Stable Video Diffusion

Stable Diffusion is Stability AI’s professional image generation model family built for creating high-quality visuals from text prompts. The models support a wide range of styles, including photography, 3D, painting, illustration, line art, and other creative formats. Stable Diffusion is designed for strong prompt adherence, diverse visual outputs, and flexible use across professional, creative, and technical workflows. Users can deploy the models through self-hosted licensing, the Stability AI API, cloud partner ecosystems, or web-based creative applications. Stability AI also provides image editing tools for inpainting, outpainting, object removal, upscaling, sketch control, structure control, and style transformation. Built for creators, developers, brands, and enterprises, Stable Diffusion helps teams generate, edit, customize, and scale visual content production.

Stable Diffusion 3.5 is Stability AI’s image generation and editing model suite, built for professional-grade creative production across self-hosted deployment, API integration, cloud partner ecosystems, and web-based creation. Its flagship Stable Diffusion 3.5 family is described as Stability AI’s most powerful image model yet, designed to generate a wide range of image styles, including 3D, photography, painting, line art, and more, with market-leading prompt adherence, diverse outputs, and flexible options for different use cases. Stable Diffusion 3.5 Large is the most powerful model in the Stable Diffusion family, with superior quality and prompt adherence for professional use cases at 1 megapixel resolution. Stable Diffusion 3.5 Large Turbo is designed to run faster than Large while generating high-quality images with exceptional prompt adherence in just four steps. Stable Diffusion 3.5 Medium balances quality and customization with improved architecture and training methods.