# Image Edit Nodes

Atlas provides powerful image-editing nodes that can accept **text + at least one image input**:

* **Text + Image → Image Node**
* **Text + Image List → Image Nodes**
* **Edit Image with Text Node**

These nodes share the same core idea:

* You provide an image (or multiple images) and a text instruction, and the node generates a modified image using the chosen backend.

They differ in how much freedom the model has:

* Text+ Image **→** Image and Text + Image List **→** Image nodes allow **fully generative edits**
* Edit Image with Text node keeps the **original image untouched except for the specified modification**.

## Nodes Overview

### Text + Image **→** Image  <a href="#multimodal-node" id="multimodal-node"></a>

A flexible, image-conditioned generation engine.

* Requires text + image(s)
* Merges all input images with the instruction
* Allows scene transformations, object replacement, isolation
* Produces new images guided by the provided visuals
* Different backends = different image generation models

### Text + Image List **→** Image  <a href="#multimodal-node" id="multimodal-node"></a>

A versatile, multi-reference image generation engine.

* Requires a text prompt + an array of up to 4 images
* Synthesizes multiple visual inputs based on complex text instructions
* Supports object isolation, composition of multiple scenes, and perspective shifts
* Produces a single output image by referencing specific inputs (e.g., `image_0`, `image_1`)
* Different backends (Gemini, Reve, Flux, etc.) offer varying levels of aesthetic quality and logic handling.

<figure><img src="https://3654894688-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FR7boiMixMhR4q36Ns33Y%2Fuploads%2FZVP9kLw21vuVUdfQZJ22%2Fimage.png?alt=media&#x26;token=49de4912-14d9-4b9c-82d3-0264ac1eb1df" alt="" width="563"><figcaption></figcaption></figure>

### Edit Image with Text <a href="#precise-text-edit-node" id="precise-text-edit-node"></a>

A constrained version that **preserves the original image**.

* Requires text + one image
* Performs **targeted edits only**
* Maintains composition, style, perspective, lighting
* Perfect for additive changes (e.g., “add vines”, “add lanterns”, “make it snowy”)
* Can change aspect ratio to expand the scene

<figure><img src="https://3654894688-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FR7boiMixMhR4q36Ns33Y%2Fuploads%2FZx5dTUpnggvqwmF9pdfD%2Fimage.png?alt=media&#x26;token=256b4223-4f8b-4122-9312-1f83764f6703" alt="" width="563"><figcaption></figcaption></figure>

<figure><img src="https://3654894688-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FR7boiMixMhR4q36Ns33Y%2Fuploads%2FjmgFNjgiaZPv6Mfm7A8G%2Fimage.png?alt=media&#x26;token=3b0750d4-43ad-4875-9a3b-8ae81dc50aa8" alt="" width="563"><figcaption></figcaption></figure>

***

## Inputs

Edit Image with Text node and Text + Image → Image node share the same input structure:

#### Required: <a href="#required" id="required"></a>

* **Text prompt**
* **At least one image**

Optional:

* **Multiple images** (Text + Image List → Image only)

These inputs can be manually uploaded or generated via other nodes.

## Backends (the AI model powering the node)

You may choose from multiple backend generative models. Each backend interprets images differently:

* Some are more realistic
* Some preserve structure better
* Some are more stylized
* Some adhere more strictly to prompts&#x20;

Switching backend changes the artistic and structural behavior.

<figure><img src="https://3654894688-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FR7boiMixMhR4q36Ns33Y%2Fuploads%2FTsuQ4E3OP1hoBaqgdeLY%2Fimage.png?alt=media&#x26;token=d64fa65a-511f-4f41-aa22-fc214aa90541" alt="" width="563"><figcaption></figcaption></figure>

***

## Seed Control

Changing the seed gives new variations while keeping:

* the same structure
* the same instruction
* the same conditioning images

Keeping the seed = reproducible outputs.

***

## Example Use Cases: Text + Image → Image&#x20;

### Style Transformation of a Scene <a href="#a-style-transformation-of-a-scene" id="a-style-transformation-of-a-scene"></a>

Turn a normal bookshelf into a **fantasy enchanted bookshelf**.

<figure><img src="https://3654894688-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FR7boiMixMhR4q36Ns33Y%2Fuploads%2Fro6NBjHJMlOEXVGJHz8g%2Fimage.png?alt=media&#x26;token=36188d6b-0986-43d7-acd6-a537f4d71464" alt="" width="563"><figcaption></figcaption></figure>

### Variation with Seed Change <a href="#b-variation-with-seed-change" id="b-variation-with-seed-change"></a>

Same prompt + same image + same backends + **different seeds** = different variations.

<figure><img src="https://3654894688-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FR7boiMixMhR4q36Ns33Y%2Fuploads%2F6KimO9D4W6SMRdnIMTl2%2Fimage.png?alt=media&#x26;token=6af53f63-5cdf-430f-8163-a9e00f33ec54" alt="" width="563"><figcaption></figcaption></figure>

### Restyling While Preserving Layout <a href="#c-restyling-while-preserving-layout" id="c-restyling-while-preserving-layout"></a>

Transform the bookshelf into an **old, damaged one** while keeping the structure.

