jyoung105 / sdxl-turbo

Adversarial Diffusion Distillation

Cold

Public
91 runs
L40S
GitHub
Weights
Paper
License

Run with an API

Playground API Examples README Versions

Input

prompt

string

Shift + Return to add a new line

Input prompt, text of what you want to generate.

negative_prompt

string

Shift + Return to add a new line

Input negative prompt, text of what you don't want to generate.

width

integer

(minimum: 1, maximum: 2048)

Width of the output image.

Default: 1024

height

integer

(minimum: 1, maximum: 2048)

Height of the output image.

Default: 1024

num_images

integer

(minimum: 1, maximum: 4)

Number of output images.

Default: 1

steps

integer

(minimum: 1, maximum: 50)

Number of denoising steps.

Default: 1

eta

number

(minimum: 0, maximum: 1)

Stochastic parameter to control the randomness.

Default: 0

guidance_scale

number

(minimum: 0, maximum: 20)

Scale for classifier-free guidance.

Default: 0

seed

integer

Random seed. Leave blank to randomize the seed.

clip_skip

integer

Number of the layers to skip in CLIP.

Default: 0

use_highres_fix

boolean

Whether you use highres fix or not

Default: true

Run this model in Node.js with one line of code:

npx create-replicate --model=jyoung105/sdxl-turbo

or set up a project from scratch

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run jyoung105/sdxl-turbo using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "jyoung105/sdxl-turbo:93c488b9fbd6bea622d354c8dcce2724c5f67adb92ccf909038042a21c5238a7",
  {
    input: {
      eta: 0,
      steps: 1,
      width: 1024,
      height: 1024,
      prompt: "A man with hoodie on, illustration",
      clip_skip: 0,
      num_images: 1,
      guidance_scale: 0,
      use_highres_fix: true
    }
  }
);

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import the client:

import replicate

Run jyoung105/sdxl-turbo using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "jyoung105/sdxl-turbo:93c488b9fbd6bea622d354c8dcce2724c5f67adb92ccf909038042a21c5238a7",
    input={
        "eta": 0,
        "steps": 1,
        "width": 1024,
        "height": 1024,
        "prompt": "A man with hoodie on, illustration",
        "clip_skip": 0,
        "num_images": 1,
        "guidance_scale": 0,
        "use_highres_fix": True
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Run jyoung105/sdxl-turbo using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "jyoung105/sdxl-turbo:93c488b9fbd6bea622d354c8dcce2724c5f67adb92ccf909038042a21c5238a7",
    "input": {
      "eta": 0,
      "steps": 1,
      "width": 1024,
      "height": 1024,
      "prompt": "A man with hoodie on, illustration",
      "clip_skip": 0,
      "num_images": 1,
      "guidance_scale": 0,
      "use_highres_fix": true
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

Generated in

2.7 seconds

Tweak it ShareReport

This output was created using a different version of the model, jyoung105/sdxl-turbo:521267bc.

Examples

View more examples

Run time and cost

This model runs on Nvidia L40S GPU hardware. We don't yet have enough runs of this model to provide performance information.

Readme

SDXL-Turbo

SDXL-Turbo is a fast generative text-to-image model that can synthesize photorealistic images from a text prompt in a single network evaluation.

A real-time demo is available here: http://clipdrop.co/stable-diffusion-turbo Please note: For commercial use, please refer to https://stability.ai/license.

Introduction

SDXL-Turbo is a distilled version of SDXL 1.0, trained for real-time synthesis.

SDXL-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: SDXL 1.0 Base

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: http://clipdrop.co/stable-diffusion-turbo

Citation

@misc{2311.17042,
Author = {Axel Sauer and Dominik Lorenz and Andreas Blattmann and Robin Rombach},
Title = {Adversarial Diffusion Distillation},
Year = {2023},
Eprint = {arXiv:2311.17042},
}