COMPUTER VISION

Imagine Flash: Accelerating Emu Diffusion Models with Backward Distillation

April 18, 2024

Abstract

Diffusion models are a powerful generative framework, but come with expensive inference. Existing acceleration methods often compromise image quality or fail under complex conditioning when operating in an extremely low-step regime. In this work, we propose a novel distillation framework tailored to enable high-fidelity, diverse sample generation using just one to three steps. Our approach comprises three key components: (i) Backward Distillation, which mitigates training-inference discrepancies by calibrating the student on its own backward trajectory; (ii) Shifted Reconstruction Loss that dynamically adapts knowledge transfer based on the current time step; and (iii) Noise Correction, an inference time technique that enhances sample quality by addressing singularities in noise prediction. Through extensive experiments, we demonstrate that our method outperforms existing competitors in quantitative metrics and human evaluations. Remarkably, it achieves performance comparable to the teacher model using only three denoising steps, enabling efficient high-quality generation.

Download the Paper

AUTHORS

Written by

Jonas Kohler

Albert Pumarola

Edgar Schoenfeld

Artsiom Sanakoyeu

Roshan Sumbaly

Peter Vajda

Ali Thabet

Publisher

Meta

Research Topics

Computer Vision

Related Publications

December 11, 2024

COMPUTER VISION

Measuring Deja Vu Memorization Efficiently

Narine Kokhlikyan, Bargav Jayaraman, Florian Bordes, Chuan Guo, Kamalika Chaudhuri

December 11, 2024

November 20, 2024

CONVERSATIONAL AI

COMPUTER VISION

Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations

Jianfeng Chi, Ujjwal Karn, Hongyuan Zhan, Eric Smith, Javier Rando, Yiming Zhang, Kate Plawiak, Zacharie Delpierre Coudert, Kartikeya Upasani, Mahesh Pasupuleti

November 20, 2024

November 11, 2024

COMPUTER VISION

HOI-Swap: Swapping Objects in Videos with Hand-Object Interaction Awareness

Sherry Xue, Romy Luo, Changan Chen, Kristen Grauman

November 11, 2024

October 31, 2024

HUMAN & MACHINE INTELLIGENCE

ROBOTICS

Digitizing Touch with an Artificial Multimodal Fingertip

Mike Lambeta, Tingfan Wu, Ali Sengül, Victoria Rose Most, Nolan Black, Kevin Sawyer, Romeo Mercado, Haozhi Qi, Alexander Sohn, Byron Taylor, Norb Tydingco, Gregg Kammerer, Dave Stroud, Jake Khatha, Kurt Jenkins, Kyle Most, Neal Stein, Ricardo Chavira, Thomas Craven-Bartle, Eric Sanchez, Yitian Ding, Jitendra Malik, Roberto Calandra

October 31, 2024

Help Us Pioneer The Future of AI

We share our open source frameworks, tools, libraries, and models for everything from research exploration to large-scale production deployment.