EdgeFusion: On-Device Text-to-Image Generation

Thibault Castells, Kyu Song, Tairen Piao, shinkookchoi, Bo-Kyeong Kim, Hanyoung Yim, Changgwun Lee, Jae Gon Kim, Tae-Ho Kim

EdgeFusion: On-Device Text-to-Image Generation: 22 upvotes on Hugging Face Daily Papers, #6 of 12 papers on 2024-04-19. Day-by-day upvote history.

The intensive computational burden of Stable Diffusion (SD) for text-to-image generation poses a significant hurdle for its practical application. To tackle this challenge, recent research focuses on methods to reduce sampling steps, such as Latent Consistency Model (LCM), and on employing architectural optimizations, including pruning and knowledge distillation. Diverging from existing approaches, we uniquely start with a compact SD variant, BK-SDM. We observe that directly applying LCM to BK-SDM with commonly used crawled datasets yields unsatisfactory results. It leads us to develop two strategies: (1) leveraging high-quality image-text pairs from leading generative models and (2) designing an advanced distillation process tailored for LCM. Through our thorough exploration of quantization, profiling, and on-device deployment, we achieve rapid generation of photo-realistic, text-aligned images in just two steps, with latency under one second on resource-limited edge devices.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.