Overview

SD Turbo is a distilled version of Stable Diffusion designed specifically for real-time image synthesis. Unlike standard diffusion models that require multiple sampling steps, SD Turbo utilizes Adversarial Diffusion Distillation (ADD) to generate high-quality images in just one to four steps. For developers, this means a drastic reduction in inference latency and compute costs, making it ideal for interactive applications, live prototyping, and edge deployment. It integrates seamlessly into existing Stable Diffusion pipelines, allowing you to swap the checkpoint for near-instantaneous text-to-image generation without needing a massive GPU cluster to maintain a responsive user experience.

Highlights

Real-time generation in one to four sampling steps
Significantly lower inference latency and compute overhead
Compatible with standard Stable Diffusion integration pipelines
Optimized for interactive apps and live prototyping
Open-source deployment under the Apache-2.0 license

Usage

Install

# Install Hugging Face transformers
pip install transformers torch

SDK Usage

# Load model with transformers
from transformers import AutoModel, AutoTokenizer

model = AutoModel.from_pretrained("stabilityai/sd-turbo")
tokenizer = AutoTokenizer.from_pretrained("stabilityai/sd-turbo")

Hugging Face Download

We recommend downloading the model via the Hugging Face CLI or Hub SDK.

Guidance：Before downloading, install huggingface_hub with:

Guidance

pip install -U huggingface_hub

CLI Download

Download the full repository

huggingface-cli download stabilityai/sd-turbo

Download a single file to a local folder (e.g. config.json into ./dir)

huggingface-cli download stabilityai/sd-turbo config.json --local-dir ./dir

See the official docs for more CLI options

SDK Download

# 模型下载
from huggingface_hub import snapshot_download
model_dir = snapshot_download('stabilityai/sd-turbo')

Git Download

Make sure git-lfs is installed first

Git Download

git lfs install
git clone https://huggingface.co/stabilityai/sd-turbo

To skip LFS large-file downloads, use:

Skip LFS

GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/stabilityai/sd-turbo

Model files are hosted on the Hugging Face Hub — download directly via HF CLI / SDK / Git, not through this site.

PyTorch / Transformers Usage

Install Transformers

pip install -U transformers torch

Load the model and run inference

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained('stabilityai/sd-turbo')
tokenizer = AutoTokenizer.from_pretrained('stabilityai/sd-turbo')

Model Download

We recommend downloading the model via the ModelScope CLI or SDK.

Guidance：Before downloading, install ModelScope with:

Guidance

pip install modelscope

CLI Download

Download the full repository

modelscope download --model stabilityai/sd-turbo

Download a single file to a local folder (e.g. README.md into ./dir)

modelscope download --model stabilityai/sd-turbo README.md --local_dir ./dir

See the docs for more CLI options

SDK Download

# 模型下载
from modelscope import snapshot_download
model_dir = snapshot_download('stabilityai/sd-turbo')

Git Download

Make sure git-lfs is installed first

Git Download

git lfs install
git clone https://www.modelscope.cn/stabilityai/sd-turbo.git

To skip LFS large-file downloads, use:

Skip LFS

GIT_LFS_SKIP_SMUDGE=1 git clone https://www.modelscope.cn/stabilityai/sd-turbo.git

ModelScope 模型页直接下载模型文件；无需将模型文件放在本站服务器。

Notebook Quickstart

Install the ModelScope library

pip install "modelscope[audio,cv,nlp,multi-modal,science]" -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html

Load the model and run inference

from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks

p = pipeline('text-generation', 'stabilityai/sd-turbo')

Full Documentation

来源: HuggingFace

---
pipeline_tag: text-to-image
inference: false
---

SD-Turbo Model Card

!row01
SD-Turbo is a fast generative text-to-image model that can synthesize photorealistic images from a text prompt in a single network evaluation.
We release SD-Turbo as a research artifact, and to study small, distilled text-to-image models. For increased quality and prompt understanding,
we recommend SDXL-Turbo.

Please note: For commercial use, please refer to https://stability.ai/license.

Model Details

Model Description

SD-Turbo is a distilled version of Stable Diffusion 2.1, trained for real-time synthesis. SD-Turbo is based on a novel training method called Adversarial Diffusion Distillation (ADD) (see the technical report), which allows sampling large-scale foundational image diffusion models in 1 to 4 steps at high image quality. This approach uses score distillation to leverage large-scale off-the-shelf image diffusion models as a teacher signal and combines this with an adversarial loss to ensure high image fidelity even in the low-step regime of one or two sampling steps.

