> ## Documentation Index
> Fetch the complete documentation index at: https://docs.qingbo.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# HY Image 3.5 Preview

> Tencent image preview model for text-to-image, editing and composition using up to five references.

Tencent image preview model for text-to-image, editing and composition using up to five references.

## Quick start

```bash theme={"system"}
curl -X POST https://api.qingbo.ai/v1/tasks \
  -H "Authorization: Bearer $WAVE_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: hy-image-v3.5-preview-example-001" \
  -d '{
  "model": "hy-image-v3.5-preview",
  "action": "generate",
  "prompt": "Minimalist poster of a blue ceramic cup, cream background",
  "resolution": "2k",
  "aspect_ratio": "3:4",
  "negative_prompt": "blur, noise",
  "seed": 42
}'
```

Submission returns a task\_id. Use [`GET /v1/tasks/{task_id}`](https://docs.qingbo.dev/en/api-reference/task/status) to poll the result. Reference assets must use publicly downloadable URLs.

## Parameters

| Parameter | Type or values | Description |
| - | - | - |
| model | `hy-image-v3.5-preview` | Exact model ID. |
| `action` | generate / edit | generate creates an image without references; edit requires references. |
| `prompt` | string | Required description or editing instruction, in Chinese or English. |
| `image_urls` | string\[] | 1–5 publicly accessible references for edit. |
| `resolution` | 1k / 2k / 4k | Defaults to 1k. |
| `aspect_ratio` | string | Defaults to auto; supports 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9 and 21:9. auto uses a square for text generation and follows the reference for edits. |
| `negative_prompt` | string | Optional description of unwanted content. |
| `seed` | integer | Non-negative integer; omitted or 0 selects a random seed. |
| `n` | 1 | One image per task. |

Use resolution and aspect\_ratio to select output specifications. width, height and exact-pixel size are not supported on this route.

## Reference-image editing

```json theme={"system"}
{
  "model": "hy-image-v3.5-preview",
  "action": "edit",
  "prompt": "Change the cup to red; preserve the background and lighting.",
  "image_urls": [
    "https://cdn.example.com/source.png"
  ],
  "resolution": "1k",
  "aspect_ratio": "auto"
}
```

## Billing and results

Successful tasks use the fixed per-image rate for 1k, 2k or 4k. Generation and editing share rates, with no reference surcharge.

Read current rates in the model market or price\_config from GET /v1/models. Images are in result.images and videos in result.videos; url is an array. Failed or cancelled tasks receive a full reservation refund. Read final cost in integer quota (500,000 quota = 1 USD) and confirm billing\_status is settled.

For callbacks, waiting, idempotency and spending limits, see [Submit a task](https://docs.qingbo.dev/en/api-reference/task/submit.md)。


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.