# HiDream I1 Dev

> Generate high-quality images from a text prompt with a strong quality-to-speed balance, using the mid-tier 28-step version of HiDream's 17B open image model.

## Overview

- **Endpoint**: `https://queue.modelrunner.run/hidream/i1-dev`
- **Model ID**: `hidream/i1-dev`
- **Category**: text-to-image
- **Kind**: inference
- **Tags**: hidream, hidream-i1, text-to-image, image-generation

## Pricing

- **Price**: $0.03 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/hidream/i1-dev` with a JSON body holding the input fields at the top level. The body may also include a reserved top-level `metadata` object — a flat string map (max 16 keys, key ≤64 / value ≤512 chars) stored on the request for your own tagging. It is never sent to the model; filter your request history with `GET https://queue.modelrunner.run/requests?metadata=<url-encoded JSON>` (exact key=value matches, AND-ed). The response carries request handles only (no output yet):

```json
{
  "status": "IN_QUEUE",
  "request_id": "<21-char id>",
  "status_url": "https://queue.modelrunner.run/hidream/i1-dev/requests/<request_id>/status",
  "response_url": "https://queue.modelrunner.run/hidream/i1-dev/requests/<request_id>",
  "cancel_url": "https://queue.modelrunner.run/hidream/i1-dev/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_):
  The same seed and the same prompt given to the same version of the model will output the same image every time.

- **`prompt`** (`string`, _required_):
  The prompt to generate an image from.

- **`image_size`** (`ImageSize | ImageSizeEnum`, _optional_):
  The size of the generated image. Use a preset string (e.g. 'landscape_16_9') or a custom {width, height} object.
  - 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: `"jpeg"`
  - Options: `"jpeg"`, `"png"`

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

- **`num_inference_steps`** (`integer`, _optional_):
  The number of inference steps to perform. Defaults to 28 for a balanced quality/speed result; more steps can improve detail at the cost of speed.
  - Default: `28`
  - Range: `1` to `50`

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

### Output Schema

_No `Output` schema properties are available._

## Default Example

**Input**

```json
{
  "prompt": "A bustling neon-lit night market in Kyoto during light autumn rain, reflections of paper lanterns and food stall signage shimmering on wet cobblestones, cinematic street photography",
  "image_size": "portrait_4_3",
  "num_images": 1,
  "output_format": "jpeg",
  "negative_prompt": "",
  "num_inference_steps": 28,
  "enable_safety_checker": true
}
```

**Output**

```json
[
  "https://media.modelrunner.ai/aKFNkvNu8Y28FrZO8PtSI.jpeg"
]
```
## 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/hidream/i1-dev \
  --header "Authorization: Key $MODEL_RUNNER_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "prompt": "A bustling neon-lit night market in Kyoto during light autumn rain, reflections of paper lanterns and food stall signage shimmering on wet cobblestones, cinematic street photography",
  "image_size": "portrait_4_3",
  "num_images": 1,
  "output_format": "jpeg",
  "negative_prompt": "",
  "num_inference_steps": 28,
  "enable_safety_checker": 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("hidream/i1-dev", {
  input: {
  "prompt": "A bustling neon-lit night market in Kyoto during light autumn rain, reflections of paper lanterns and food stall signage shimmering on wet cobblestones, cinematic street photography",
  "image_size": "portrait_4_3",
  "num_images": 1,
  "output_format": "jpeg",
  "negative_prompt": "",
  "num_inference_steps": 28,
  "enable_safety_checker": true
}
});

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

### Python

```python
import asyncio
import modelrunner_ai

async def main():
    response = await modelrunner_ai.submit_async(
        "hidream/i1-dev",
        arguments={
  "prompt": "A bustling neon-lit night market in Kyoto during light autumn rain, reflections of paper lanterns and food stall signage shimmering on wet cobblestones, cinematic street photography",
  "image_size": "portrait_4_3",
  "num_images": 1,
  "output_format": "jpeg",
  "negative_prompt": "",
  "num_inference_steps": 28,
  "enable_safety_checker": true
}
    )
    result = await response.get()
    print(result["output"])

asyncio.run(main())
```

## Additional Resources

- [Playground](https://modelrunner.ai/models/hidream/i1-dev)
- [OpenAPI Schema](https://modelrunner.ai/models/hidream/i1-dev/openapi.json)
- [LLM Instructions](https://modelrunner.ai/models/hidream/i1-dev/llms.txt)