Logo
LoginGet Started
Profile

tongyi-mai / z-image/base

Generate high-quality, stylistically diverse images with precise prompt adherence using the Z-Image foundation model.

0.01 per megapixel of image

Model Input

Input

The prompt to generate an image from.

The size of the generated image.

Additional Settings

Customize your input with more control.

Min: 1 - Max: 50

The number of inference steps to perform.

The same seed and the same prompt given to the same version of the model will output the same image every time.

Min: 1 - Max: 4

The number of images to generate.

Safety checker can only be disabled on API call

The format of the generated image.

The acceleration level to use.

Min: 1 - Max: 20

The guidance scale to use for the image generation.

The negative prompt to use for the image generation.

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

Model Output

Output

preview
Generated in 11.76 seconds
Logs (1 lines)

Model Example Requests

Examples

hKWr3Ci3RMU1rPnClwY5JrdjDcdyezDVN18XDOow7X

Model Details

Model Details

Z-Image Base is a foundational text-to-image generation model designed to deliver high-quality visuals with robust diversity and broad stylistic coverage. As the core of the Z-Image family, this model is engineered to interpret prompts with high precision, making it an ideal tool for creators looking to translate detailed textual descriptions into coherent and aesthetically pleasing images. Whether you are generating concept art, marketing assets, or illustrative content, Z-Image Base aims to respect the nuances of your input while maintaining structural consistency.

Key capabilities of this model include handling complex scene descriptions and offering a wide range of artistic styles. Users can interact with the model directly through the application UI to generate images and download the results immediately. The model supports various configuration options to fine-tune the output, allowing for control over aspect ratios, inference steps, and guidance scales.

**Input Configurations** To get the best results, users can adjust several parameters: * **Prompt**: The primary text description (e.g., "Grandmother knitting by a window"). * **Image Size**: Select from standard aspect ratios like `landscape_4_3`, `square`, or `portrait_16_9` to fit your composition needs. * **Inference Steps**: Control the quality-speed trade-off. The default is 28 steps, but it ranges from 1 to 50. * **Guidance Scale**: Determines how strictly the model follows the prompt. The default is 4. * **Negative Prompt**: Specify elements to exclude from the image.

**Example Usage** To run this model using the ModelRunner JavaScript client, utilize the following code snippet. This example demonstrates a standard generation request with specific sizing and quality settings.

```javascript import { modelrunner } from "@modelrunner/client";

const result = await modelrunner.subscribe("tongyi-mai/z-image/base", { input: { prompt: "Grandmother knitting by a window, an empty chair by her", image_size: "landscape_4_3", num_inference_steps: 28, num_images: 1, enable_safety_checker: true, output_format: "png", acceleration: "regular", guidance_scale: 4, negative_prompt: "blurry, low quality, distorted" } });

console.log(result); ```