-diffusion-webui\models\insightface. Move the model there if it's stored in a different directory.

(for Mac M1/M2 users) If you get errors when trying to install Insightface - please read #42

(for Windows Users) If you have VS C++ Build Tools or MS VS 2022 installed but still have a problem, then try the next step:

1. Close (stop) your SD WebUI Server and start it again

(for Any OS Users) If the problem still there, then do the following:

1. Close (stop) your SD WebUI Server if it's running
2. Go to (Windows)venv\Lib\site-packages folder or (MacOS/Linux)venv/lib/python3.10/site-packages
3. If you see any folders with names start from ~ (e.g. "~rotobuf") - delete them
4. Go to (Windows)venv\Scripts or (MacOS/Linux)venv/bin
5. Run Terminal or Console (cmd) for that folder and type activate
6. Update your pip at first: pip install -U pip
7. Then one-by-one:
   • pip install insightface==0.7.3
   • pip install onnx
   • pip install "onnxruntime-gpu>=1.16.1"
   • pip install opencv-python
   • pip install tqdm
8. Type deactivate, you can close your Terminal or Console and start your SD WebUI, ReActor should start OK - if not, welcome to the Issues section.

First of all - you need to disable any other Roop-based extensions:

• Go to 'Extensions -> Installed' tab and uncheck any Roop-based extensions except this one
• Click 'Apply and restart UI'

Alternative solutions:

• #3 (comment)
• #39 (comment) (can be actual, if you use Vladmandic SD.Next)

Probably, you need to disable the "SD-CN-Animation" extension (or perhaps some another that causes the conflict)

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 stable-diffusion-webui\models\insightface replacing existing one

1. Close (stop) your SD WebUI Server if it's running
2. Go to the (Windows)venv\Lib\site-packages or (MacOS/Linux)venv/lib/python3.10/site-packages and see if there are any folders with names start from "~" (for example "~rotobuf"), delete them
3. Go to the (Windows)venv\Scripts or (MacOS/Linux)venv/bin run Terminal or Console (cmd) there and type activate
4. Then:

• python -m pip install -U pip
• pip uninstall -y onnxruntime onnxruntime-gpu onnxruntime-silicon onnxruntime-extensions
• pip install "onnxruntime-gpu>=1.16.1"

If it didn't help - it seems that you have another extension reinstalling onnxruntime when SD WebUI checks requirements. Please see your extensions list. Some extensions can causes reinstalling of onnxruntime-gpu to onnxruntime<1.16.1 every time SD WebUI runs.
ORT 1.16.0 has a bug microsoft/onnxruntime#17631 - don't install it!

1. Close (stop) your SD WebUI Server if it's running
2. Go to the (Windows)venv\Lib\site-packages or (MacOS/Linux)venv/lib/python3.10/site-packages and see if there are any folders with names start from "~" (for example "~rotobuf"), delete them
3. Go to the "google" folder (inside the "site-packages") and delete any folders there with names start from "~"
4. Go to the (Windows)venv\Scripts or (MacOS/Linux)venv/bin run Terminal or Console (cmd) there and type activate
5. Then:

• python -m pip install -U pip
• pip uninstall protobuf
• pip install "protobuf>=3.20.3"

If this method doesn't help - there is some other extension that has a wrong version of protobuf dependence and SD WebUI installs it on a startup requirements check

1. Close (stop) your SD WebUI Server if it's running
2. Download and put prebuilt Insightface package into the stable-diffusion-webui (or SD.Next) root folder where you have "webui-user.bat" file or (A1111 Portable) "run.bat"
3. From stable-diffusion-webui (or SD.Next) root folder run CMD and .\venv\Scripts\activate
   OR
   (A1111 Portable) Run CMD
4. Then update your PIP: python -m pip install -U pip
   OR
   (A1111 Portable)system\python\python.exe -m pip install -U pip
5. Then install Insightface: pip install insightface-0.7.3-cp310-cp310-win_amd64.whl
   OR
   (A1111 Portable)system\python\python.exe -m pip install insightface-0.7.3-cp310-cp310-win_amd64.whl
6. Enjoy!

If after git pull you see the message: Merge made by the 'recursive' strategy and then when you check git status you see Your branch is ahead of 'origin/main' by

Please do the next:

Inside the folder extensions\sd-webui-reactor run Terminal or Console (cmd) and then:

• git reset f48bdf1 --hard
• git pull

OR

Just delete the folder sd-webui-reactor inside the extensions directory and then run Terminal or Console (cmd) and type git clone https://github.com/Gourieff/sd-webui-reactor

If you encounter any issues with installing this extension in the StabilityMatrix package manager - read here how to solve: #129 (comment)

A good and quick way to check for Extensions updates: https://github.com/Gourieff/sd-webui-extensions-updater

You can use ReActor with ComfyUI.
For the installation instruction follow the ReActor Node repo

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 application 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;
• propogates (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 licence: 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