# CogView3: Finer and Faster Text-to-Image Generation via Relay Diffusion

arXiv: https://arxiv.org/abs/2403.05121 · HTML: https://mlsanity.com/paper/2403.05121/

## Key facts

- Cited by 72 papers in the map (data through 14 Oct 2026).
- Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models.
- Builds on 26 of its 35 references that are in the map.
- First posted on arXiv 8 Mar 2024.

## Placed in

- Diffusion models / [Image generation, text-to-image and editing](https://mlsanity.com/diffusion/image-generation-text-to-image-and-editing/)

## Builds on (most cited first, 26 of 26)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Scaling Autoregressive Models for Content-Rich Text-to-Image Generation](https://mlsanity.com/paper/2206.10789/) (2022)
- [Cascaded Diffusion Models for High Fidelity Image Generation](https://mlsanity.com/paper/2106.15282/) (2021)
- [Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis](https://mlsanity.com/paper/2306.09341/) (2023)
- [Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference](https://mlsanity.com/paper/2310.04378/) (2023)
- [Adversarial Diffusion Distillation](https://mlsanity.com/paper/2311.17042/) (2023)
- [On Distillation of Guided Diffusion Models](https://mlsanity.com/paper/2210.03142/) (2022)
- [CogVLM: Visual Expert for Pretrained Language Models](https://mlsanity.com/paper/2311.03079/) (2023)
- [CogView: Mastering Text-to-Image Generation via Transformers](https://mlsanity.com/paper/2105.13290/) (2021)
- [MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation](https://mlsanity.com/paper/2302.08113/) (2023)
- [Scaling up GANs for Text-to-Image Synthesis](https://mlsanity.com/paper/2303.05511/) (2023)
- [Emu: Enhancing Image Generation Models Using Photogenic Needles in a Haystack](https://mlsanity.com/paper/2309.15807/) (2023)
- [Relay Diffusion: Unifying diffusion process across resolutions for image synthesis](https://mlsanity.com/paper/2309.03350/) (2023)
- [Mixture of Diffusers for scene composition and high resolution image generation](https://mlsanity.com/paper/2302.02412/) (2023)
- [Wuerstchen: An Efficient Architecture for Large-Scale Text-to-Image Diffusion Models](https://mlsanity.com/paper/2306.00637/) (2023)

## Built on by (most cited first, 30 of 72)

- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools](https://mlsanity.com/paper/2406.12793/) (2024)
- [Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer](https://mlsanity.com/paper/2511.22699/) (2025)
- [Lumina-T2X: Transforming Text into Any Modality, Resolution, and Duration via Flow-based Large Diffusion Transformers](https://mlsanity.com/paper/2405.05945/) (2024)
- [Simpler Diffusion (SiD2): 1.5 FID on ImageNet512 with pixel-space diffusion](https://mlsanity.com/paper/2410.19324/) (2024)
- [ControlVAR: Exploring Controllable Visual Autoregressive Modeling](https://mlsanity.com/paper/2406.09750/) (2024)
- [VideoTetris: Towards Compositional Text-to-Video Generation](https://mlsanity.com/paper/2406.04277/) (2024)
- [Pixel-Perfect Depth with Semantics-Prompted Diffusion Transformers](https://mlsanity.com/paper/2510.07316/) (2025)
- [Diffusion Feedback Helps CLIP See Better](https://mlsanity.com/paper/2407.20171/) (2024)
- [FlowTok: Flowing Seamlessly Across Text and Image Tokens](https://mlsanity.com/paper/2503.10772/) (2025)
- [FlashVideo: Flowing Fidelity to Detail for Efficient High-Resolution Video Generation](https://mlsanity.com/paper/2502.05179/) (2025)
- [Dimba: Transformer-Mamba Diffusion Models](https://mlsanity.com/paper/2406.01159/) (2024)
- [AutoFigure: Generating and Refining Publication-Ready Scientific Illustrations](https://mlsanity.com/paper/2602.03828/) (2026)
- [ResMaster: Mastering High-Resolution Image Generation via Structural and Fine-Grained Guidance](https://mlsanity.com/paper/2406.16476/) (2024)
- [Improving Long-Text Alignment for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2410.11817/) (2024)
- [Owl-1: Omni World Model for Consistent Long Video Generation](https://mlsanity.com/paper/2412.09600/) (2024)
- [MMIG-Bench: Towards Comprehensive and Explainable Evaluation of Multi-Modal Image Generation Models](https://mlsanity.com/paper/2505.19415/) (2025)
- [T2I-RiskyPrompt: A Benchmark for Safety Evaluation, Attack, and Defense on Text-to-Image Model](https://mlsanity.com/paper/2510.22300/) (2025)
- [Self-Cross Diffusion Guidance for Text-to-Image Synthesis of Similar Subjects](https://mlsanity.com/paper/2411.18936/) (2024)
- [Enhancing Intent Understanding for Ambiguous prompt: A Human-Machine Co-Adaption Strategy](https://mlsanity.com/paper/2501.15167/) (2025)
- [MMMG: A Massive, Multidisciplinary, Multi-Tier Generation Benchmark for Text-to-Image Reasoning](https://mlsanity.com/paper/2506.10963/) (2025)
- [Is One GPU Enough? Pushing Image Generation at Higher-Resolutions with Foundation Models](https://mlsanity.com/paper/2406.07251/) (2024)
- [Audio Super-Resolution with Latent Bridge Models](https://mlsanity.com/paper/2509.17609/) (2025)
- [Ultra-Resolution Adaptation with Ease](https://mlsanity.com/paper/2503.16322/) (2025)
- [PrimeDepth: Efficient Monocular Depth Estimation with a Stable Diffusion Preimage](https://mlsanity.com/paper/2409.09144/) (2024)
- [Patch Matters: Training-free Fine-grained Image Caption Enhancement via Local Perception](https://mlsanity.com/paper/2504.06666/) (2025)
- [Twin Co-Adaptive Dialogue for Progressive Image Generation](https://mlsanity.com/paper/2504.14868/) (2025)
- [PosterVerse: A Full-Workflow Framework for Commercial-Grade Poster Generation with HTML-Based Scalable Typography](https://mlsanity.com/paper/2601.03993/) (2026)
- [Slight Corruption in Pre-training Data Makes Better Diffusion Models](https://mlsanity.com/paper/2405.20494/) (2024)
- [Text-to-Image Synthesis: A Decade Survey](https://mlsanity.com/paper/2411.16164/) (2024)

## Abstract (arXiv)

Recent advancements in text-to-image generative systems have been largely driven by diffusion models. However, single-stage text-to-image diffusion models still face challenges, in terms of computational efficiency and the refinement of image details. To tackle the issue, we propose CogView3, an innovative cascaded framework that enhances the performance of text-to-image diffusion. CogView3 is the first model implementing relay diffusion in the realm of text-to-image generation, executing the task by first creating low-resolution images and subsequently applying relay-based super-resolution. This methodology not only results in competitive text-to-image outputs but also greatly reduces both training and inference costs. Our experimental results demonstrate that CogView3 outperforms SDXL, the current state-of-the-art open-source text-to-image diffusion model, by 77.0% in human evaluations, all while requiring only about 1/2 of the inference time. The distilled variant of CogView3 achieves comparable performance while only utilizing 1/10 of the inference time by SDXL.