Self-corrected flow distillation for consistent one-step and few-step text-to-image generation

Q Dao, H Phung, T Dao, D Metaxas, A Tran - arxiv preprint arxiv …, 2024 - arxiv.org
Flow matching has emerged as a promising framework for training generative models,
demonstrating impressive empirical performance while offering relative ease of training …

FADA: Fast Diffusion Avatar Synthesis with Mixed-Supervised Multi-CFG Distillation

T Zhong, C Liang, J Jiang, G Lin, J Yang… - arxiv preprint arxiv …, 2024 - arxiv.org
Diffusion-based audio-driven talking avatar methods have recently gained attention for their
high-fidelity, vivid, and expressive results. However, their slow inference speed limits …

Nitrofusion: High-fidelity single-step diffusion through dynamic adversarial training

DY Chen, H Bandyopadhyay, K Zou… - arxiv preprint arxiv …, 2024 - arxiv.org
We introduce NitroFusion, a fundamentally different approach to single-step diffusion that
achieves high-quality generation through a dynamic adversarial framework. While one-step …

SnapGen-V: Generating a Five-Second Video within Five Seconds on a Mobile Device

Y Wu, Z Zhang, Y Li, Y Xu, A Kag, Y Sui… - arxiv preprint arxiv …, 2024 - arxiv.org
We have witnessed the unprecedented success of diffusion-based video generation over
the past year. Recently proposed models from the community have wielded the power to …

SNOOPI: Supercharged One-step Diffusion Distillation with Proper Guidance

V Nguyen, AA Nguyen, T Dao, K Nguyen… - arxiv preprint arxiv …, 2024 - arxiv.org
Recent approaches have yielded promising results in distilling multi-step text-to-image
diffusion models into one-step ones. The state-of-the-art efficient distillation technique, ie …

Human Body Restoration with One-Step Diffusion Model and A New Benchmark

J Gong, J Wang, Z Chen, X Liu, H Gu, Y Zhang… - arxiv preprint arxiv …, 2025 - arxiv.org
Human body restoration, as a specific application of image restoration, is widely applied in
practice and plays a vital role across diverse fields. However, thorough research remains …