# MOSS Image

> MOSS-Image-SFT is a text-to-image model specializing in Chinese and English text rendering and structured layout control for precise text placement and object arrangement.


## Overview

- **Endpoint**: `https://fal.run/fal-ai/moss-image`
- **Model ID**: `fal-ai/moss-image`
- **Category**: text-to-image
- **Kind**: inference


## Pricing

Your request will cost **$0.05** per megapixel

For more details, see [fal.ai pricing](https://fal.ai/pricing).

## API Information

This model can be used via our HTTP API or more conveniently via our client libraries.
See the input and output schema below, as well as the usage examples.


### Input Schema

The API accepts the following input parameters:


- **`prompt`** (`string`, _required_):
  Text prompt for image generation. Supports natural language, tag sequences, and JSON layouts.
  - Examples: "A wide view of a refrigerator beside a kitchen counter with a fruit bowl. A small sticky note on the refrigerator door is handwritten in Chinese:\n\"记得买牛奶和鸡蛋！\n牛奶两盒，鸡蛋一打。\""

- **`negative_prompt`** (`string`, _optional_):
  Negative prompt. When empty, guidance uses transformer layer skipping for the negative branch. Default value: `""`
  - Default: `""`

- **`enable_prompt_expansion`** (`boolean`, _optional_):
  Plan a structured layout from your prompt before generation. Preserves requested visible text and uses the selected image dimensions. If enhancement is unavailable, uses the original prompt. Default value: `true`
  - Default: `true`

- **`image_size`** (`ImageSize | Enum`, _optional_):
  Output image size. Width and height are rounded to multiples of 16 between 512 and 2048 pixels. Default value: `square_hd`
  - Default: `"square_hd"`
  - One of: ImageSize | Enum

- **`num_inference_steps`** (`integer`, _optional_):
  Number of denoising steps. Default value: `50`
  - Default: `50`
  - Range: `1` to `100`

- **`guidance_scale`** (`float`, _optional_):
  Classifier-free guidance scale. Default value: `3`
  - Default: `3`
  - Range: `0` to `10`

- **`seed`** (`integer`, _optional_):
  Random seed for reproducible generation.

- **`num_images`** (`integer`, _optional_):
  Number of images to generate. Default value: `1`
  - Default: `1`
  - Range: `1` to `4`

- **`enable_safety_checker`** (`boolean`, _optional_):
  Enable output content moderation. Disabling it requires account authorization; unauthorized requests are always checked, and images flagged as unsafe are returned as black images. Default value: `true`
  - Default: `true`

- **`output_format`** (`OutputFormatEnum`, _optional_):
  Output image format. Default value: `"jpeg"`
  - Default: `"jpeg"`
  - Options: `"jpeg"`, `"png"`, `"webp"`

- **`sync_mode`** (`boolean`, _optional_):
  Return images as data URIs instead of storing them in request history.
  - Default: `false`



**Required Parameters Example**:

```json
{
  "prompt": "A wide view of a refrigerator beside a kitchen counter with a fruit bowl. A small sticky note on the refrigerator door is handwritten in Chinese:\n\"记得买牛奶和鸡蛋！\n牛奶两盒，鸡蛋一打。\""
}
```

**Full Example**:

```json
{
  "prompt": "A wide view of a refrigerator beside a kitchen counter with a fruit bowl. A small sticky note on the refrigerator door is handwritten in Chinese:\n\"记得买牛奶和鸡蛋！\n牛奶两盒，鸡蛋一打。\"",
  "enable_prompt_expansion": true,
  "image_size": "square_hd",
  "num_inference_steps": 50,
  "guidance_scale": 3,
  "num_images": 1,
  "enable_safety_checker": true,
  "output_format": "jpeg"
}
```


### Output Schema

The API returns the following output format:

- **`images`** (`list<Image>`, _required_):
  Generated images.
  - Array of Image

- **`seed`** (`integer`, _required_):
  Seed used for the first generated image.

- **`has_nsfw_concepts`** (`list<boolean>`, _required_):
  Whether each generated image contains unsafe content.
  - Array of boolean

- **`actual_prompt`** (`string`, _optional_):
  Expanded prompt used for generation, when enhancement succeeds.



**Example Response**:

```json
{
  "images": [
    {
      "url": "",
      "content_type": "image/png",
      "file_name": "z9RV14K95DvU.png",
      "file_size": 4404019,
      "width": 1024,
      "height": 1024
    }
  ]
}
```


## Usage Examples

### cURL

```bash
curl --request POST \
  --url https://fal.run/fal-ai/moss-image \
  --header "Authorization: Key $FAL_KEY" \
  --header "Content-Type: application/json" \
  --data '{
     "prompt": "A wide view of a refrigerator beside a kitchen counter with a fruit bowl. A small sticky note on the refrigerator door is handwritten in Chinese:\n\"记得买牛奶和鸡蛋！\n牛奶两盒，鸡蛋一打。\""
   }'
```

### Python

Ensure you have the Python client installed:

```bash
pip install fal-client
```

Then use the API client to make requests:

```python
import fal_client

def on_queue_update(update):
    if isinstance(update, fal_client.InProgress):
        for log in update.logs:
           print(log["message"])

result = fal_client.subscribe(
    "fal-ai/moss-image",
    arguments={
        "prompt": "A wide view of a refrigerator beside a kitchen counter with a fruit bowl. A small sticky note on the refrigerator door is handwritten in Chinese:
    \"记得买牛奶和鸡蛋！
    牛奶两盒，鸡蛋一打。\""
    },
    with_logs=True,
    on_queue_update=on_queue_update,
)
print(result)
```

### JavaScript

Ensure you have the JavaScript client installed:

```bash
npm install --save @fal-ai/client
```

Then use the API client to make requests:

```javascript
import { fal } from "@fal-ai/client";

const result = await fal.subscribe("fal-ai/moss-image", {
  input: {
    prompt: "A wide view of a refrigerator beside a kitchen counter with a fruit bowl. A small sticky note on the refrigerator door is handwritten in Chinese:
  \"记得买牛奶和鸡蛋！
  牛奶两盒，鸡蛋一打。\""
  },
  logs: true,
  onQueueUpdate: (update) => {
    if (update.status === "IN_PROGRESS") {
      update.logs.map((log) => log.message).forEach(console.log);
    }
  },
});
console.log(result.data);
console.log(result.requestId);
```


## Additional Resources

### Documentation

- [Model Playground](https://fal.ai/models/fal-ai/moss-image)
- [API Documentation](https://fal.ai/models/fal-ai/moss-image/api)
- [OpenAPI Schema](https://fal.ai/api/openapi/queue/openapi.json?endpoint_id=fal-ai/moss-image)

### fal.ai Platform

- [Platform Documentation](https://fal.ai/docs/documentation)
- [Python Client](https://fal.ai/docs/api-reference/client-libraries/python)
- [JavaScript Client](https://fal.ai/docs/api-reference/client-libraries/javascript)

### Other agent-readable surfaces

This file covers one model. To find anything else:

- [Platform overview](https://fal.ai/llms.txt): Entry points and representative endpoint IDs
- [Documentation index](https://fal.ai/docs/llms.txt): Every documentation page
- [Full documentation text](https://fal.ai/docs/llms-full.txt): The whole documentation inlined
- Any other model: `https://fal.ai/models/<endpoint-id>/llms.txt`