Edit or combine images with a text instruction
Open this ready-to-run workflow on Floyo. No install needed.
HOW IT WORKS
Step 1. Upload your main image. The image you want to edit. Use it on its own to change clothing, backgrounds, lighting, or objects. Works great with: portraits · product photos · characters · fashion photography
Step 2. Add a second image (optional). Upload another image to combine two photos, drop a subject into a new scene, or borrow a background or object from it. Skip this step to edit one image.
Step 3. Describe your edit. Write exactly what you want, and name the images when you combine them, like "place the person from image 1 inside the castle from image 2" or "change the outfit to a black leather jacket."
Step 4. Hit run and download. The model generates the edit in a few steps. Preview it in the workflow, then download. Ready for: Photoshop · Figma · Canva · any editor
First time? Leave every setting as-is. The defaults (720 x 1280 · 6 steps · guidance 1 · random seed) are the right starting point for almost every edit.
Overview
This workflow edits and combines images from a text instruction using Mage Flow Edit Turbo, a fast open-source editing model from Microsoft. It takes one or two images. With one, it changes backgrounds, outfits, lighting, or objects. With two, it merges them, so you can place a person from one photo into the scene of another or pull an object across. A Qwen3-VL encoder reads your references and follows the instruction, and a Flux2 Klein consistency LoRA keeps composites clean when you combine two images. Turbo means few steps, so an edit comes back in about 20 seconds. You upload your images, describe the edit, and download the result. No setup, no nodes to wire.
Who it's for: creators, marketers, and product teams who want instruction-based editing and two-image compositing in ComfyUI without wiring the nodes from scratch. Not for: pixel-perfect retouching with zero iteration. Complex composites still need a clear prompt, and some edits take a couple of tries.
Why Floyo
Floyo is the only ComfyUI platform built for teams in the browser.
Made for teams. Share run history, files, and models across your whole team. A teammate opens your exact run and picks up where you left off. No file handoffs, no version confusion.
No install, no setup. Every workflow and model is preloaded. Open it in your browser and run. Nothing to download, nothing to configure.
No local hardware. Workflows run on H100 NVL GPUs, so heavy models run fast without a card of your own. Your VRAM stops being the limit.
Open and closed models in one place. Floyo runs open-source workflows and API models side by side.
How to use (in your browser on Floyo)
Upload your main image, and a second image if you want to combine two.
Describe the edit, naming the images when you combine them, then run.
Download the result, ready for any editor.
Expectations The models are preloaded, so there is nothing to download. Running it needs a free Floyo account. Each edit comes back in about 20 seconds, so trying variations stays quick. The prompt does the work: name the environment, clothing, objects, lighting, and camera angle, and the result gets cleaner. A few things to know. Clear, high-resolution inputs edit better than compressed or low-res ones. Two reference images composite well, but very crowded scenes and tiny or distant faces are harder. Want sharper output? Raise steps to 8 to 10. Want a faster preview? Drop them to 4 to 5.
Use Cases
Background Replacement. Move a subject into a new environment from a text prompt, no manual masking.
Image Compositing. Combine two photos into one scene, placing a subject or object from one into the other.
Outfit & Product Edits. Swap clothing on a person or drop a product into a marketing scene with the setting intact.
AI Photography. Turn existing photos into editorial, travel, lifestyle, or fashion images from a single instruction.
What can Mage Flow Edit Turbo do to your images?
