# Wan | 2.5 | Preview | Text to Image

Wan 2.5 Preview Text to Image generates high-quality, realistic images from text prompts.

## API Information

- **Model Slug:** wan-2-5-preview-text-to-image
- **Branded URL:** https://www.eachlabs.ai/alibaba/wan-2-5/wan-2-5-preview-text-to-image
- **Provider:** Alibaba
- **Category:** Text to Image
- **Output Type:** image
- **Status:** active
- **Version:** 0.0.1
- **Base Cost:** Per image pricing: $0.05/image
- **Estimated Processing Time:** 30 seconds
- **Last Updated:** 2026-04-02
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/wan-2-5-preview-text-to-image

## Pricing

- **Charge Type:** dynamic
- **Pricing Details:** Per image pricing: $0.05/image

### Pricing Rules

| Condition | Pricing |
| --- | --- |
| Rule 1 | Per image pricing: $0.05/image |

## Input Schema

| Parameter | Type | Required | Default | Constraints | Description |
|-----------|------|----------|---------|-------------|-------------|
| prompt | string | Yes | - | - | The prompt for image generation. Supports Chinese and English, max 2000 characters. |
| negative_prompt | string | No | - | - | Negative prompt to describe content to avoid. Max 500 characters. |
| num_images | integer | No | 1 | 1–4 | Number of images to generate. Values from 1 to 4. |
| image_size | string | No | square_hd | square_hd,square,portrait_4_3,portrait_16_9,landscape_4_3,landscape_16_9 | The size of the generated image. Can use preset names like 'square', 'landscape_16_9', etc., or specific dimensions. Total pixels must be between 768×768 and 1440×1440, with aspect ratio between [1:4, 4:1]. |
| enable_prompt_expansion | boolean | No | true | - | Whether to enable prompt rewriting using LLM. Improves results for short prompts but increases processing time. |
| seed | integer | No | - | - | Random seed for reproducibility. If None, a random seed is chosen. |

## Example Request

```bash
curl -X POST https://api.eachlabs.ai/v1/prediction/ \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "wan-2-5-preview-text-to-image",
  "input": {
    "prompt": "A grand gothic library bathed in moonlight, towering bookshelves curving into a perfect archway. In the center, a massive oak table holds scattered scrolls, ink quills, and a shimmering crystal orb. Light streams diagonally through a tall stained-glass window, casting colorful patterns on the marble floor. The scholar, in a dark velvet cloak embroidered with silver patterns, is frozen mid-gesture as he turns a page, his face illuminated by the glow of the orb. Photorealistic composition, dramatic perspective, ultra-detailed textures, oil-painting aesthetic with chiaroscuro lighting."
  }
}'
```

## Output Schema

Response returned by `GET /v1/prediction/{id}` when the job completes:

```json
{
  "status": "success",
  "predictionID": "string",
  "output": "string (URL of generated image)",
  "metrics": {
    "predict_time": "number (seconds)"
  }
}
```

## Polling

```bash
curl https://api.eachlabs.ai/v1/prediction/{PREDICTION_ID} \
  -H "Authorization: Bearer YOUR_API_KEY"
```

| Status | Meaning |
|--------|---------|
| `processing` | Still running — poll again |
| `success` | Done — read `output` |
| `error` | Failed — read `message` / `details` |

## Webhook (alternative to polling)

Pass `"webhook_url": "https://your.host/path"` in the create request. Eachlabs POSTs this payload when the job ends:

```json
{
  "exec_id": "prediction-uuid",
  "status": "succeeded",
  "output": "https://...",
  "error": ""
}
```

`status` is `"succeeded"` or `"failed"`. `exec_id` equals the `predictionID` from create. Return 2xx within 30 seconds.

## Errors

Error body: `{ "status": "error", "message": "...", "details": "..." }`

| Code | Meaning |
|------|---------|
| `400` | Invalid input |
| `401` | Missing / invalid `Authorization` bearer token |
| `404` | Unknown model or prediction id |
| `429` | Rate limit — 100 creates / min, 10 concurrent per key |
| `5xx` | Retry with backoff |

## Overview

**wan-2-5-preview-text-to-image — Text-to-Image AI Model**

Developed by Alibaba as part of the **wan-2.5** family, **wan-2-5-preview-text-to-image** transforms detailed text prompts into high-quality, realistic images, enabling creators and developers to generate photorealistic visuals without traditional design tools. This **Alibaba text-to-image** model stands out with its preview capabilities from the advanced Wan series, delivering sharp details and accurate compositions ideal for **text-to-image AI model** applications in marketing and prototyping. Users searching for "Alibaba text-to-image API" will find it excels in rendering complex scenes with consistent lighting and subject fidelity, part of Alibaba's ecosystem that powers everything from static images to dynamic videos.

## Usage Notes

- API Base URL: `https://api.eachlabs.ai/v1`
- Authentication: send `Authorization: Bearer YOUR_API_KEY`. Generate a key from the Eachlabs dashboard at https://www.eachlabs.ai/dashboard/api-keys.
- File-typed parameters (`*_url`, `image_url`, `video_url`, `audio_url`, etc.) accept publicly-reachable HTTPS URLs only. Upload your asset first (GCS / S3 / your CDN) and pass the resulting URL. Data-URIs and localhost URLs are rejected.
- For structured parameters (arrays / objects) send real JSON values, not stringified payloads.
- Monetary values are reported in USD; per-token / per-megapixel rates may be billed in micro-cents internally.
- Prefer `webhook_url` over polling for long-running predictions — see the Webhook Callback section.