# Qwen Image · Image to Image

Edit and enhance images with Qwen Image · Image to Image from fal through one Spiral API key. It runs in the background and returns images. Pay as you go, with no subscription.

- Provider: fal
- Category: Image
- Runs: In the background
- Returns: image
- Tool id: `fal` / `fal-ai/qwen-image/image-to-image`
- Page: https://spiral.ai/tools/fal/fal-ai/qwen-image/image-to-image

## Pricing

Up to $0.026 per run at the default inputs. $0.026 per unit of `num_images`.

## Limits

- Longest queue wait: 1 hour
- Run deadline: 30 minutes
- Longest run, end to end: 225 minutes
- Largest inline input: 1 MB
- Largest input file: 2 GB
- Largest output: 5 GB

## Input

| Field | Kind | Allowed | Default | Description |
| --- | --- | --- | --- | --- |
| `prompt` (required) | text |  | — | The prompt to generate the image with |
| `image_size` | JSON |  | — | The size of the generated image. By default, we will use the provided image for determining the image_size. |
| `num_inference_steps` | number (whole) | 2 to 250 | 30 | The number of inference steps to perform. |
| `seed` | number (whole) |  | — | The same seed and the same prompt given to the same version of the model will output the same image every time. |
| `guidance_scale` | number | 0 to 20 | 2.5 | The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you. |
| `num_images` | number (whole) | 1 to 4 | 1 | The number of images to generate. |
| `output_format` | one of | jpeg, png | png | The format of the generated image. |
| `negative_prompt` | text |  |  | The negative prompt for the generation |
| `acceleration` | one of | none, regular, high | none | Acceleration level for image generation. Options: 'none', 'regular', 'high'. Higher acceleration increases speed. 'regular' balances speed and quality. 'high' is recommended for images without text. |
| `loras` | JSON |  | [] | The LoRAs to use for the image generation. You can use up to 3 LoRAs and they will be merged together to generate the final image. |
| `use_turbo` | true or false |  | false | Enable turbo mode for faster generation with high quality. When enabled, uses optimized settings (10 steps, CFG=1.2). |
| `image_url` (required) | URL or file |  | — | The reference image to guide the generation. |
| `strength` | number | 0 to 1 | 0.6 | Denoising strength. 1.0 = fully remake; 0.0 = preserve original. |

## Example

```bash
curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "fal",
    "model": "fal-ai/qwen-image/image-to-image",
    "input": {
      "prompt": "Mount Fuji with purple japanese wisteria in the foreground, clear sky, peaceful spring day, soft natural light, landscape, painted with oil brush on a wood…",
      "image_url": "https://v3.fal.media/files/rabbit/KoIbq6nhDBDPxDQrivW-m.png"
    }
  }'
```

Try it in the Playground: https://spiral.ai/start?provider=fal&model=fal-ai%2Fqwen-image%2Fimage-to-image

## Common questions

### Qwen Image · Image to Image

**How much does Qwen Image · Image to Image cost?**

Up to $0.026 per run at the default inputs. $0.026 per unit of `num_images`. You pay as you go from one Spiral balance, with no subscription, and a failed run is not charged.

**How do I use Qwen Image · Image to Image through an API?**

Send `POST /v1/runs` with `"provider": "fal"`, `"model": "fal-ai/qwen-image/image-to-image"` and the input fields on this page, using one Spiral API key. It runs in the background: poll the run, or name a webhook to be told when it finishes.

**Do I need an account with fal to use Qwen Image · Image to Image?**

No. Spiral runs it on its own fal account and charges your Spiral balance.

**Can my AI agent use Qwen Image · Image to Image?**

Yes. Agents find and run it through Spiral's MCP server, CLI or agent skill, with the same API key.

