# HunyuanImage 3.0

> Generate high-resolution images from a text prompt with an 80-billion-parameter model built for strong prompt adherence and long, detailed descriptions.

## Overview

- **Endpoint**: `https://queue.modelrunner.run/tencent/hunyuan-image/v3/text-to-image`
- **Model ID**: `tencent/hunyuan-image/v3/text-to-image`
- **Category**: text-to-image
- **Kind**: inference
- **Tags**: hunyuan-image, hunyuan, tencent, text-to-image, image-generation

## Pricing

- **Price**: $0.1 per megapixel

## Request Lifecycle

This model runs on the ModelRunner **asynchronous queue API** — a single POST does not return the output. Every call requires an `Authorization: Key $MODEL_RUNNER_KEY` header. Run three steps:

1. **Submit** — `POST https://queue.modelrunner.run/tencent/hunyuan-image/v3/text-to-image` with a JSON body. The response carries request handles only (no output yet):

```json
{
  "status": "IN_QUEUE",
  "request_id": "<21-char id>",
  "status_url": "https://queue.modelrunner.run/tencent/hunyuan-image/v3/text-to-image/requests/<request_id>/status",
  "response_url": "https://queue.modelrunner.run/tencent/hunyuan-image/v3/text-to-image/requests/<request_id>",
  "cancel_url": "https://queue.modelrunner.run/tencent/hunyuan-image/v3/text-to-image/requests/<request_id>/cancel"
}
```

2. **Poll status** — `GET <status_url>` until `status` is `COMPLETED`. Possible values are `IN_QUEUE`, `IN_PROGRESS`, `COMPLETED`, `FAILED`, `CANCELLED`. A `FAILED` request responds with HTTP 400 and an `error` field.

3. **Read result** — `GET <response_url>`. Returns the finished request, including the generated `output`:

```json
{ "id": "<request_id>", "status": "COMPLETED", "output": ..., "input": ... }
```

The JavaScript and Python SDKs below perform steps 2–3 for you. In any language without an SDK (Swift, Go, Kotlin, etc.) you must implement the polling loop and the final result fetch yourself — see the cURL example for the full flow.

### Input Schema

- **`seed`** (`integer | null`, _optional_):
  Random seed for reproducible results. The same seed and prompt produce the same image; leave unset for a random seed.

- **`prompt`** (`string`, _required_):
  The text prompt describing the image you want to generate.

- **`image_size`** (`ImageSize | ImageSizeEnum`, _optional_):
  The size of the generated image.
  - Default: `"square_hd"`
  - Options: `"square_hd"`, `"square"`, `"portrait_4_3"`, `"portrait_16_9"`, `"landscape_4_3"`, `"landscape_16_9"`

- **`num_images`** (`integer`, _optional_):
  The number of images to generate. Each generated image is billed.
  - Default: `1`
  - Range: `1` to `4`

- **`output_format`** (`OutputFormatEnum`, _optional_):
  The format of the generated image.
  - Default: `"png"`
  - Options: `"jpeg"`, `"png"`

- **`guidance_scale`** (`number`, _optional_):
  The CFG scale. Higher values increase adherence to the prompt.
  - Default: `7.5`
  - Range: `1` to `20`

- **`negative_prompt`** (`string`, _optional_):
  Describe what you do NOT want to appear in the image.
  - Default: `""`

- **`num_inference_steps`** (`integer`, _optional_):
  The number of denoising steps to perform.
  - Default: `28`
  - Range: `1` to `50`

- **`enable_safety_checker`** (`boolean`, _optional_):
  If set to true, the safety checker will be enabled.
  - Default: `true`

- **`enable_prompt_expansion`** (`boolean`, _optional_):
  Whether to enable prompt expansion. This uses a large language model to expand the prompt with additional details while maintaining the original meaning.
  - Default: `false`

