# 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](https://fater.gitbook.io/fater-ai-docs/core-concepts-ai-and-editor-features/text-prompts "mention") *&* [negative-prompts](https://fater.gitbook.io/fater-ai-docs/core-concepts-ai-and-editor-features/negative-prompts "mention") *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.