Logo
LoginGet Started
Profile

bytedance / seedream-v4.5/text-to-image(deprecated)

Generate ultra-high-resolution, photorealistic images from text prompts with customizable sizes and batch generation capabilities.

0.04

Model Input

Input

The text prompt used to generate the image

Min: 1 - Max: 6

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

The size of the generated image. Width and height must be between 1920 and 4096, or total number of pixels must be between 2560*1440 and 4096*4096.

Additional Settings

Customize your input with more control.

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`.

Safety checker can only be disabled on API call

Random seed to control the stochasticity of image generation.

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

Model Output

Output

Fill in the input form and click submit to see the output
Logs (1 lines)

Model Details

Model Details

Seedream v4.5 is an advanced text-to-image generation model designed to create stunning, high-fidelity visuals from descriptive text prompts. Built to handle demanding creative workflows, this model excels at producing both photorealistic imagery and highly stylized concept art. Users can easily experiment with this model directly through the user interface, downloading results instantly, or integrate it seamlessly into applications via the API, making it highly versatile for various creative environments.

**Features** - **Ultra-High Resolution**: Natively supports large image generation (using settings like `auto_2K` and `auto_4K`), ensuring your outputs contain crisp, intricate details suitable for professional and commercial use. - **Flexible Sizing Options**: Choose from a wide range of convenient aspect ratio presets (such as `portrait_16_9`, `landscape_4_3`, or `square_hd`) or define custom exact pixel dimensions for precise control over your canvas. - **Batch Generation Capabilities**: Leverage `num_images` and `max_images` parameters to quickly generate multiple variations in a single run, allowing you to explore different concepts and compositions efficiently.

**What it’s good at** - Producing highly detailed, photorealistic scenes, character portraits, and cinematic environmental landscapes. - Generating high-resolution marketing assets, digital wallpapers, and composite background plates. - Delivering diverse artistic illustrations with rich compositions, vibrant colors, and accurate lighting.

**Tips** - Be highly specific in your text prompt regarding lighting, artistic style, camera angles, and subject matter to guide the model accurately. - Take advantage of the `auto_4K` preset when you need the absolute maximum fidelity for large-format displays or print media. - When fine-tuning a successful generation, reuse the same `seed` value to maintain structural consistency while making minor adjustments to your prompt.

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

const result = await modelrunner.subscribe("bytedance/seedream-v4.5-text-to-image", { input: { prompt: "A cinematic shot of a futuristic neon city at night, rain reflecting on the streets, cyberpunk style, highly detailed, vivid colors", image_size: "auto_4K", num_images: 1, max_images: 4, seed: 42 }, }); ```