text-to-image

Name: Seedream V5 Text to Image
Author: bytedance

Generate high-quality, intelligent images from text prompts using the fast Lite version of Seedream 5.0.

0.035

Input

Prompt

The text prompt used to generate the image

Image Size

Width

Height

The size of the generated image. Total pixels must be between 2560x1440 and 3072x3072. In case the image size does not fall within these parameters, the image size will be adjusted to by scaling.

Num Images

Min: 1 - Max: 6

Number of separate model generations to be run with the prompt.

Additional Settings

Customize your input with more control.

Max Images

Min: 1 - Max: 6

If set to a number greater than one, enables multi-image generation. The model will potentially return up to `max_images` images every generation, and in total, `num_images` generations will be carried out. In total, the number of images generated will be between `num_images` and `max_images*num_images`.

Enable Safety Checker

Safety checker can only be disabled on API call

You need to be logged in to run this model and view results.

Output

{
  "error": "",
  "inferenceTime": 35667,
  "output": [
    "https://media.modelrunner.ai/gS7ft2chgfBClU2M3n7Te.png"
  ],
  "input": {
    "prompt": "A bustling 1920s jazz club in New Orleans, dimly lit with warm amber lamps and thick atmospheric haze. A talented saxophonist in a sharp pinstripe suit is playing passionately on stage. In the foreground resting on a polished mahogany bar, a vintage wooden sign with elegant gold-leaf lettering reads \"Blue Note\". Cinematic lighting, high fidelity, realistic DSLR photograph, shallow depth of field.",
    "image_size": "landscape_16_9",
    "max_images": 1,
    "num_images": 1,
    "enable_safety_checker": true
  },
  "logs": "Generated 1 output(s)"
}

Generated in 35.667 seconds

Logs (1 lines)

Examples

Model Details

Seedream 5.0 Lite Text-to-Image is a fast, highly capable model designed to generate stunning visuals directly from text descriptions. Built for speed without sacrificing fidelity, it excels at translating complex, detailed prompts into vivid, realistic, and stylized outputs.

Whether you are creating hyper-realistic photography, imaginative concept art, or engaging digital assets, Seedream delivers high-quality results efficiently. The model natively handles complex prompt structures, including integrated text rendering and intricate subject-environment interactions.

Features - Fast generation — optimized Lite architecture ensures rapid image creation - High-fidelity outputs — capable of rendering intricate details, accurate anatomy, and realistic textures - Flexible sizing — supports auto-scaling and various high-resolution output formats (up to 3K resolution) - Multi-image support — generate several conceptual variations in a single run

What it’s good at - Generating realistic photography, DSLR-style shots, and cinematic imagery - Creating expressive anthropomorphic characters and unique stylized scenes - Handling short text inclusions seamlessly within the generated image composition - Producing highly detailed backgrounds, landscapes, and diverse environments

Tips - Be as specific as possible: include explicit details about lighting, camera style, and mood (e.g., "Realistic DSLR photograph", "golden hour lighting") - If you want specific text rendered in your image, place the exact phrase in quotes within your prompt - Use preset size values like `auto_2K` or `auto_3K` to easily scale your outputs to high resolutions directly from the UI

To run via ModelRunner JavaScript client: ```javascript import { modelrunner } from "@modelrunner/client";

const result = await modelrunner.subscribe("bytedance/seedream-v5/text-to-image", { input: { prompt: "Realistic DSLR photograph of anthropomorphic Pekingese dog enjoying a bowl of ramen on the Great Wall of China with the words \"Seedream 5.0 Lite\" visible at the top.", image_size: "auto_2K", num_images: 1, max_images: 1, enable_safety_checker: true }, });

console.log(result.images); ```

bytedance / seedream-v5/text-to-image

Model Input

Input

Additional Settings

Model Output

Output

Model Example Requests

Examples

Model Details

Model Details