models/Shuttle 3 Diffusion - fp8

Shuttle 3 Diffusion - fp8

9/17/2025

5:16:43 PM

Related Keywords & Tags

checkpoint,complex prompts,flux.1,flux.1 s,fp8,image quality,photorealistic,resource efficiency,shuttle 3 diffusion,shuttleai,style,text-to-image ai model,typography

Portrait of a female robot with porcelain white skin and intricate golden radial markings forming organic shapes on her face, featuring symmetrical facial details, striking blue-yellow eyes, and a glass body with golden accents under volumetric lighting.

An elderly man wearing a VR headset, standing confused with hands raised in the middle of a busy crowded urban street with bright neon signs and dramatic lighting.

A chubby old clown with a blue horn, frowning and holding a whisky bottle, sits on an ornate chair on a wooden stage illuminated by yellow spotlights and surrounded by red curtains.

Recommended Hires (High-Resolution) Parameters

steps

10 - null

Tips

Using more than 10 steps enters 'refiner mode' which enhances image details without changing the overall composition.

Creator Sponsors

You can try out the model through a website at https://chat.shuttleai.com/images

Use Shuttle 3 Diffusion via API through ShuttleAI and see the Documentation.

Shuttle 3 Diffusion

Shuttle 3 Diffusion is a text-to-image AI model designed to create detailed and diverse images from textual prompts. It offers enhanced performance in image quality, typography, understanding complex prompts, and resource efficiency.

You can try out the model through a website at https://chat.shuttleai.com/images

Using the model via API

You can use Shuttle 3 Diffusion via API through ShuttleAI

- ShuttleAI

- Documentation

Shuttle 3 Diffusion uses Flux.1 Schnell as its base. It can produce images similar to Flux Pro in just 4 steps, and it is licensed under Apache 2. The model was partially de-distilled during training. When used beyond 10 steps, it enters "refiner mode," enhancing image details without altering the composition. We overcame the limitations of the Schnell-series models by employing a special training method, resulting in improved details and colors.