# Bytedance | Seedream | v5 | Lite | Text to Image

ByteDance Seedream v5 Lite turns text prompts into 4K images using real-time web search and Chain of Thought reasoning making it the first Seedream model to think before it generates. Ideal for marketing visuals, multilingual posters, and brand assets that need accurate, detail-rich results at speed.

## API Information

- **Model Slug:** bytedance-seedream-v5-lite-text-to-image
- **Branded URL:** https://www.eachlabs.ai/bytedance/seedream-v5/bytedance-seedream-v5-lite-text-to-image
- **Provider:** ByteDance
- **Category:** Text to Image
- **Output Type:** array
- **Status:** active
- **Base Cost:** $0.035 per image
- **Estimated Processing Time:** 30 seconds
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/bytedance-seedream-v5-lite-text-to-image

## Pricing

- **Charge Type:** dynamic
- **Estimate:** $0.035 per image
- **Pricing Details:** default: $0.035

## Input Schema

| Parameter | Type | Required | Default | Constraints | Description |
|-----------|------|----------|---------|-------------|-------------|
| prompt | string | Yes | - | - | Text description of the image to generate. Recommended: under 600 English words. |
| resolution | string | No | 2K | 2K, 3K | Output resolution. '2K' (~2048px) or '3K' (~3072px). Both support all aspect ratios with specific pixel dimensions. |
| aspect_ratio | string | No | - | auto, 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 21:9 | Aspect ratio of the output image. Applies to both 2K and 3K resolutions with resolution-specific pixel dimensions. |
| num_images | integer | No | - | 1–6 | Number of images to generate (1–15). When > 1, batch generation is enabled automatically and the count is injected into the prompt. |
| output_format | string | No | jpeg | jpeg, png | File format of the output image. Default: jpeg. |

## 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-v5-lite-text-to-image",
  "input": {
    "prompt": "high-fashion editorial portrait, close-up beauty shot of a model with an intense, magnetic gaze, wearing an architectural statement headpiece, bold contrasting color palette with deep jewel tones, crisp razor-sharp focus on the eyes, creamy shallow depth of field, dramatic sculpted studio lighting with high contrast and soft falloff, ultra-detailed skin texture, refined makeup, minimal clean backdrop, luxury magazine cover aesthetic, shot on medium format, cinematic color grading, ultra high resolution."
  }
}'
```

## 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

The **Bytedance | Seedream | v5 | Lite | Text to Image** model transforms precise text prompts into high-quality images with exceptional realism and detail. Developed by ByteDance as part of the Seedream family, this lightweight version excels in generating photorealistic visuals, particularly in handling complex lighting, materials, and real-time information integration. Its primary differentiator is superior physics-based rendering, such as accurate light refraction and global illumination, making it ideal for creators needing cinematic-quality outputs from simple text descriptions.

Built on the advanced Seedream 5.0 architecture, the Lite variant prioritizes speed and efficiency without sacrificing visual fidelity. Whether for concept art, marketing visuals, or rapid prototyping, **Bytedance | Seedream | v5 | Lite | Text to Image** delivers clear, precise results that match described visions quickly. Available via the **Bytedance | Seedream | v5 | Lite | Text to Image API** on platforms like each::labs, it empowers users to iterate fast in **Bytedance text-to-image** workflows.

## 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.