Papers › Vector Quantized Diffusion Model for Text-to-Image Synthesis
Vector Quantized Diffusion Model for Text-to-Image Synthesis
Shuyang Gu, Dong Chen, Jianmin Bao, Fang Wen, Bo Zhang, Dongdong Chen, Lu Yuan, Baining Guo
We present the vector quantized diffusion (VQ-Diffusion) model for text-to-image generation. This method is based on a vector quantized variational autoencoder (VQ-VAE) whose latent space is modeled by a conditional variant of the recently developed Denoising Diffusion Probabilistic Model (DDPM). We find that this latent-space method is well-suited for text-to-image generation tasks because it not only eliminates the unidirectional bias with existing methods but also allows us to incorporate a mask-and-replace diffusion strategy to avoid the accumulation of errors, which is a serious problem with existing methods. Our experiments show that the VQ-Diffusion produces significantly better text-to-image generation results when compared with conventional autoregressive (AR) models with similar numbers of parameters. Compared with previous GAN-based text-to-image methods, our VQ-Diffusion can handle more complex scenes and improve the synthesized image quality by a large margin. Finally, we show that the image generation computation in our method can be made highly efficient by reparameterization. With traditional AR methods, the text-to-image generation time increases linearly with the output image resolution and hence is quite time consuming even for normal size images. The VQ-Diffusion allows us to achieve a better trade-off between quality and speed. Our experiments indicate that the VQ-Diffusion model with the reparameterization is fifteen times faster than traditional AR methods while achieving a better image quality.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Text-to-Image Generation | COCO (Common Objects in Context) | VQ-Diffusion-F | FID | 13.86 | #37 of 69 | Archive leaderboard | report |
| Text-to-Image Generation | COCO (Common Objects in Context) | VQ-Diffusion-B | FID | 19.75 | #43 of 69 | Archive leaderboard | report |
| Text-to-Image Generation | CUB | VQ-Diffusion-F | FID | 10.32 | #6 of 20 | Archive leaderboard | report |
| Text-to-Image Generation | CUB | VQ-Diffusion-B | FID | 11.94 | #8 of 20 | Archive leaderboard | report |
| Text-to-Image Generation | CUB | VQ-Diffusion-S | FID | 12.97 | #9 of 20 | Archive leaderboard | report |
| Text-to-Image Generation | Oxford 102 Flowers | VQ-Diffusion-F | FID | 14.1 | #2 of 8 | Archive leaderboard | report |
| Text-to-Image Generation | Oxford 102 Flowers | VQ-Diffusion-B | FID | 14.88 | #3 of 8 | Archive leaderboard | report |
| Text-to-Image Generation | Oxford 102 Flowers | VQ-Diffusion-S | FID | 14.95 | #4 of 8 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections