# Text to Image

### 🧠 What Is Text-to-Image?

Text-to-Image lets you generate images from a text prompt right in your browser. Use it to quickly explore ideas, create reference images, and generate inputs you can feed into Image-to-3D.

***

### 🚀 How It Works

{% stepper %}
{% step %}

#### Write a prompt

* Keep it short and specific.
* Examples:
  * "a stylized toy car, studio lighting, white background"
  * "an iron chain link, close-up product photo"
  * "a medieval shield, worn metal, white background"
    {% endstep %}

{% step %}

#### Pick a Style (optional)

* If you want a consistent look, choose a style preset.
* If you leave it on **No style preset**, the result is driven by your prompt.
  {% endstep %}

{% step %}

#### Toggle T-Pose (optional)

* Use **T-Pose** when you want character references in a neutral pose (useful for consistency and later 3D work).
  {% endstep %}

{% step %}

#### Generate

* Click **Generate** and review the result.
* Iterate by changing one thing at a time (material, style, camera angle).

{% hint style="info" %}
Pro Tip: If you want to use the image for Image-to-3D, aim for one subject, a clear silhouette, and a simple background.
{% endhint %}
{% endstep %}
{% endstepper %}

***

### ✍️ Prompting Tips

* ✅ One subject per prompt
* ✅ Add style cues: “realistic”, “stylized”, “low poly”, “clay”, “anime”
* ✅ Add material cues: “wood”, “metal”, “plastic”, “stone”, “glass”
* ✅ Add camera cues: “front view”, “3/4 view”, “close-up”, “studio photo”
* ✅ Add background cues: “plain background”, “white backdrop”, “no clutter”
* ❌ Avoid full scenes (too many objects competing)
* ❌ Avoid vague prompts like “cool fantasy thing”

{% hint style="info" %}
Pro Tip: Make 3 to 5 variations of the same prompt and only change one word each time.
{% endhint %}

***

### ✅ Best Use Cases

* Concept and mood exploration (fast variations)
* Reference images for modeling and sculpting
* Generating inputs for Image-to-3D (when you do not have a photo)
* Quick art direction alignment (pick a look, then refine)

***

### 🔁 Combine Workflows

Use Text to Image alongside other Sloyd tools:

* **Text to 3D**: best for fast ideation without references
* **Image to 3D**: best when you only have one image
* **Multi-Image to 3D:** best when you have multiple views of the same object
* **Template Editor**: best for clean, editable, game-ready assets

***

### 🌍 Who’s It For?

* **Game Devs:** Fast concepting and reference generation for props and set dressing.
* **3D Artists:** Quick references for modeling, sculpting, and texture direction.
* **Concept Artists:** Rapid exploration of variations and visual themes.
* **Students/Educators:** Visualize ideas fast without advanced software.

***

### 🧪 Status

{% hint style="warning" %}
Text-to-Image is under active development. Quality will continue to improve over time, and feedback helps guide what to prioritize next.
{% endhint %}

***

### 🔗 Try It Now

Head to [app.sloyd.ai](https://app.sloyd.ai/) → Choose **Text to Image** in the **Create** section.


---

# 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://sloyd.gitbook.io/documentation/creating-image/text-to-image.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.