<figure><img src="https://3654894688-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FR7boiMixMhR4q36Ns33Y%2Fuploads%2F6W13LQhQZ4GmYWjmM1TC%2Fimage.png?alt=media&#x26;token=416f158d-54de-4ca9-83ef-2e701dfd0817" alt="" width="563"><figcaption></figcaption></figure>

### Isolate an Object with Neutral Background <a href="#d-isolate-an-object-with-neutral-background" id="d-isolate-an-object-with-neutral-background"></a>

Perfect for Image → 3D workflows.

<figure><img src="https://3654894688-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FR7boiMixMhR4q36Ns33Y%2Fuploads%2FTEa6ECNChBYt2M36ZH7K%2Fimage.png?alt=media&#x26;token=a767a64b-1016-4550-af78-d064fea2dc40" alt="" width="563"><figcaption></figcaption></figure>

### Multi-Image Conditioning for Object Replacement <a href="#e-multi-image-conditioning-for-object-replacement" id="e-multi-image-conditioning-for-object-replacement"></a>

Replace specific items on a shelf using three reference object images.

<figure><img src="https://3654894688-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FR7boiMixMhR4q36Ns33Y%2Fuploads%2F624kGE9TFakRdC9GpS4B%2Fimage.png?alt=media&#x26;token=d09ed51e-c762-4b6d-ba75-242caa33023a" alt="" width="563"><figcaption></figcaption></figure>

***

## Example Use Cases: Edit Image with Text Node

The **Edit Image with Text node** keeps the original image intact, modifying only what you request.

#### Adding Details to a Generated Asset <a href="#a-adding-details-to-a-generated-asset" id="a-adding-details-to-a-generated-asset"></a>

Example: adding decorative elements or small props without changing the underlying concept.

<figure><img src="https://3654894688-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FR7boiMixMhR4q36Ns33Y%2Fuploads%2Fxmb6ATLLxCikwbrUaGZJ%2Fimage.png?alt=media&#x26;token=a59ed4d7-7567-4cf2-854b-cc8fe494a953" alt="" width="563"><figcaption></figcaption></figure>

#### Removing Objects <a href="#b-removing-objects" id="b-removing-objects"></a>

<figure><img src="https://3654894688-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FR7boiMixMhR4q36Ns33Y%2Fuploads%2F6AAGjkZaQ5FDqLmrTSk5%2Fimage.png?alt=media&#x26;token=367032dd-a92e-4b76-9c1d-85a81a0d2de0" alt="" width="563"><figcaption></figcaption></figure>

#### Changing the Design Style <a href="#c-changing-the-design-style" id="c-changing-the-design-style"></a>

You can restyle the asset into a new design language (e.g., Scandinavian / futuristic / gothic) while keeping the **same layout and camera**.

<figure><img src="https://3654894688-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FR7boiMixMhR4q36Ns33Y%2Fuploads%2FtDeKMmrkJqAB5vXVfhRX%2Fimage.png?alt=media&#x26;token=e669243f-394d-4736-83a3-bf4e9aec5c1d" alt="" width="563"><figcaption></figcaption></figure>

Changing the **seed** gives controlled alternatives of the *same style*.

<figure><img src="https://3654894688-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FR7boiMixMhR4q36Ns33Y%2Fuploads%2FpEDjB78YEDgzptYyqH2U%2Fimage.png?alt=media&#x26;token=a8258a37-fbda-4cbe-8b2b-024aa2a84e51" alt="" width="563"><figcaption></figcaption></figure>

#### Changing Image Aspect Ratio <a href="#d-changing-image-aspect-ratio" id="d-changing-image-aspect-ratio"></a>

<figure><img src="https://3654894688-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FR7boiMixMhR4q36Ns33Y%2Fuploads%2FkPQtubK4yvPVZMcck9bb%2Fimage.png?alt=media&#x26;token=487ac58a-ccf1-48bc-8f56-9b0fd8287b50" alt="" width="563"><figcaption></figcaption></figure>

## Capabilities Summary

#### Text + Image → Image Node  & Text + Image List → Image Node <a href="#multimodal-node-1" id="multimodal-node-1"></a>

* generative transformations
* scene edits
* object replacement
* object isolation
* image mixing
* multi-image conditioning

#### Edit Image with Text Node <a href="#precise-text-edit-node-1" id="precise-text-edit-node-1"></a>

* preserves the original image
* applies minimal, targeted changes
* ideal for controlled additions
* supports aspect-ratio changes
* keeps lighting/composition intact

## Summary

Both nodes require **text + image input** and work with backend models, but their behavior differs:

#### Text + Image → Image Node  & Text + Image List → Image Node <a href="#multimodal-node-1" id="multimodal-node-1"></a>

* Broad, creative, generative
* Perfect for image transformation, restyling, object edits, isolation

#### Edit Image with Text Node <a href="#precise-text-edit-node-1" id="precise-text-edit-node-1"></a>

* Controlled, minimal, additive
* Perfect for polishing assets, expanding images, subtle modifications