Stable Diffusion

What this tool can do

Stable Diffusion is an open-source generative AI model for creating images from text prompts, sketches and reference material. It enables artists, designers and creators to generate high-quality visuals, explore styles and transform ideas into detailed artwork. The model supports flexible workflows including image-to-image transformations, inpainting and customization through fine-tuning or community model variants.

Typical Use Cases

Text-to-image generation
Stable Diffusion creates detailed images, concepts and visual scenes from text prompts.

Image-to-image transformation
Users modify existing images, change styles or rework compositions using reference inputs.

Inpainting and outpainting
The model fills missing areas, removes objects or extends scenes while maintaining visual consistency.

Artistic exploration
Designers explore artistic styles, moods and creative directions powered by generative models.

Concept art and ideation
Teams and creators use Stable Diffusion to develop visual drafts and moodboards for projects in film, games and design.

Custom model training
Users fine-tune models or use community checkpoints to achieve specific artistic styles or domains.

Stable Diffusion is free of charge for researchers, developers, small businesses, and creators with less than $1M in annual revenue.