# Bytedance | Seedream | v4.5 | Text to Image

ByteDance Seedream v4.5 is a high-resolution text-to-image model delivering cinematic-quality visuals with industry-leading typography rendering, strong multi-part prompt adherence, and native 4K output with measurable improvements in layout precision, aesthetic coherence, and detail fidelity over Seedream v4.0. It supports English and Chinese text rendering and up to 14 reference images for consistent batch generation.

## API Information

- **Model Slug:** bytedance-seedream-v4-5-text-to-image
- **Branded URL:** https://www.eachlabs.ai/bytedance/seedream-v4-5/bytedance-seedream-v4-5-text-to-image
- **Provider:** ByteDance
- **Category:** Text to Image
- **Output Type:** array
- **Status:** active
- **Base Cost:** $0.04 per image
- **Estimated Processing Time:** 10 seconds
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/bytedance-seedream-v4-5-text-to-image

## Pricing

- **Charge Type:** dynamic
- **Estimate:** $0.04 per image
- **Pricing Details:** default: $0.04

## Input Schema

| Parameter | Type | Required | Default | Constraints | Description |
|-----------|------|----------|---------|-------------|-------------|
| prompt | string | Yes | - | - | Text description of the image to generate. Recommended: under 600 English words. |
| image_size | string | No | square_hd | square_hd, square, auto_2K, auto_4K, portrait_4_3, landscape_4_3, portrait_16_9, landscape_16_9 | Output image dimensions. square_hd/square: 2048x2048. auto_2K: automatic 2K resolution. auto_4K: automatic 4K resolution. portrait_4_3: 1728x2304. landscape_4_3: 2304x1728. portrait_16_9: 1600x2848. landscape_16_9: 2848x1600. |
| num_images | integer | No | - | 1–15 | Number of images to generate (1–15). When > 1, batch generation is enabled automatically and the count is injected into the prompt. |
| enable_safety_checker | boolean | No | - | - | Compatibility field. Accepted but not used by BytePlus API. |
| sync_mode | boolean | No | - | - | Compatibility field. Accepted but not used. |
| max_images | integer | No | - | - | Compatibility field. Accepted but not used. |
| output_format | string | No | - | - | Compatibility field. Accepted but not used — v4.5 does not support output_format. |
| aspect_ratio | string | No | - | - | Compatibility field. Accepted but not used. |
| image_seed | integer | No | - | - | Compatibility field. Accepted but not used. |
| seed | integer | No | - | - | Seed for reproducibility. Accepted but not used by v4.5. |
| safety_tolerance | string | No | - | - | Compatibility field. Accepted but not used. |

## 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": "bytedance-seedream-v4-5-text-to-image",
  "input": {
    "prompt": "A quiet urban street on a bright, dry day. Sunlight casts clean, sharp shadows across the pavement. Small shops and cafés line the street, with a modern rectangular sign reading “EACHLABS” hanging above one storefront. The air is clear, the sidewalk is dry, and a gentle breeze rustles a few scattered posters on a nearby wall. Cars are parked along the curb, and a cyclist passes in the background. Ultra-realistic details, crisp lighting, natural colors, and a calm daytime atmosphere."
  }
}'
```

## Output Schema

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

```json
{
  "status": "success",
  "predictionID": "string",
  "output": "array",
  "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

**bytedance-seedream-v4.5-text-to-image — Text-to-Image AI Model**

Developed by Bytedance as part of the **seedream-v4.5** family, **bytedance-seedream-v4.5-text-to-image** revolutionizes image generation by unifying high-fidelity text-to-image creation with advanced editing in a single multimodal architecture, enabling seamless workflows for designers and developers seeking **Bytedance text-to-image** solutions. This model stands out with native 4K resolution up to 2048×2048 and designer-level text rendering, producing crisp typography even in small fonts that most text-to-image AI models struggle to achieve. For users searching for a **text-to-image AI model** with multi-image reference support, **bytedance-seedream-v4.5-text-to-image** delivers professional results 10x faster than prior versions, perfect for rapid prototyping in e-commerce visuals or branding assets.

## 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.