Research map / Image generation / Text-to-image diffusion
CogView: Mastering Text-to-Image Generation via Transformers
Ming Ding, Zhuoyi Yang, Wenyi Hong, Wendi Zheng, Chang Zhou, Da Yin, Junyang Lin, Xu Zou, Zhou Shao, Hongxia Yang, 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 |
|---|---|---|---|
| CogView 4B transformer vs DALL-E | text-to-image generation · MS COCO | FID-0: 27.5 -> 27.1 | Improved |
| CogView vs DALL-E | text-to-image generation · MS COCO | FID-2: 45.5 -> 13.9 | Improved |
| CogView vs DM-GAN | text-to-image generation · MS COCO | IS: 32.2 -> 18.2 | Hurt |
| add Sandwich-LN and PB-relax (ablation) | deep Transformer (toy, 64 layers) · toy training stability | training without overflow | Improved |
| self-reranking by CapLoss instead of CLIP (ablation) | CogView · MS COCO | FID-0 | Improved |
| self-reranking by CapLoss instead of CLIP (ablation) | CogView · MS COCO | IS | Hurt |
| shrink token embedding gradient by 0.1 (ablation) | CogView · pretraining | performance | No clear effect |
| add super-resolution finetuning | CogView · human evaluation | image quality | Improved |
Later papers that compared with this method
8 later accepted papers report CogView4 as a baseline in their results tables; 8 of them report a better number on most of the results they share with it.
- Guiding Token-Sparse Diffusion Models (CVPR 2026 · better on 1 of 1 shared result)
- HieraFashDiff: Hierarchical Fashion Design with Multi-stage Diffusion Models (AAAI 2025 · better on 3 of 3 shared results)
- DiffCloth: Diffusion Based Garment Synthesis and Manipulation via Structural Cross-modal Semantic Alignment (ICCV 2023 · better on 1 of 1 shared result)
- CogView2: Faster and Better Text-to-Image Generation via Hierarchical Transformers (NeurIPS 2022 · better on 3 of 3 shared results)
- Text-to-Image Synthesis Based on Object-Guided Joint-Decoding Transformer (CVPR 2022 · better on 2 of 2 shared results)
- Towards Language-Free Training for Text-to-Image Generation (CVPR 2022 · better on 2 of 2 shared results)
- Make-a-Scene: Scene-Based Text-to-Image Generation with Human Priors (ECCV 2022 · better on 2 of 2 shared results)
- Vector Quantized Diffusion Model for Text-to-Image Synthesis (CVPR 2022 · better on 1 of 1 shared result)
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.
- DM-GAN — DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-To-Image Synthesis (CVPR 2019) · better on 5 of 7 shared results
- AttnGAN — AttnGAN: Fine-Grained Text to Image Generation With Attentional Generative Adversarial Networks (CVPR 2018) · better on 6 of 7 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 0.85)
- OneIG-Bench: Omni-dimensional Nuanced Evaluation for Image Generation (NeurIPS 2025 · similarity 0.85)
- Towards Transformer-Based Aligned Generation with Self-Coherence Guidance (CVPR 2025 · similarity 0.85)
- IT3D: Improved Text-to-3D Generation with Explicit View Synthesis (AAAI 2024 · similarity 0.85)
- Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis (ICLR 2025 · similarity 0.85)
- PreciseCam: Precise Camera Control for Text-to-Image Generation (CVPR 2025 · similarity 0.85)
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.
