AI Paper Atlas

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

CogView2: Faster and Better Text-to-Image Generation via Hierarchical Transformers

Ming Ding, Wendi Zheng, Wenyi Hong, Jie Tang

NeurIPS 2022 · Image generation › Text-to-image diffusion · approach: Personalized and region-controlled generation · 120 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
fine-tune on MS-COCOCogView2 · MS-COCO 256x256FID-0: 24.0 -> 17.5Improved
fine-tune on MS-COCOCogView2 · COCO captions human evaluationhuman preferenceHurt
use customized CUDA 2D local attention instead of global attentionsuper-resolution transformer · 4,096-token sequencesspeed: up to 40xImproved
hierarchical local parallel autoregressive super-resolution instead of sliding windowCogView · high-resolution generationspeed: about 10xImproved
upweight textual attention by constant cCogView2 · text-to-imagetext relevanceImproved

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