Z-Image Omni (Omni-Base) is an AI image model that supports text-to-image and image-to-image editing in one unified system. Built on a 6B-parameter Single-stream Diffusion Transformer, it delivers high-quality results in both English and Chinese. Try it free on MaxStudio.
Start by typing a text description to create a new image, or upload an image if you want to edit an existing one. Use simple words to explain what you want, and the AI will understand better.
Click the Generate button. The AI will create a new image or edit your uploaded image based on your instructions.
Once the image is ready, preview the result. If you are happy with it, download the image and use it for your project.
The model supports both Text-to-Image (T2I) generation and Image-to-Image (I2I) editing in one unified system. Users can generate new images from text or modify existing images without changing models or workflows.
Built on a scalable Single-stream Diffusion Transformer (S3-DiT), the model processes all data in one flow. This helps the AI understand instructions better and produce more accurate and consistent images.
With 6 billion parameters, Z-Image Omni Base has strong learning capacity, allowing it to generate detailed, high-quality images and handle complex prompts effectively.
Z-Image Omni Base supports both English and Chinese, allowing users to write prompts in either language while maintaining accurate and high-quality image results.