AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

MobileDiffusion: Instant Text-to-Image Generation on Mobile Devices

Yang Zhao, Zhisheng Xiao, Yanwu Xu, Haolin Jia, Tingbo Hou

ECCV 2024 · Image generation › Text-to-image diffusion · approach: Text-driven synthesis and semantic guidance · 98 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
set W_K = W_V in self-attention (ablation)MobileDiffusion UNet · text-to-image qualitymodel quality: about 5% parameter reductionNo clear effect
replace gelu with swish in GLU (ablation)MobileDiffusion UNet · text-to-image qualitymetrics and perceptual qualityNo clear effect
finetune softmax attention into relu attention (ablation)MobileDiffusion UNet · text-to-image qualityvisual qualityNo clear effect
trim feed-forward expansion ratio from 4 to 3 (ablation)MobileDiffusion UNet · MS-COCO FIDFID: +0.27 FID, 10% fewer parametersHurt
use larger separable-conv kernels (7x7, 9x9) instead of 3x3 (ablation)MobileDiffusion separable conv block · text-to-image qualityqualityNo clear effect
use LoRA adversarial fine-tuning instead of full-parameter fine-tuning (ablation)UFOGen one-step model · MS-COCO FIDFID: 11.67 -> 13.45Hurt
replace diffusion reconstruction loss with distillation loss (ablation)UFOGen one-step model · MS-COCO FIDFID: 11.67 -> 11.20Improved
replace diffusion loss with distillation loss for downstream applications (ablation)UFOGen one-step model · downstream conditional generationapplication qualityHurt
use MobileDiffusion architecture instead of SD UNet (386M vs 862M params)text-to-image diffusion · MS-COCO FID-30K, 50 step DDIMFID-30K: 9.62 -> 8.65Improved
reduce to one-step generation with MobileDiffusionMobileDiffusion · HPS v2average score: 27.30 -> 26.65Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy