GUIDE: Image Editor & Combiner - How to write Prompts

Written By Leonid

Last updated 3 months ago

Overview

The Image Editor & Combiner tool lets you modify, combine, or transform any images into completely new visuals — powered by Seedream 4.0.

All operations are censorship-free, so you can edit SFW or NSFW content with full creative freedom.

This model supports:

Image Editing – add, delete, replace, or modify parts of an image
Image Combination – blend or merge multiple images
Reference-based Generation – keep visual consistency (character, outfit, style, or lighting)
Multi-image Composition – use two or more images as sources for new content

🪄 How It Works

Input Type	Description
Image(s)	Upload one or several images. PNG/JPG recommended (avoid WEBP).
Prompt	Describe exactly what you want to change or combine using clear English.
Mode	Edit / Combine / Replace / Style Transfer
Output Resolution	4K
NSFW Mode	Always allowed — all generations are censorship-free.

✏️ Image Editing

You can modify any part of an image using plain language.
Supported operations: add, remove, replace, change color/style, adjust proportions, or alter mood.

Operation	Example Prompt
Add	`Add a silver necklace and earrings to the woman in the picture.`
Remove	`Remove the hat from the man’s head.`
Replace	`Replace the dog with a cat while keeping the same pose and lighting.`
Modify	`Turn the three robots into transparent crystal, colored red, yellow, and green.`

Pro Tip:
Use clear, complete sentences — avoid vague references like “change that one.”

If you want to keep some elements unchanged, explicitly mention them:

Change the background to a sunset sky, keeping the person exactly as in the original.

🎨 Reference-Based Generation

Use another image as a reference to maintain the same character, style, or visual tone.

This is perfect for:

Recreating a character in a new setting
Keeping consistent style across multiple photos
Product or fashion variations

Example Prompts:

Based on the character in Image 1, place her sitting in a cafe with natural lighting. Keep hairstyle, outfit, and facial expression consistent.

Use the style of Image 2 (comic watercolor look) and apply it to Image 1.

Tips:

Use clear reference mapping like “from Image 1”, “in the style of Image 2”.
Mention what should stay the same (identity, clothing, composition) and what should change (background, action, mood).

🧩 Image Combination

Combine subjects, environments, or items from different images to create one cohesive scene.

Scenario	Example Prompt
Merge Characters	`Combine the man from Image 1 and the woman from Image 2 into a single photo where they stand together on a balcony.`
Outfit Transfer	`Dress the model from Image 1 in the outfit from Image 2.`
Style Fusion	`Apply the color tone and lighting from Image 3 to the merged image.`

Pro Tip:
Describe relationships explicitly:

“Replace subject in Image 2 with character from Image 1, using lighting from Image 3.”

🖌️ Drawing & Doodle Input

If describing spatial edits is hard — mark regions visually using simple doodles or boxes.
Just upload a sketch and explain it in your prompt.

Example:

Insert a TV where the red area is marked and a sofa where the blue area is marked. Keep wooden style.

💡 Best Practices

✅ Use natural, visual language (subject + action + environment)
✅ Be explicit about what changes and what stays the same
✅ Use reference images for better stylistic control
✅ Combine no more than 3 inputs per generation for stable results
✅ Avoid contradicting instructions (“bright but dark”, “minimalist with lots of detail”)

🧭 Summary

The Image Editor & Combiner with Seedream 4.0 is your creative studio — capable of merging ideas, characters, and styles seamlessly.

Just describe visually what you want to happen — and it will.

🎨 Think visually. Be clear. Create without limits.