Lesson Content

The image generation interface.

The Image Generation interface is Leonardo's primary generation workspace: a prompt field for the text description, a model selector for choosing which generation model to use, parameter controls for image count, dimensions, and guidance scale, and generation controls (generate button, negative prompt field). Understanding each control before generating avoids default behaviors that may not match the intended output.

Selecting a model and entering a prompt.

Leonardo AI offers multiple generation models with different visual strengths – selecting an appropriate model before entering a prompt is important, as the same prompt produces different results across models. (Model selection is covered in detail in Course 3.) For first generation, a general-purpose model like Leonardo Diffusion XL or a similar versatile option is appropriate. Enter a descriptive text prompt covering subject, setting, style, and mood.

Setting generation parameters.

Key first-generation parameters: number of images (typically 2-4 for evaluation), dimensions (match the intended use case – square, portrait, or landscape ratio), and guidance scale (how closely the generation follows the prompt – higher values for more prompt adherence). Leave advanced settings at default for initial generation.

Reviewing and saving.

Generated images appear below the prompt field after processing. Review each result, click to view at full size, and use the download button to save selected images. The Personal Feed retains all past generations for access in later sessions.