ComfyUI: Generate composite image with Flux 2

ComfyUI Try it →Watch full video →WINBUSH · Mar 2026

Demo summary

The creator demonstrates image-to-image generation by uploading two reference photos and using a text prompt to replace a logo on a coffee can with his own headshot using the Flux model.

Step-by-step

Press R on your keyboard to refresh the ComfyUI interface until the nodes turn white
Drag the base image (e.g., the coffee can) into the top reference image slot
Drag the replacement image (e.g., the headshot) into the bottom reference image slot
Enter a text prompt in the prompt field referencing the images as 'reference image one' and 'reference image two'
Click the blue Run button in the top right-hand corner
Monitor the queue percentage to track generation progress

Watch out for

Nodes must be white before proceeding; if they are red, the setup is not correctly loaded or refreshed
Processing time is dependent on your specific GPU hardware

Tips

Refer to the images specifically as 'reference image one' and 'reference image two' in your prompt to help the model identify which photo is which

Highlights

“I find this is an easy way to tell it what photo I'm talking about.”

All demos from “ComfyUI in 20 Minutes: Absolute Beginner Guide to Getting Started”

4:150:35Launch ComfyUI on WindowsThe creator demonstrates how to launch the portable version of ComfyUI by running the 'run_nvidia_gpu' batch file and accessing the interface via a web browser.ComfyUI· AI Image Generator
10:071:30Browse and load ComfyUI templatesThe creator demonstrates how to navigate the templates menu, filter for local models, and load a Flux 2 image generation workflow.ComfyUI· AI Image Generator
16:571:43Generate composite image with Flux 2CurrentThe creator demonstrates image-to-image generation by uploading two reference photos and using a text prompt to replace a logo on a coffee can with his own headshot using the Flux model.ComfyUI· AI Inpainting
20:010:28Text-to-image manipulation in ComfyUIThe video shows how to use a text prompt to attempt to rotate an object in an image within a specific node-based workflow.ComfyUI· AI Inpainting
Watch “ComfyUI in 20 Minutes: Absolute Beginner Guide to Getting Started” →

AI Inpainting

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.AI Search
6:360:29Adjust mask expansion settingsThe user demonstrates adjusting the 'Grow Mask with Blur' node's expand value to accommodate larger replacement characters.MDMZ
3:120:44Anime character replacement with MochaA demonstration of replacing one anime character with another using a reference image, highlighting the tool's performance on complex outfits and hair.AI Search
7:201:48Edit image details with Flux KontextThe user shows how to load a reference image and use a text prompt to change specific features, such as changing a cartoon bunny's eye color to red.pixaroma
19:191:08Modify hairstyles and facial featuresThe creator shows how to change a subject's hair color and style (e.g., to a blunt bob with bangs) while attempting to maintain facial consistency using Flux Kontext.pixaroma
21:030:26Edit text within an imageA demonstration of Flux Kontext's ability to change text on a 3D render from 'Welcome' to 'Pixaroma' while maintaining the original font style and perspective.pixaroma
23:191:55Remove objects using Mask Editor and InpaintingThe user demonstrates precisely removing a necklace from a portrait by painting a mask in the ComfyUI Mask Editor and using an inpainting prompt.pixaroma
16:571:43Generate composite image with Flux 2CurrentThe creator demonstrates image-to-image generation by uploading two reference photos and using a text prompt to replace a logo on a coffee can with his own headshot using the Flux model.WINBUSH
20:010:28Text-to-image manipulation in ComfyUIThe video shows how to use a text prompt to attempt to rotate an object in an image within a specific node-based workflow.WINBUSH
15:063:12Transform 3D scenes with Qwen2-VL (Qwen-Edit)The creator uses the Qwen-Edit workflow to perform complex scene modifications, such as changing weather to rain or snow, while preserving the original 3D geometry and text.Matt Hallett Visual
20:221:07Fix text and faces using Crop and StitchA demonstration of a custom 'crop image' node to isolate specific areas like signs or faces, regenerate them at native resolution, and stitch them back into the high-res image.Matt Hallett Visual
8:230:24Change hairstyles with AIA demonstration of using an outfit change system to apply a new haircut to a character by using a hairstyle image as a reference.Yaroflasher