Image Models

  • Stable Diffusion XL

    Get involved with the fastest growing open software project. Download and join other developers in creating incredible applications with Stable Diffusion XL as a foundation model.

    Read the Paper
    Download Code

  • Stable Diffusion XL Turbo

    Discover the groundbreaking SDXL Turbo, the latest advancement from our research team. Built on the robust foundation of Stable Diffusion XL, this ultra-fast model transforms the way you interact with technology.

    Read the Paper
    Download Code

  • Japanese Stable Diffusion XL

    A text-to-image model that emphasizes Japanese input to better understand Japanese culture. It comprehends Japanese expressions better than traditional English models, allowing for high-quality image generation that feels native.

    Download Code

  • Stable Diffusion 3.5 Large

    At 8 billion parameters, with superior quality and prompt adherence, this base model is the most powerful in the Stable Diffusion family. This model is ideal for professional use cases at 1 megapixel resolution.

    Get Started with API
    Read More about SD3.5

  • Stable Diffusion 3.5 Large Turbo

    A distilled version of Stable Diffusion 3.5 Large generates high-quality images with exceptional prompt adherence in just 4 steps, making it considerably faster than Stable Diffusion 3.5 Large.

    Get Started with API
    Read More about SD3.5

  • Stable Diffusion 3.5 Medium

    At 2.5 billion parameters, with improved MMDiT-X architecture and training methods, this model is designed to run “out of the box” on consumer hardware, striking a balance between quality and ease of customization. It is capable of generating images ranging between 0.25 and 2 megapixel resolution. 

  • Stable Diffusion 3 Large

    The largest base model in the SD3 series delivers outstanding quality, with a balanced trade-off between output speed and image excellence. Ideal for content creation in media, entertainment, and retail industries.

    Read the Paper

  • Stable Diffusion 3 Large Turbo

    SD3 Large Turbo, with 8 billion parameters, offers top-tier image quality and faster inference. Ideal for industries like media and retail that need high-quality content at speed.

    Read the Paper

  • Stable Diffusion 3 Medium

    SD3 Medium is a two billion parameters great at photorealism and clear text generation. The small size of this model makes it perfect for running on consumer PCs and laptops as well as enterprise-tier GPUs. Available under a community license.

    Download Code