Wan 2.7 · Image Editing

ABOUT THE WORKFLOW

Edit an Image
Upload a picture and describe the change you want. Wan 2.7 Unified reasons about the edit before it draws, applies the change, and returns the result at the same size as your original. The edit appears in a preview on screen.

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

• Wan 2.7 Unified by Tongyi Lab at Alibaba. Released April 2026. The unified image endpoint of the Wan 2.7 family. Handles generation, editing, and multi-reference work in one model. Includes a thinking mode that reasons about the edit before drawing, which helps complex or layered instructions land more precisely. This is the standard tier.

HOW IT WORKS

Step 1. Upload your picture
The image you want edited. The output is returned at the same size.
Works great with: portraits · product shots · interiors · landscapes

Step 2. Describe the change
Say what should change and what must stay. "Turn this image into a futuristic cyberpunk forest" or "change the jacket to red leather, keep the pose and the face."

Step 3. Add a second picture (optional)
For edits that combine two pictures, like placing a subject from one into the setting of the other.

Step 4. Hit run
The model reasons about the instruction, applies the edit, and returns the result in the preview. Right-click the preview to download.
Ready for: Photoshop · Figma · Canva · any editor

First time? Leave every setting as-is. The defaults (custom size · prompt extend on · thinking mode on · watermark off · random seed) are the right starting point for almost everyone.

RECOMMENDED SETTINGS

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

• Standard edit (most people) — custom size · prompt extend on · thinking mode on · watermark off · random seed. The right starting point for almost everyone.

• The edit changed too much — Name what must stay fixed alongside what changes. "Change the sky to sunset, keep the buildings, the street, and the people unchanged" holds more of the picture in place.

• The edit barely landed — Be more specific. Name the object, the area, and what replaces it rather than giving a broad instruction.

• Complex, layered instruction — Leave thinking mode on. The model reasons through the plan before drawing, which helps when several conditions have to hold at once.

• Speed matters more than precision — Turn thinking mode off. The edit runs faster but may interpret a complex instruction less accurately.

• Your wording is already exact — Turn prompt extend off. Left on, the model rewrites your prompt for richer detail, which helps loose descriptions and works against carefully worded ones.

• Combining two pictures — Connect a second image and say in the prompt what each one contributes, so the model knows which supplies the subject and which the setting.

• Repeat a result you liked — Set a fixed seed number instead of leaving it on random. The same picture, prompt, and seed give you the same edit back.

Prompt: Write the change, not the scene. "Turn the background into a misty forest at dawn, keep the person and the lighting on their face" gives you more than "make it look moody." When you connect two pictures, say what each one is for.

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

🌅 Style and Mood Transfer
Restyle a photo into a different look, time of day, or season while the subject holds.

🖼️ Background and Setting Changes
Swap the background behind a subject without cutting them out by hand.

🛍️ Product Retouching
Adjust a product shot, change the setting, or restyle it for a different listing or market.

🔀 Two-Image Compositing
Combine a subject from one picture with the setting from another in a single pass.

WHAT WORKS BEST / WHAT TO AVOID

✅ Works great

• Specific instructions that name what changes and what stays

• Style transfers and relighting that change mood while keeping the subject

• Layered instructions where several conditions have to hold at once

• Clear, well-lit source images

⚠️ May produce softer results

• Vague instructions like "make it better" or "enhance this"

• Expecting untouched areas to remain pixel-identical

• Edits that conflict with each other in the same prompt

• Leaving thinking mode off for complex multi-step instructions

FAQ

What is Wan 2.7 Unified?
Wan 2.7 Unified is the standard image endpoint of the Wan 2.7 family from Tongyi Lab at Alibaba, released April 2026. It handles text-to-image generation, single-image editing, and multi-reference compositing through one model. Its standout feature is a thinking mode where the model reasons through the instruction before drawing, which helps layered or complex edits land more precisely.

What is the difference between Wan 2.7 Unified and Wan 2.7 Pro Unified?
Both share the same capabilities: thinking mode, editing, generation, and multi-reference work. Pro is the higher-fidelity tier with better detail, and its workflow includes a save step and a before-and-after comparison view. This standard tier is lighter and cheaper per run, with the result appearing in a preview that you right-click to download.

What is thinking mode?
The model plans the edit before it draws. It reads your instruction, reasons about what needs to change and what must stay, and then executes. That planning step is what makes complex, multi-condition edits work better than a single-pass interpretation. It costs extra time per run.

Why is there no save step?
This workflow uses a preview node instead of a save node. The result appears on screen, and you right-click the preview to download it. Adding a SaveImage node after the partner node would save the result automatically.

Is Wan 2.7 Unified open source?
No. Wan 2.7 is API-only with no published weights. Open weights in the Wan family stop at Wan 2.2, which is released under Apache 2.0. This workflow calls the hosted standard endpoint.

How many images can I edit at once?
The workflow connects one image by default, with a second slot open for compositing. The model itself supports up to nine references for generation tasks, though this workflow exposes two.

How to run Wan 2.7 image editing online?
You can run Wan 2.7 image editing online through Floyo. No installation, no setup, no API key to wire up. Open the workflow in your browser, upload a picture, describe the change, 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 runs an edit 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 a picture, describe the change, and run it. The settings are already set.

→ Launch Workflow, Free

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