To generate an image, you simply need a text prompt — a description of what you want to see. Our AI tools, such as Stable Diffusion and ComfyUI, interpret your prompt and turn it into a visual artwork in seconds. No technical experience is required.

The standard image size is 512×512 pixels, but you can customize the resolution depending on the model used. Some tools support higher resolutions like 768×768 or 1024×1024, and even wide-format images depending on your needs.

Note: Upscale can be 2K-4K

Yes, most AI models support batch generation. You can generate multiple variations of an image from the same prompt or different prompts at once — perfect for exploring ideas or creating content in bulk.