# HunyuanImage 3.0 Instruct

> Edit and transform an existing image from a written instruction and up to 3 reference images, with an instruction-tuned checkpoint built for following long, complex edit directions.

## Overview

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

## Pricing

- **Price**: $0.09 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/instruct/edit` 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/instruct/edit/requests/<request_id>/status",
  "response_url": "https://queue.modelrunner.run/tencent/hunyuan-image/v3/instruct/edit/requests/<request_id>",
  "cancel_url": "https://queue.modelrunner.run/tencent/hunyuan-image/v3/instruct/edit/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 inputs produce the same edit; leave unset for a random seed.

- **`prompt`** (`string`, _required_):
  The instruction describing how to edit the reference image(s).

- **`image_size`** (`ImageSize | ImageSizeEnum`, _optional_):
  The size of the edited image. Use a preset, an explicit width/height object, or 'auto' to let the model choose from the input image.
  - Default: `"auto"`
  - Options: `"auto"`, `"square_hd"`, `"square"`, `"portrait_4_3"`, `"portrait_16_9"`, `"landscape_4_3"`, `"landscape_16_9"`

- **`image_urls`** (`array<string>`, _required_):
  The URLs of the images to use as a reference for the edit. A maximum of 3 images are supported.

- **`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: `3.5`
  - Range: `"-inf"` to `20`

- **`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. Enabled by default; disable it to have your exact wording honored.
  - Default: `true`

### Output Schema

_No `Output` schema properties are available._

## Default Example

**Input**

```json
{
  "prompt": "Transform this summer lakeside cabin into a cozy winter scene at dusk: snow blanketing the roof and the ground, warm golden light glowing from the windows, and a soft pink-and-purple twilight sky reflected in the half-frozen lake.",
  "image_size": "auto",
  "image_urls": [
    "https://media.modelrunner.ai/kOrNCD7gvHLVyYdDEEvZP.png"
  ],
  "num_images": 1,
  "output_format": "png",
  "guidance_scale": 3.5,
  "enable_safety_checker": true,
  "enable_prompt_expansion": true
}
```

**Output**

```json
[
  "https://media.modelrunner.ai/I1jrC51DOzfRSTxFhItEz.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/instruct/edit \
  --header "Authorization: Key $MODEL_RUNNER_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "prompt": "Transform this summer lakeside cabin into a cozy winter scene at dusk: snow blanketing the roof and the ground, warm golden light glowing from the windows, and a soft pink-and-purple twilight sky reflected in the half-frozen lake.",
  "image_size": "auto",
  "image_urls": [
    "https://media.modelrunner.ai/kOrNCD7gvHLVyYdDEEvZP.png"
  ],
  "num_images": 1,
  "output_format": "png",
  "guidance_scale": 3.5,
  "enable_safety_checker": true,
  "enable_prompt_expansion": true
}')

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/instruct/edit", {
  input: {
  "prompt": "Transform this summer lakeside cabin into a cozy winter scene at dusk: snow blanketing the roof and the ground, warm golden light glowing from the windows, and a soft pink-and-purple twilight sky reflected in the half-frozen lake.",
  "image_size": "auto",
  "image_urls": [
    "https://media.modelrunner.ai/kOrNCD7gvHLVyYdDEEvZP.png"
  ],
  "num_images": 1,
  "output_format": "png",
  "guidance_scale": 3.5,
  "enable_safety_checker": true,
  "enable_prompt_expansion": true
}
});

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

### Python

```python
import asyncio
import modelrunner_ai

async def main():
    response = await modelrunner_ai.submit_async(
        "tencent/hunyuan-image/v3/instruct/edit",
        arguments={
  "prompt": "Transform this summer lakeside cabin into a cozy winter scene at dusk: snow blanketing the roof and the ground, warm golden light glowing from the windows, and a soft pink-and-purple twilight sky reflected in the half-frozen lake.",
  "image_size": "auto",
  "image_urls": [
    "https://media.modelrunner.ai/kOrNCD7gvHLVyYdDEEvZP.png"
  ],
  "num_images": 1,
  "output_format": "png",
  "guidance_scale": 3.5,
  "enable_safety_checker": true,
  "enable_prompt_expansion": true
}
    )
    result = await response.get()
    print(result["output"])

asyncio.run(main())
```

## Additional Resources

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