Project Overview

TensorArt Stable Diffusion 3.5 Medium Turbo (SD3.5M Turbo) is a high-performance text-to-image model distilled from StabilityAI's stable-diffusion-3.5-medium. This model emphasizes stability and efficiency, making it suitable for a wide range of art styles and creative expression scenarios.

https://huggingface.co/tensorart/stable-diffusion-3.5-medium-turbo

Our LoRA implementation is also available on TensorArt.

项目概览

TensorArt Stable Diffusion 3.5 Medium Turbo (SD3.5M Turbo)是一个从SAI的SD3.5M版本蒸馏的高性能文生图模型。它兼顾稳定性和生图效率，能够胜任各种艺术风格和创意领域的高效生图。

https://huggingface.co/tensorart/stable-diffusion-3.5-medium-turbo

也可在吐司上访问我们的LoRA版本

Model Features

- 🚀 Turbo Performance: Up to 8x Faster generation speeds, ideal for multitasking and high-demand scenarios.

- 🎨 Versatile Styles: Supports a wide range of styles, from photorealistic to abstract art.

- 🖼️ High-Resolution Outputs: Produces images with exceptional clarity and intricate details up to 1440*1440 resolution

- ⚙️ Easy to Extend: Integrated with `LoRA` technology, making it easier for users to customize and experiment.

模型特性

- 🚀 极致性能：相比SD3.5M，最高可达8倍生图速度，适合多任务高并发的生图场景。

- 🎨 多样风格: 支持广泛的艺术风格，包括真实摄影和抽象艺术

- 🖼️ 高清生成: 最高可支持1440*1440分辨率的生成，追求极致的清晰度和细节表达

- ⚙️ 轻松扩展: 使用LoRA版本可以为任何SD3.5M的基座模型加速

Recommended Parameters / 推荐参数

Sampler: Euler

Scheduler: Beta

Steps: 8

CFG Scale: 1.0~1.5 Higher cfg still works well

stable-diffusion-3.5-medium-turbo - gguf-Q4_K_M-8steps