Announcing Stable Diffusion 3.5 Large & Turbo by stability.ai

fal is partnering with stability.ai to offer the new Stable Diffusion 3.5 Large & Turbo models.

To play around with the new models now, check out the demo page here on fal.

Where the models shine

Stable Diffusion 3.5 stands out as one of the most customizable and accessible image models, excelling in key areas such as:

• Customizability: Easily fine-tune the model for specific creative needs or develop applications with tailored workflows.
• Efficient Performance: Optimized for standard consumer hardware, with models like Stable Diffusion 3.5 Medium and Large Turbo running smoothly without heavy resource demands.
• Diverse Outputs: Generates a wide variety of images reflecting different styles without complex prompting.

What is being released?

Stable Diffusion 3.5 introduces two new models:

• Large: Featuring 8 billion parameters, this model offers superior image quality and prompt accuracy, making it ideal for professional applications at 1-megapixel resolution.
• Turbo: A distilled version of the Large model, Turbo delivers high-quality images in just 4 steps, offering faster performance while maintaining exceptional prompt adherence. Perfect for users seeking speed without compromising quality.

There is also a third variant, Medium that will be released on October 29th, which is a 2.5 billion parameters, with improved MMDiT-X architecture and training methods.

Stay tuned for new model releases and join our Discord here: discord.gg/fal-ai