Reve 2.1 · Edit (Image to Image)

ABOUT THE WORKFLOW

Edit an image
Upload an image and describe the change, and the model plans the edit as a layout, then re-renders at native 4K. It changes the part you name and keeps everything you do not mention, so you can revise one element without re-rolling the whole picture.

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 an edit as a structured layout before rendering at native 4K. It edits individual elements without re-rolling the whole picture, and it is strong at in-image text changes and design revisions.

HOW IT WORKS

Step 1. Upload your image
The image you want to edit.
Works great with: photos · posters · packaging · designs

Step 2. Describe the edit
Say what to change, add, remove, or restyle, and which part, like "change the headline to 'SUMMER SALE' and keep the layout." Be specific about what stays and what changes.

Step 3. Hit run and download
The model plans the edit, re-renders at native 4K, and 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.

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

• Editing text in the image — spell out the new words in quotes, exactly as they should read. The model renders text faithfully.

• Keeping the rest intact — name what changes and what stays, since the model holds everything you do not mention.

• Changing the frame shape — set the aspect ratio, though a large change from the original can crop or extend the image.

• Need a different file type — switch the output format to match where the image is going.

Prompt: Say what changes and what stays, and point to the part of the image, like "replace the sky with a sunset, keep the building and the people." For text, put the new words in quotes exactly as they should appear. Specific, targeted edits land better than broad instructions.

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

✏️ Targeted Edits
Change one element and keep the rest of the image intact.

🔤 Text Swaps
Update a headline, label, or sign with new, legible text.

🎨 Design Revisions
Restyle or adjust a poster or layout without rebuilding it.

📦 Packaging Updates
Change product text or elements on a pack shot at 4K.

WHAT WORKS BEST / WHAT TO AVOID

✅ Works great

• Specific edits that name what stays

• In-image text changes spelled out

• Design and layout revisions

• Single, clear source images

⚠️ May produce softer results

• Vague instructions like "make it better"

• Photoreal face and hand edits

• Many changes packed into one prompt

• Large aspect-ratio changes from the original

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 edit mode, it plans your change as a structured layout and re-renders the result at native 4K. Because the image is handled as an editable layout, it can change one element without re-rolling the whole picture.

How does editing with Reve 2.1 work?
You upload an image and write a prompt describing the change, and the model applies it while keeping everything you do not mention. It reads the image as a layout of regions, objects, and text, so it can target the part you name, then renders the edited result at 4K. Specific instructions about what to change and what to keep give the cleanest edits.

Can Reve 2.1 edit text inside an image?
Yes. Changing in-image text is one of its strengths, so you can swap a headline, label, or sign and get legible, correctly placed type. Put the new words in quotes in your prompt, exactly as they should read, and the model renders them in place.

Does it keep the rest of the image unchanged?
It holds everything you do not mention and changes only the part you name, which is the point of its layout-aware editing. To keep an edit contained, say what stays as well as what changes, for example "swap the jacket to red, keep the pose and background."

What resolution are the edits?
Reve 2.1 renders edited images 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 edits 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 the 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 an image, describe the edit, 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 edits a poster 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 an image, describe the change, and run it.

→ Launch Workflow, Free

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