Adversarial Diffusion Distillation

Key Takeaways:

  • SDXL Turbo achieves state-of-the-art performance with a new distillation technology, enabling single-step image generation with unprecedented quality, reducing the required step count from 50 to just one.

  • Download the model weights and code on Hugging Face, currently being released under a non-commercial research license that permits personal, non-commercial use.

  • Test SDXL Turbo on Stability AI’s image editing platform Clipdrop, with a beta demonstration of the real-time text-to-image generation capabilities.

SDXL Turbo Adversarial Diffusion Distillation

We introduce Adversarial Diffusion Distillation (ADD), a novel training approach that efficiently samples large-scale foundational image diffusion models in just 1–4 steps while maintaining high image quality. We use score distillation to leverage large-scale off-the-shelf image diffusion models as a teacher signal in combination with an adversarial loss to ensure high image fidelity even in the low-step regime of one or two sampling steps.

Read the paper

Previous
Previous

Scalable High-Resolution Pixel-Space Image Synthesis with Hourglass Diffusion Transformers

Next
Next

Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets