> For the complete documentation index, see [llms.txt](https://help.chatlyai.app/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.chatlyai.app/products-and-features/ai-images/what-is-ai-image-generation.md).

# What is AI Image Generation?

AI Image Generation lets you create high-quality visuals directly within Chatly. You can generate new images or edit existing ones using different image models, all through a simple conversational experience.

{% embed url="<https://www.youtube.com/watch?v=3540m41YL4I>" %}

### **Available Models**

* **Ideogram 3.0** *(Generation only)*
* **Nano Banana** *(Generation model - also supports editing))*
* **Nano Banana** **Pro** *(Generation model - also supports editing))*
* **Nano Banana** **2** *(Generation model - also supports editing))*
* **Flux.2 Pro** *(Generation model - also supports editing)*
* **Seedream 4.0** *(Generation model - also supports editing)*
* **Seedream 4.5** *(Generation model - also supports editing)*
* **Seedream 5 Lite** *(Generation model - also supports editing)*
* **Flux Kontext Pro** *(Image Editing model*)
* **Z Image Turbo** *(Generation model - also supports editing*)
* **Qwen Image Edit** (*Image Editing Model)*
* **Qwen Image** *(Generation Only)*
* **xAI Image** *(Generation model - also supports editing)*

### **Key Capabilities**

Chatly’s conversational AI image generation feature supports:

* **Image Generation:** Create new images from text prompts.
* **Image Editing:** Edit your own images.
* **Reference Images:** Attach up multiple reference images per request for better results.
* **Aspect Ratios:** Control image dimensions per model: 1:1, 3:4, 4:3, 16:9, 9:16.
* **Conversational Workflow:** Refine results by chatting naturally with the image agent.
* **Variations:** Each generation produces 2 images for easy comparison.
* **Enhancement Tools:** Upscale and Background Removal (additional token costs).
* **Image Manual Editing Options:** users can apply adjustments/filters to their images in full view including tint, saturation, highlights, exposure etc.

### **Token Usage**

* Token consumption depends on the **model** used
* Each request generates 2 images → **tokens per image × 2**
* Example: If one image = 20 tokens, the request = 40 tokens

### Token Consumption by Model

| **Model**            | **Credits per image** | **Tokens per request (2 images)** |
| -------------------- | --------------------- | --------------------------------- |
| **Seedream 4.0**     | 18                    | 36                                |
| **Seedream 4.5**     | 24                    | 48                                |
| **Nano Banana**      | 24                    | 48                                |
| **Nano Banana Pro**  | 90                    | 180                               |
| **Flux.2 Pro**       | 27                    | 54                                |
| **Flux Kontext Pro** | 24                    | 48                                |
| **Qwen Image Edit**  | 18                    | 36                                |
| **Qwen Image**       | 12                    | 24                                |
| **Z Image Turbo**    | 3                     | 6                                 |
| **Ideogram 3.0**     | 36                    | 72                                |
| **xAI Grok Image**   | 14                    | 28                                |
| **Nano Banana 2**    | 72                    | 144                               |
| **Seedream 5 Lite**  | 21                    | 42                                |

### **Token Consumption for Enhancements**

| Enhancement            | **Credits Deduction / per image** | **Notes**                                       |
| ---------------------- | --------------------------------- | ----------------------------------------------- |
| **Upscale**            | 20 tokens                         | Applies to a single image, improves resolution. |
| **Background Removal** | 1 token                           | Applies to a single image, removes background.  |

You get **100** tokens **FREE** on signup for image generation. 🎉<br>

<table data-view="cards"><thead><tr><th></th><th data-hidden data-card-cover data-type="image">Cover image</th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td>How to Use Image Generation</td><td><a href="/files/lZOEJXUAtXmdlNLLqdVl">/files/lZOEJXUAtXmdlNLLqdVl</a></td><td><a href="/pages/pR7SkuSlKZwGfZrOhAYB">/pages/pR7SkuSlKZwGfZrOhAYB</a></td></tr><tr><td>Image Generation Use Cases</td><td><a href="/files/17ec3ZDph31JwHSKwisF">/files/17ec3ZDph31JwHSKwisF</a></td><td><a href="/pages/WZqCC75R02fPq3ViFoaQ">/pages/WZqCC75R02fPq3ViFoaQ</a></td></tr></tbody></table>


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## 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, and the optional `goal` query parameter:

```
GET https://help.chatlyai.app/products-and-features/ai-images/what-is-ai-image-generation.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.