π Model Description
license: other license_name: stabilityai-ai-community license_link: LICENSE.md language:
- en
- stabilityai/stable-diffusion-3.5-medium
#
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."*
β TensorArt
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.
Model Features
- π Turbo Performance: Faster generation speeds, ideal for multitasking and high-demand scenarios.
- π¨ Versatile Styles: Supports a wide range of styles, from photorealistic to abstract art.
- πΌοΈ High-Resolution Outputs: Produces images with exceptional clarity and intricate details.
- βοΈ Easy to Extend: Integrated with
LoRAtechnology, making it easier for users to customize and experiment.
How to Use
- Download the Model
ckpt or LoRA files from the following links:
- (New) SD3.5M LoRA 4steps, showing the best performance and speed! (Updated on 2025/01/16)
- (New) SD3.5M LoRA 8Steps Final, fix human and facial breakdown (Updated on 2024/12/24)
- SD3.5M Checkpoint (Updated on 2024/12/16)
- Environment Setup
diffusers
- Model Loading
Contact
- Website: https://tensor.art https://tusiart.com
- Developed by: TensorArt
Example Output
Using ckptοΌimport torch
from diffusers import StableDiffusion3Pipeline
pipe = StableDiffusion3Pipeline.frompretrained("tensorart/stable-diffusion-3.5-medium-turbo", torchdtype=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.",
numinferencesteps=8,
guidance_scale=1.5,
height=1024,
width=768
).images[0]
image.save("./test4-2.webp")
Using loraοΌ
import torch
from diffusers import StableDiffusion3Pipeline
import numpy as np
from safetensors.torch import load_file
from huggingfacehub import hfhub_download
repo = "tensorart/stable-diffusion-3.5-medium-turbo"
ckpt = "lorasd3.5mturbo_8steps.safetensors"
pipe = StableDiffusion3Pipeline.frompretrained("stabilityai/stable-diffusion-3.5-medium", torchdtype=torch.float16,)
pipe = pipe.to("cuda")
pipe.loadloraweights(hfhubdownload(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.",
numinferencesteps=8,
guidance_scale=1.5,
height=1024,
width=768
).images[0]
image.save("./test1.webp")