# Image Generation

The Image Generation tool lets you create AI-generated images from text prompts directly within the chat interface — powered by **Nano Banana 2**.

***

#### What It Does

When Image Generation is enabled, describe an image in your prompt and the model generates it inline within the chat. You can generate images from scratch, edit uploaded images, blend multiple images, or create variations — all from within the conversation.

Common use cases:

* Ad creatives and campaign visuals
* Brand mood boards and visual references
* UI concept visualization and wireframe illustrations
* Storyboarding and narrative visuals
* Social media content drafts

***

#### How to Enable It

Toggle **Image Generation** on in the Toolkit panel. Include your image description in the prompt — be specific about style, composition, tone, and subject for better results.

**Example prompt:**

```
A minimalist flat-design illustration of a robot reading a book,
soft pastel colors, white background, suitable for a tech blog header.
```

***

#### Key Capabilities

<table><thead><tr><th width="290.4593505859375">Scenario</th><th>What to Do</th></tr></thead><tbody><tr><td><strong>Generate from scratch</strong></td><td>Describe the image in your prompt</td></tr><tr><td><strong>Edit an uploaded image</strong></td><td>Attach your image in the message and describe the edit</td></tr><tr><td><strong>Edit a previously generated image</strong></td><td>Reference the image by its position in the conversation (e.g., "edit the third image")</td></tr><tr><td><strong>Blend multiple images</strong></td><td>Upload 2 or more images and describe the desired composition</td></tr><tr><td><strong>Keep character consistent</strong></td><td>Use character consistency prompts across multiple scenes</td></tr><tr><td><strong>Generate variations</strong></td><td>Ask for multiple outputs from the same prompt</td></tr><tr><td><strong>Change output size</strong></td><td>Specify resolution in your prompt (0.5K to 4K) and aspect ratio</td></tr></tbody></table>

{% hint style="info" %}
The more specific your prompt, the more accurate the output. Include details like style (photorealistic, illustration, flat design), mood, color palette, and intended use.
{% endhint %}


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.qolaba.ai/chatbot/toolkit/image-generation.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.