ComfyUI: Face swapping with InstantID

ComfyUI Try it →Watch full video →AI Search · Aug 2024

Demo summary

Demonstrates the full setup and execution of InstantID to swap Will Smith's face onto a generated policeman character in both realistic and watercolor styles.

Step-by-step

Insert the 'Apply InstantID' node between your prompt nodes and the K Sampler.
Connect the model, positive prompt, and negative prompt to the Apply InstantID node, then route them to the K Sampler.
Add a 'Load Image' node and upload the source face image.
Connect a 'ControlNet Loader' node and select the 'instantid/diffusion_pytorch_model'.
Add an 'InstantID Face Analysis' node and set the provider to 'CUDA' if using a compatible GPU.
Connect an 'InstantID Model Loader' node and ensure 'ip-adapter.bin' is selected.
Adjust the 'Weight' to control face influence and set 'Start' and 'End' values for the step range.
Enter your positive and negative prompts and click 'Queue Prompt' to generate.

Options

Set 'End' value to 0.5 to stop applying the face swap halfway through the sampling steps.
Switch prompts from 'realistic' to 'watercolor painting' to change the artistic style.

Watch out for

The process requires multiple manual connections between the model, prompts, and K Sampler.
You must have the 'ip-adapter.bin' file installed for the Model Loader to function.

Tips

Use face swapping to maintain consistent characters across animations or comic books.
Set the 'End' value to 1 to apply the face swap throughout all sampling steps.
Hold Control and Shift while dragging to move multiple nodes and keep the workflow organized.

Highlights

“there's a lot of connections that needs to be made and I wish this process was simpler but it is what it is”

All demos from “Master AI image generation - ComfyUI FULL TUTORIAL”

7:390:44Basic text-to-image generation in ComfyUIThe user demonstrates a basic text-to-image workflow using the RealVisXL model to generate an image of a castle in a forest.ComfyUI· Text to Image
8:418:40Building a ComfyUI workflow from scratchA step-by-step walkthrough of adding nodes (Checkpoint, CLIP Text Encode, KSampler, VAE Decode) and connecting them to build a custom image generation pipeline.ComfyUI· AI Image Generator
19:571:09Generating a medieval warrior with batch processingDemonstrates generating multiple images of a medieval warrior by increasing the batch size in the Empty Latent Image node.ComfyUI· AI Image Generator
25:330:32Importing workflows from image metadataShows how to drag an existing AI-generated image into the ComfyUI canvas to automatically reconstruct the entire node workflow used to create it.ComfyUI· AI Image Generator
30:073:41Upscaling images using modelsDemonstrates upscaling a low-resolution 512x512 image using the 4X Ultra Sharp model to add clarity and detail.ComfyUI· AI Image Upscaler
36:021:32Using Preview Chooser for selective upscalingShows how to use the Image Chooser node to generate a batch of images and selectively progress only one specific image to the upscaler.ComfyUI· AI Image Upscaler
41:391:29Image-to-image generation with denoisingDemonstrates the image-to-image process by loading an existing photo and adjusting the denoising strength to create variations.ComfyUI· Image to Image
43:496:52Tiled upscaling with Ultimate SD UpscaleA detailed demo of the Ultimate SD Upscale node, showing how tiled upscaling generates significantly higher facial detail than standard upscaling.ComfyUI· AI Image Upscaler
58:094:05Controlling character poses with ControlNetDemonstrates using the OpenPose pre-processor and ControlNet Union model to force a generated princess character into a specific pose from a reference image.ComfyUI· AI Image Generator
1:02:141:23Landscape composition control with Canny ControlNetShows how to use the Canny edge pre-processor to maintain the shape of mountains while changing the lighting to a sunset.ComfyUI· AI Inpainting
1:09:444:55Face swapping with InstantIDCurrentDemonstrates the full setup and execution of InstantID to swap Will Smith's face onto a generated policeman character in both realistic and watercolor styles.ComfyUI· AI Face Swap Generator
Watch “Master AI image generation - ComfyUI FULL TUTORIAL” →

AI Face Swap Generator

1:09:444:55Face swapping with InstantIDCurrentDemonstrates the full setup and execution of InstantID to swap Will Smith's face onto a generated policeman character in both realistic and watercolor styles.AI Search
2:081:55Configuring LTX 2.3 Face Swap Workflow in ComfyUIThe creator walks through a custom ComfyUI workflow, showing how to load the LTX 2.3 model with the face swap LoRA and set up resolution scaling and frame count calculations.Veteran AI
8:090:41Close-up Face Swap TestA demonstration of a close-up face swap where the LTX 2.3 model transfers facial expressions and lip movements from a driving video to a target portrait.Veteran AI
9:521:03Testing Face Swap with Scene CutsThe video demonstrates how the LTX 2.3 face swap LoRA handles a reference video with a camera cut and clothing change, showing its ability to maintain character features across transitions.Veteran AI
10:550:39Underwater Environmental Interference TestA demonstration of the face swap effect in an extreme underwater environment, showing the model's ability to reveal and swap a face through water surface interference.Veteran AI
1:110:46Inpainting face swap with ComfyUIThe creator demonstrates an inpainting face swap workflow in ComfyUI by loading a reference and target image to achieve a high-resemblance result on a close-up shot.Yaroflasher
1:410:46Prepare driving data and auto-prompts with Qwen2-VLThe demo shows running pose detection on source footage and using Qwen2-VL (referred to as Gwen VL) to generate a semantic text description from a reference image for the face swap.ComfyUI
3:280:27Simplified face swap using ComfyUI App ModeA demonstration of the simplified 'App Mode' interface where users can upload footage and a reference image to perform a face swap without interacting with the node graph.ComfyUI