Stable Diffusion 3.5 Medium Turbo

🚀 TensorArt Stable Diffusion 3.5 Medium Turbo (SD3.5M Turbo)

TensorArt Stable Diffusion 3.5 Medium Turbo (SD3.5M Turbo) 是一款高性能的文生图模型，它从 StabilityAI 的 stable-diffusion-3.5-medium 模型蒸馏而来。该模型注重稳定性和效率，适用于各种艺术风格和创意表达场景。

**TensorArt Stable Diffusion 3.5 Medium Turbo (SD3.5M Turbo)** *"All that has passed is but a prologue, what you hold in your heart will one day echo back."*

— TensorArt

🚀 快速开始

下载模型

从以下链接下载模型的 ckpt 或 LoRA 文件的最新版本：

• (New) SD3.5M LoRA 4steps，展现最佳性能和速度！(2025/01/16 更新)
• (New) SD3.5M LoRA 8Steps Final，修复人物和面部问题 (2024/12/24 更新)
• SD3.5M 检查点 (2024/12/16 更新)

环境搭建

确保你的环境满足以下要求：

• Python 3.8+
• PyTorch 2.0+
• 所需库，如 diffusers

模型加载

按照仓库中提供的详细说明加载和使用模型。你也可以通过我们提供的工作流在 comfyui 中使用它们：4steps-nonstop comfyui_ckpt，comfyui_lora。

✨ 主要特性

• 🚀 Turbo 性能：更快的生成速度，适用于多任务和高需求场景。
• 🎨 风格多样：支持从写实到抽象艺术等广泛的风格。
• 🖼️ 高分辨率输出：生成的图像具有出色的清晰度和复杂的细节。
• ⚙️ 易于扩展：集成了 LoRA 技术，方便用户进行自定义和实验。

💻 使用示例

基础用法

使用 ckpt

import torch
from diffusers import StableDiffusion3Pipeline

pipe = StableDiffusion3Pipeline.from_pretrained("tensorart/stable-diffusion-3.5-medium-turbo", torch_dtype=torch.float16,)
                                                   
pipe = pipe.to("cuda")


image = pipe(
    "A beautiful bald girl with silver and white futuristic metal face jewelry, her full body made of intricately carved liquid glass in the style of Tadashi, the complexity master of cyberpunk, in the style of James Jean and Peter Mohrbacher. This concept design is trending on Artstation, with sharp focus, studio-quality photography, and highly detailed, intricate details.",
    num_inference_steps=8,
    guidance_scale=1.5,
    height=1024,
    width=768 
).images[0]

image.save("./test4-2.webp")

使用 lora

import torch
from diffusers import StableDiffusion3Pipeline
import numpy as np
from safetensors.torch import load_file
from huggingface_hub import hf_hub_download

repo = "tensorart/stable-diffusion-3.5-medium-turbo"
ckpt = "lora_sd3.5m_turbo_8steps.safetensors"

pipe = StableDiffusion3Pipeline.from_pretrained("stabilityai/stable-diffusion-3.5-medium", torch_dtype=torch.float16,)
                                                   
pipe = pipe.to("cuda")

pipe.load_lora_weights(hf_hub_download(repo, ckpt))
pipe.fuse_lora()


pipe = pipe.to("cuda")

image = pipe(
    "A beautiful bald girl with silver and white futuristic metal face jewelry, her full body made of intricately carved liquid glass in the style of Tadashi, the complexity master of cyberpunk, in the style of James Jean and Peter Mohrbacher. This concept design is trending on Artstation, with sharp focus, studio-quality photography, and highly detailed, intricate details.",
    num_inference_steps=8,
    guidance_scale=1.5,
    height=1024,
    width=768 
).images[0]
image.save("./test1.webp")

📄 许可证

• 许可证类型：other
• 许可证名称：stabilityai-ai-community
• 许可证链接：LICENSE.md

📚 详细文档

联系信息

• 网站：https://tensor.art https://tusiart.com
• 开发者：TensorArt