0.5.1

What's New:

• 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_size parameter of the restoration model) BEFORE pasting it to the target image (via inswapper algorithms), more information is here (PR#321)

Full size demo preview

• Sorting facemodels alphabetically
• A lot of fixes and improvements

0.5.0

What's New:

• Huge performance boost of the image analyzer's module! 10x speed up! Working with videos is now a pleasure!

• 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)!

• 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):

• 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:

• ReActorBuildFaceModel Node got "face_model" output to provide a blended face model directly to the main Node:

Basic workflow 💾

• 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"
• Spandrel lib support for GFPGAN
• Fixes and improvements

0.4.2

What's New:

• 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 - more info
• GPEN-BFR-512 and RestoreFormer_Plus_Plus face restoration models support - more info
• Fixes and improvements

0.4.1

What's New:

• Face Restore Visibility and CodeFormer Weight (Fidelity) options are now available

• Separate Node for the Face Restoration postprocessing
• (Windows) Installation can be done for Python from the System's PATH
• CUDA 12 Support
• A lot of fixes and improvements

0.4.0

What's New:

• 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

• Inputs are optional now, just connect one of them according to your workflow; if both is connected - image has a priority
• Different fixes and improvements

0.3.1

What's New:

• CUDA support alongside with CPU support
• A lot of fixes and improvements

0.3.0

What's New:

• Built-in Face Restoration
• Insightface models were moved to the ComfyUI\models directory
• Huge boost when swapping several faces
• Node Enabled (ON/OFF) Toggle added
• MPS torch device support for retinaface module
• Source and Target images hashing -> good speed boost of images processing
• A lot of fixes and improvements

0.2.0

The First version (0.1.0) Base: Simplified version of SD WebUI ReActor extension + the first version of @ssitu ComfyUI_roop (thank you for the great work)

What's In This Release (0.2.0):

• Gender detection added
• Different fixes and improvements

You can also download the very simple and stable v0.1.1 from the Assets below