Developed by: Stability AI

Funded by: Stability AI

Model type: Generative text-to-image model

Finetuned from model: Stable Diffusion 2.1

Model Sources

For research purposes, we recommend our generative-models Github repository (https://github.com/Stability-AI/generative-models),
which implements the most popular diffusion frameworks (both training and inference).

Repository: https://github.com/Stability-AI/generative-models

Paper: https://stability.ai/research/adversarial-diffusion-distillation

Demo [for the bigger SDXL-Turbo]: http://clipdrop.co/stable-diffusion-turbo

Evaluation

!comparison1 !comparison2 The charts above evaluate user preference for SD-Turbo over other single- and multi-step models. SD-Turbo evaluated at a single step is preferred by human voters in terms of image quality and prompt following over LCM-Lora XL and LCM-Lora 1.5.

Note: For increased quality, we recommend the bigger version SDXL-Turbo.
For details on the user study, we refer to the research paper.

Uses

Direct Use

The model is intended for both non-commercial and commercial usage. Possible research areas and tasks include

Research on generative models.

Research on real-time applications of generative models.

Research on the impact of real-time generative models.

Safe deployment of models which have the potential to generate harmful content.

Probing and understanding the limitations and biases of generative models.

Generation of artworks and use in design and other artistic processes.

Applications in educational or creative tools.

For commercial use, please refer to https://stability.ai/membership.

Excluded uses are described below.

Diffusers

code

pip install diffusers transformers accelerate --upgrade

Text-to-image:

SD-Turbo does not make use of guidance_scale or negative_prompt, we disable it with guidance_scale=0.0.
Preferably, the model generates images of size 512x512 but higher image sizes work as well.
A single step is enough to generate high quality images.

py

from diffusers import AutoPipelineForText2Image
import torch
pipe = AutoPipelineForText2Image.from_pretrained("stabilityai/sd-turbo", torch_dtype=torch.float16, variant="fp16")
pipe.to("cuda")
prompt = "A cinematic shot of a baby racoon wearing an intricate italian priest robe."
image = pipe(prompt=prompt, num_inference_steps=1, guidance_scale=0.0).images[0]

Image-to-image:

When using SD-Turbo for image-to-image generation, make sure that num_inference_steps * strength is larger or equal
to 1. The image-to-image pipeline will run for int(num_inference_steps * strength) steps, *e.g.* 0.5 * 2.0 = 1 step in our example
below.

py

from diffusers import AutoPipelineForImage2Image
from diffusers.utils import load_image
import torch
pipe = AutoPipelineForImage2Image.from_pretrained("stabilityai/sd-turbo", torch_dtype=torch.float16, variant="fp16")
pipe.to("cuda")
init_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png").resize((512, 512))
prompt = "cat wizard, gandalf, lord of the rings, detailed, fantasy, cute, adorable, Pixar, Disney, 8k"
image = pipe(prompt, image=init_image, num_inference_steps=2, strength=0.5, guidance_scale=0.0).images[0]

Out-of-Scope Use

The model was not trained to be factual or true representations of people or events,
and therefore using the model to generate such content is out-of-scope for the abilities of this model.
The model should not be used in any way that violates Stability AI's Acceptable Use Policy.

Limitations and Bias

Limitations

The quality and prompt alignment is lower than that of SDXL-Turbo.

The generated images are of a fixed resolution (512x512 pix), and the model does not achieve perfect photorealism.

The model cannot render legible text.

Faces and people in general may not be generated properly.

The autoencoding part of the model is lossy.

Recommendations

The model is intended for both non-commercial and commercial usage.

How to Get Started with the Model

Check out https://github.com/Stability-AI/generative-models

sd turbo

Overview

Highlights

Usage

Hugging Face Download

CLI Download

SDK Download

Git Download

PyTorch / Transformers Usage

Model Download

CLI Download

SDK Download

Git Download

Notebook Quickstart

Full Documentation

SD-Turbo Model Card

Model Details

Model Description

Model Sources

Evaluation

Uses

Direct Use

Diffusers

Out-of-Scope Use

Limitations and Bias

Limitations

Recommendations

How to Get Started with the Model