# Hunyuan Image v3 | Text to Image

Hunyuan Image v3 generates realistic, high-quality images from text prompts with vivid detail and style flexibility.

## API Information

- **Model Slug:** hunyuan-image-v3-text-to-image
- **Branded URL:** https://www.eachlabs.ai/tencent/hunyuan-image/hunyuan-image-v3-text-to-image
- **Provider:** Tencent
- **Category:** Text to Image
- **Output Type:** image
- **Status:** active
- **Version:** 0.0.1
- **Base Cost:** $0.3 per image (input.num_images, default 1)
- **Estimated Processing Time:** 70 seconds
- **Last Updated:** 2026-06-10
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/hunyuan-image-v3-text-to-image

## Pricing

- **Charge Type:** dynamic
- **Estimated Price (default example):** $0.3000
- **Pricing Details:** $0.3 per image (input.num_images, default 1)

### Pricing Rules

| Condition | Pricing |
| --- | --- |
| Rule 1 | $0.3 per image (input.num_images, default 1) |

## Input Schema

| Parameter | Type | Required | Default | Constraints | Description |
|-----------|------|----------|---------|-------------|-------------|
| prompt | string | Yes | - | - | The text prompt for image-to-image. |
| negative_prompt | string | No | - | - | The negative prompt to guide the image generation away from certain concepts. |
| image_size | string | No | square_hd | square_hd,square,portrait_4_3,portrait_16_9,landscape_4_3,landscape_16_9 | The desired size of the generated image. |
| num_images | integer | No | 1 | 1–4 | The number of images to generate. |
| num_inference_steps | integer | No | 28 | 1–50 | Number of denoising steps. |
| guidance_scale | number | No | 3.5 | 1–20 | Controls how much the model adheres to the prompt. Higher values mean stricter adherence. |
| seed | integer | No | - | - | Random seed for reproducible results. If None, a random seed is used. |
| enable_safety_checker | boolean | No | true | - | If set to true, the safety checker will be enabled. |
| output_format | string | No | png | jpeg,png | The format of the generated image. |

## 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": "hunyuan-image-v3-text-to-image",
  "input": {
    "prompt": "A lone astronaut stands on the surface of a mysterious alien desert, carefully lifting off one glove as shimmering rings of a colossal gas giant fill the sky. The alien landscape glows with bioluminescent plants scattered across jagged rocks, casting surreal blue and green light on the astronaut’s suit. The horizon is painted with vibrant auroras, and the astronaut’s reflective visor captures the glowing planet above. Ultra realistic, cinematic detail, otherworldly yet breathtaking atmosphere."
  }
}'
```

## 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

**hunyuan-image-v3-text-to-image — Text-to-Image AI Model**

Developed by Tencent as part of the **hunyuan-image** family, **hunyuan-image-v3-text-to-image** is a cutting-edge text-to-image AI model that generates photorealistic, high-fidelity images from complex prompts using an 80B parameter Mixture-of-Experts (MoE) architecture. This unified multimodal design excels at prompt adherence and intelligent reasoning, automatically elaborating sparse inputs into coherent, detailed visuals—rivaling top closed-source models like DALL-E 3. Ideal for developers seeking a **Tencent text-to-image** solution or creators needing precise **text-to-image AI model** outputs, it powers applications from e-commerce visuals to digital art with superior bilingual English-Chinese alignment.

## 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.