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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| fine-tune on MS-COCO | CogView2 · MS-COCO 256x256 | FID-0: 24.0 -> 17.5 | Improved |
| fine-tune on MS-COCO | CogView2 · COCO captions human evaluation | human preference | Hurt |
| use customized CUDA 2D local attention instead of global attention | super-resolution transformer · 4,096-token sequences | speed: up to 40x | Improved |
| hierarchical local parallel autoregressive super-resolution instead of sliding window | CogView · high-resolution generation | speed: about 10x | Improved |
| upweight textual attention by constant c | CogView2 · text-to-image | text relevance | Improved |
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.
- CogView — CogView: Mastering Text-to-Image Generation via Transformers (NeurIPS 2021) · better on 3 of 3 shared results
- DF-GAN* — DF-GAN: A Simple and Effective Baseline for Text-to-Image Synthesis (CVPR 2022) · better on 2 of 2 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
- Exploring the Deep Fusion of Large Language Models and Diffusion Transformers for Text-to-Image Synthesis (CVPR 2025 · similarity 0.87)
- CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer (ICLR 2025 · similarity 0.86)
- PixArt-$\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis (ICLR 2024 · similarity 0.86)
- EditAR: Unified Conditional Generation with Autoregressive Models (CVPR 2025 · similarity 0.86)
- Towards Transformer-Based Aligned Generation with Self-Coherence Guidance (CVPR 2025 · similarity 0.86)
- SANA: Efficient High-Resolution Text-to-Image Synthesis with Linear Diffusion Transformers (ICLR 2025 · similarity 0.86)
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.
