A fast generative text-to-image model that can synthesize photorealistic images from a text prompt in a single network evaluation
Request the model checkpoint from Stability AI
SDXL-Turbo, a distilled variant of SDXL 1.0, empowers real-time image synthesis via Adversarial Diffusion Distillation (ADD). ADD enables high-fidelity sampling from large-scale image diffusion models in 1-4 steps. Employing score distillation for leveraging teacher signals from pre-trained models, ADD seamlessly integrates an adversarial loss, guaranteeing image fidelity even at minimal sampling steps (1-2).
Developed by: Stability AI Funded by: Stability AI Model type: Generative image-to-video model Finetuned from model: SDXL 1.0 Base
By using this software or model, you are agreeing to the terms and conditions of the license, acceptable use policy and Stability’s privacy policy.
Architecture Type: Transformer and Convolutional Neural Network (CNN) Network Architecture: UNet + attention blocks Model Version: SDXL Turbo
Input Format: Text, Image (Optional) Input Parameters: inference_steps, seed, prompt_strength (for an image input)
Output Format: Red, Green, Blue (RGB) Image Output Parameters: seed
Supported Hardware Platform(s): Hopper, Ampere/Turing Supported Operating System(s): Linux
Engine: Triton Test Hardware: Other
You can request the model checkpoint from Stability AI