AI Paper Atlas

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

One Transformer Fits All Distributions in Multi-Modal Diffusion at Scale

Fan Bao, Shen Nie, Kaiwen Xue, Chongxuan Li, Shi Pu, Yaole Wang, Gang Yue, Yue Cao, Hang Su, Jun Zhu

ICML 2023 · Image generation › Text-to-image diffusion · approach: Compositional text-to-image guidance · 28 citations (OpenAlex)

Read the paper

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 one joint noise-prediction model with modality-specific timesteps instead of the multi-flow multi-task strategyGeneral-purpose image-text generation · MS-COCO validation, text-to-image generationFID: 10.09 -> 9.71Improved
Use UniDiffuser instead of Versatile DiffusionGeneral-purpose image-text generation · Text-to-image and image-to-text generationFID and CLIP scoreImproved
Apply classifier-free guidance during conditional and joint samplingUniDiffuser · Conditional and joint generationSample quality and image-text alignmentImproved
Use UniDiffuser instead of Versatile DiffusionGeneral-purpose image-text generation · Text-to-image generation, 10 samples and 25 denoising steps on one A100 80GB GPUInference time: 23.89s -> 19.77sImproved
Use UniDiffuser instead of Versatile DiffusionGeneral-purpose image-text generation · Text-to-image generation, 10 samples and 25 denoising steps on one A100 80GB GPUInference memory: 76.53GB -> 48.30GBImproved

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