CVLGDec 13, 2023

SpeedUpNet: A Plug-and-Play Adapter Network for Accelerating Text-to-Image Diffusion Models

arXiv:2312.08887v41 citationsh-index: 4Has CodeECCV
Originality Highly original
AI Analysis

This addresses computational bottlenecks for users of diffusion models, offering a plug-and-play solution that works across fine-tuned models without retraining.

The paper tackles the problem of accelerating text-to-image diffusion models while maintaining universality and output consistency, achieving over 10x speedup on SD v1.5 with state-of-the-art FID scores.

Text-to-image diffusion models (SD) exhibit significant advancements while requiring extensive computational resources. Existing acceleration methods usually require extensive training and are not universally applicable. LCM-LoRA, trainable once for diverse models, offers universality but rarely considers ensuring the consistency of generated content before and after acceleration. This paper proposes SpeedUpNet (SUN), an innovative acceleration module, to address the challenges of universality and consistency. Exploiting the role of cross-attention layers in U-Net for SD models, we introduce an adapter specifically designed for these layers, quantifying the offset in image generation caused by negative prompts relative to positive prompts. This learned offset demonstrates stability across a range of models, enhancing SUN's universality. To improve output consistency, we propose a Multi-Step Consistency (MSC) loss, which stabilizes the offset and ensures fidelity in accelerated content. Experiments on SD v1.5 show that SUN leads to an overall speedup of more than 10 times compared to the baseline 25-step DPM-solver++, and offers two extra advantages: (1) training-free integration into various fine-tuned Stable-Diffusion models and (2) state-of-the-art FIDs of the generated data set before and after acceleration guided by random combinations of positive and negative prompts. Code is available: https://williechai.github.io/speedup-plugin-for-stable-diffusions.github.io.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes