Reve 2.1 · Remix (Multi-Image)

ABOUT THE WORKFLOW

Blend images into one
Upload up to eight reference images and describe how to combine them, and the model blends their subjects, styles, and elements into a new image at native 4K, matching lighting and shadows across the mix. Tell it which element to take from which image.

Partner node. This workflow calls an external API, so each run uses credits from your API wallet. No API key needed. Floyo handles the connection.

Model

• Reve 2.1 by Reve AI. A layout-first image model, ranked #2 on the Text-to-Image Arena, that plans a remix as a structured layout before rendering at native 4K. It blends elements from up to eight references with coherent lighting and shadows, and it is strong at multi-reference compositing and in-image text.

HOW IT WORKS

Step 1. Upload your reference images
One to eight images to draw from. Two are connected by default. Each one feeds a subject, style, setting, or element.
Works great with: subject + scene · product + background · style references

Step 2. Describe the mix
Say how to combine them and what to take from each, like "put the person from image 1 into the cafe from image 2, in the style of image 3." Be specific about what to keep from each image.

Step 3. Hit run and download
The model blends the references and renders at native 4K, then saves a PNG. Preview it, then download.
Ready for: print · Photoshop · Figma · Canva

First time? Leave every setting as-is. The defaults (16:9 · 1 image · PNG) are the right starting point for almost everyone.

RECOMMENDED SETTINGS

Quick-start guide. Find the goal that matches yours and copy the settings.

• Standard use (most people) — 16:9, 1 image, PNG. The right starting point for almost everyone.

• Combining more sources — connect more reference images, up to eight. More references give the model more to work with, but also more to reconcile.

• Want variants to choose from — raise the number of images to get several blends and keep the best. Each one is another generation and adds to the cost.

• Cleaner blends — use references with consistent lighting and style, since mismatched sources are harder to combine.

• Getting text right — spell out any in-image words in quotes, exactly as they should read.

• Changing the frame shape — set the aspect ratio to match where the image is going.

Prompt: Tell the model which element to take from which image, like "the jacket from image 1, the pose from image 2, on the street from image 3." Vague prompts produce unpredictable blends, so name the source of each part. Put any in-image words in quotes exactly as they should appear.

LEARN

📹 Videos

• Intro to Floyo

• ComfyUI 101 Free Course ft. Sebastian Kamph

• Floyo 101 for Team Collaboration

✨ Quick links

• Help docs

• LoRA Training guide

• Discover more workflows

USE CASES

🧩 Multi-image Compositing
Combine subjects, scenes, and styles from several images into one.

👗 Style Transfer
Apply the look of one image to the subject of another.

🛍️ Product in a Scene
Place a product from one shot into a setting from another.

🎨 Moodboard to Image
Turn a set of references into a single finished composition.

WHAT WORKS BEST / WHAT TO AVOID

✅ Works great

• References with consistent lighting and style

• Clear instructions on what to take from each

• Two to a few strong references

• A defined result to aim for

⚠️ May produce softer results

• Vague prompts with no per-image direction

• Many references that fight each other

• Mismatched lighting across sources

• Photoreal faces and hands

FAQ

What is Reve 2.1?
Reve 2.1 is a layout-first image model from Reve AI, released on July 9, 2026, and ranked #2 on the Text-to-Image Arena. In remix mode, it takes up to eight reference images and blends their elements into a new image, planning the composition as a structured layout and rendering it at native 4K.

How does remixing multiple images work?
You upload one to eight reference images and write a prompt describing how they should combine, and the model draws a subject, style, setting, or element from each. It reconciles them into one image with coherent lighting and shadows, so the parts read as a single scene rather than a collage. The clearest results come from telling it what to take from which image.

How many reference images can I use?
You can connect up to eight reference images, and two are wired by default. More references give the model more to draw from, but also more to reconcile, so a handful of strong, consistent sources usually blends more cleanly than eight mismatched ones.

How do I control which parts come from which image?
Name the source of each element in your prompt, for example "the coat from image 1, the background from image 2." The model responds to specific, per-image direction, while a vague prompt leaves it to guess and produces less predictable blends. References that share lighting and style combine more cleanly.

What resolution is the output?
Reve 2.1 renders the remixed image at native 4K, up to 4096 by 4096, with no separate upscaling step. The detail holds up for print, large format, and close client review straight out of the workflow.

Can I use Reve 2.1 images commercially?
Reve 2.1 is a proprietary Reve AI model accessed through its API and plans, so commercial use is supported under Reve's plan terms rather than an open license. Review Reve's current terms for your plan, and make sure you hold the rights to every reference image you upload.

How to run Reve 2.1 online?
You can run Reve 2.1 online through Floyo. No installation, no setup, no API key to wire up. Open the workflow in your browser, upload your references, and hit run. Free to try.

WHY FLOYO?

Floyo is the only platform with team collaboration for ComfyUI in the browser. You run workflows with no install. You share run history, assets, and models across your team. You pay only when you generate. Floyo supports open-source and closed-source models.

A designer builds a composite and likes the result. A teammate opens that exact run from shared history and keeps going. No file handoffs. No version confusion.

For studios and enterprise teams, Floyo adds private workspaces, pooled resources, and a team usage dashboard. Other ComfyUI cloud tools run for one person at a time. Floyo runs for the whole team, with transparent per-generation costs.

Ready to try it?
Upload your references, describe the mix, and run it.

→ Launch Workflow, Free

Questions? Watch the free course or check the FAQ above.