### Output Schema

_No `Output` schema properties are available._

## Default Example

**Input**

```json
{
  "prompt": "A bustling night market alley in Taipei glowing with red paper lanterns and steam rising from food stalls, vendors calling out to a stream of passersby, neon shop signs reflecting on wet pavement after rain, wide-angle street photography with a shallow depth of field",
  "image_size": "portrait_16_9",
  "num_images": 1,
  "output_format": "png",
  "guidance_scale": 7.5,
  "negative_prompt": "",
  "num_inference_steps": 28,
  "enable_safety_checker": true,
  "enable_prompt_expansion": false
}
```

**Output**

```json
[
  "https://media.modelrunner.ai/WPG1XvqmWQdXLOttJS2us.png"
]
```
## Usage Examples

### cURL

The queue API is asynchronous: submit the request, poll `status_url` until it is `COMPLETED`, then read the result from `response_url`. Requires `jq`.

```bash
# 1. Submit the request (returns request handles, not the output)
SUBMIT=$(curl --silent --request POST \
  --url https://queue.modelrunner.run/tencent/hunyuan-image/v3/text-to-image \
  --header "Authorization: Key $MODEL_RUNNER_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "prompt": "A bustling night market alley in Taipei glowing with red paper lanterns and steam rising from food stalls, vendors calling out to a stream of passersby, neon shop signs reflecting on wet pavement after rain, wide-angle street photography with a shallow depth of field",
  "image_size": "portrait_16_9",
  "num_images": 1,
  "output_format": "png",
  "guidance_scale": 7.5,
  "negative_prompt": "",
  "num_inference_steps": 28,
  "enable_safety_checker": true,
  "enable_prompt_expansion": false
}')

STATUS_URL=$(echo "$SUBMIT" | jq -r '.status_url')
RESPONSE_URL=$(echo "$SUBMIT" | jq -r '.response_url')

# 2. Poll until the request leaves the queue / in-progress state
while true; do
  STATUS=$(curl --silent --url "$STATUS_URL" \
    --header "Authorization: Key $MODEL_RUNNER_KEY" | jq -r '.status')
  echo "Status: $STATUS"
  case "$STATUS" in
    COMPLETED) break ;;
    FAILED|CANCELLED) echo "Request $STATUS"; exit 1 ;;
  esac
  sleep 1
done

# 3. Read the finished request, including the generated output
curl --silent --url "$RESPONSE_URL" \
  --header "Authorization: Key $MODEL_RUNNER_KEY"
```

### JavaScript

```javascript
import { modelrunner } from "@modelrunner/client";

const result = await modelrunner.subscribe("tencent/hunyuan-image/v3/text-to-image", {
  input: {
  "prompt": "A bustling night market alley in Taipei glowing with red paper lanterns and steam rising from food stalls, vendors calling out to a stream of passersby, neon shop signs reflecting on wet pavement after rain, wide-angle street photography with a shallow depth of field",
  "image_size": "portrait_16_9",
  "num_images": 1,
  "output_format": "png",
  "guidance_scale": 7.5,
  "negative_prompt": "",
  "num_inference_steps": 28,
  "enable_safety_checker": true,
  "enable_prompt_expansion": false
}
});

console.log(result.data);
```

### Python

```python
import asyncio
import modelrunner_ai

async def main():
    response = await modelrunner_ai.submit_async(
        "tencent/hunyuan-image/v3/text-to-image",
        arguments={
  "prompt": "A bustling night market alley in Taipei glowing with red paper lanterns and steam rising from food stalls, vendors calling out to a stream of passersby, neon shop signs reflecting on wet pavement after rain, wide-angle street photography with a shallow depth of field",
  "image_size": "portrait_16_9",
  "num_images": 1,
  "output_format": "png",
  "guidance_scale": 7.5,
  "negative_prompt": "",
  "num_inference_steps": 28,
  "enable_safety_checker": true,
  "enable_prompt_expansion": false
}
    )
    result = await response.get()
    print(result["output"])

asyncio.run(main())
```

## Additional Resources

- [Playground](https://modelrunner.ai/models/tencent/hunyuan-image/v3/text-to-image)
- [OpenAPI Schema](https://modelrunner.ai/models/tencent/hunyuan-image/v3/text-to-image/openapi.json)
- [LLM Instructions](https://modelrunner.ai/models/tencent/hunyuan-image/v3/text-to-image/llms.txt)