> For the complete documentation index, see [llms.txt](https://docs.samita.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.samita.io/badges-and-labels/create-image-label-with-ai-generator.md).
# Create Image label with AI-generator
If you want to display a label or badge with specific content but haven’t decided on a design yet, the **AI Label generator** setting is here to help.
Simply enter a few short and clear requirements, and the app will automatically generate a label that matches your description.
**Step to manage:**
1. Go to our app > Click on **Badges and Labels** > **Create badge** > Select **Image** type:
2. Since you select the **Image** type, the app will immediately show the Image library setting modal shown as below > Click on the **Edit image with AI** setting:
3. Write down a **prompt** for the image you want for the label to the input field > Click **Generate**:
For example: *A premium badge with the text “BEST SELLER”, modern style, crown icons, gold accent*
4. Click on the generated label > You just finished creating a label by AI:
***
To get the best results from the AI Label & Badge generator, writing a **clear and detailed prompt** is essential. So how do you write a prompt that’s concise, easy to understand, and still detailed enough for the AI to generate exactly what you need?
Below, we’ll share a few examples to guide you through the process.
#### 1. Elements should be used in a prompt:
* **Shape** (e.g., round, square, ribbon, shield)
* **Text content** (like “SALE”, “NEW”, “50% OFF”)
* **Colors** (e.g., red, gold, blue, or specific hex codes)
* **Text style** (bold, serif, script, modern minimalist)
* **Visual style** (flat, 3D, vintage, glossy)
* **Decorative details** (borders, icons, shadows)
* **Context or purpose** (e.g., holiday sale, premium brand)
#### 2. Prompt structure:
* **Detailed version:** Describe exact specifics like shape, colors, typography, style, and decorative elements. It will give you precise control over the output.
Formula:
> Create a *\[Shape]* label displaying “*\[Text content]*”. Use *\[Color]* as the main color palette, apply *\[Text style]* typography, and design it in a *\[Style]* style. Add *\[Decorative details]* so it works well for *\[Context]*.
e.g: Create a **round** label with the text **“SALE 30% OFF”**. Use **red and white** as the primary colors and apply **bold sans-serif** typography. Style it as **modern and eye-catching**, then add **a thin white border and subtle shadow**. The design should be suitable for a **storewide promotion**.
* **Short version:** A brief description with the most important details - good for quick experimentation and creative diversity.
Formula:
> A *\[Color] \[Shape]* label with “*\[Text content]*”, *\[Style]* design, and *\[Decorative details]*.
e.g: A **red round** label with the text "**Sale 30% off**", **modern** design and **a thin white border**.
#### 3. Tips to have a good prompt:
* Use specific and descriptive wording instead of generic terms such as “beautiful label” or “good badge”
* Stick to one visual style at a time and avoid mixing incompatible styles (for example, don't add flat and 3D designs together).
* Keep your prompts short and to the point, focusing on the most important visual details.
* Clearly specify the exact text that should appear on the label or badge.
* In some cases, simpler prompts can give the AI more creative freedom and produce better results.
If the first generated result does not match what you want, refine the prompt and try again. Small changes to the shape, color, text style, or decorative details can quickly improve the output and help you get a label that fits your campaign better.
---
# 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://docs.samita.io/badges-and-labels/create-image-label-with-ai-generator.md?ask=&goal=
```
`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.