> For the complete documentation index, see [llms.txt](https://fater.gitbook.io/fater-ai-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://fater.gitbook.io/fater-ai-docs/generating-images-with-ai/text-to-image-generation.md).

# Text-to-Image Generation

While Fater excels at editing existing visuals, its **Text-to-Image** capabilities within the **Image Editor** also allow you to **generate new elements or scenes based on your text descriptions (prompts)**. These can be created on a blank canvas or, more commonly, generated with the intention of integrating them into an existing project.

***

### When to Use Text-to-Image

* Generating entirely new objects or characters to composite into your scene.
* Creating background elements or textures.
* Visualizing concepts or specific items described in text.
* Quickly producing options for elements before detailed editing.

***

### Workflow for Generating New Elements with Text-to-Image

1. **Prepare Your Canvas & Context:**
   * **Generation Area Bounding Box:** Adjust the bounding box on the canvas to define the **area and aspect ratio** where you want the new element to be generated.
     * If generating into an existing scene, position and size this box where the new element should appear.
     * If generating a standalone element, the box defines its initial canvas.
   * **Existing Layers (Optional Context):** Models in the "Generate" category *can* sometimes be influenced by visible content within the Generation Area, even if their primary input is the text prompt. If you want a completely clean generation, you might temporarily hide other layers or work in a separate Layer Workspace. However, for generating elements intended to fit an existing scene, leaving relevant context visible *can* be beneficial.
2. **Select a Text-to-Image Model:**
   * Go to the **Model Selector** in the Left Sidebar.
   * Choose the **"Generate"** category tab (✨ icon).
   * Typically, you'll select a model from the **"Basic"** SubCategory for general text-to-image tasks (e.g., "Medium \[Generate/Basic]" or "Turbo \[Generate/Basic]").
3. **Configure Model-Specific Parameters:**
   * In the Left Sidebar, adjust parameters for the chosen model, such as:
     * **Steps**
     * **Guidance Scale**
     * **Seed**
     * *(Other parameters specific to the selected "Generate" model).*
4. **Write a Detailed Text Prompt:**
   * In the **Floating Prompt Area**, write a clear prompt describing the element or scene you want the AI to create within the Generation Area.
   * *(Refer to* [Text Prompts](/fater-ai-docs/core-concepts-ai-and-editor-features/text-prompts.md) *&* [Negative Prompts](/fater-ai-docs/core-concepts-ai-and-editor-features/negative-prompts.md) *for tips).*
   * Enter a **Negative Prompt** in the model's parameter panel (if available).
5. **Initiate Generation:**
   * Click the **Generate** button (✨ Sparkles icon) in the Floating Prompt Area.
6. **Review and Use Results:**
   * The **first generated image is automatically added as a new layer** at the top of your layer stack, filling the defined Generation Area.
   * Thumbnails for all generated outputs appear in the **Generation Task List**.
   * Click a different thumbnail to swap the current result layer. You can then move, scale, mask, and integrate this new layer into your broader composition.

***

While Fater's primary strength is often in editing existing real-world imagery, its Text-to-Image models offer a flexible way to introduce entirely new AI-generated content into your projects.


---

# 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:

```
GET https://fater.gitbook.io/fater-ai-docs/generating-images-with-ai/text-to-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.