AI Paper Atlas

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

MultiGen: Zero-shot Image Generation from Multi-modal Prompts

Zhi-Fan Wu, Lianghua Huang, Wei Wang, Yanheng Wei, Yu Liu

ECCV 2024 · Image generation › Text-to-image diffusion · approach: Personalized and region-controlled generation · 2 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
use SigLIP ViT-SO400M-384 instead of CLIP ViT-L/14-336 as image feature encoder (ablation)MultiGen · object-conditioned generation (qualitative)object attribute fidelityImproved
extract object features by cropping object images instead of RoIAlign pooling from full-image feature map (ablation)MultiGen · object-conditioned generation (qualitative)object attribute fidelityImproved
add augmented tokens (object-level text, coordinates, image) to the SD 1.5 text conditionStable Diffusion 1.5 · MS-COCO 2014 val 30kFID: 9.93 -> 9.84No clear effect
use multi-modal zero-shot MultiGen versus per-subject tuning with Textual InversionMultiGen · DreamBooth benchmarkDINO: 0.569 -> 0.615Improved
use zero-shot MultiGen versus DreamBooth tuningMultiGen · DreamBooth benchmarkDINO: 0.668 -> 0.615Hurt
use MultiGen versus zero-shot BLIP-DiffusionMultiGen · DreamBooth benchmarkDINO: 0.594 -> 0.615Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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