most citedUnleashing Transformers: Parallel Token Prediction with Discrete Absorbing Diffusion for Fast High-Resolution Image Generation from Vector-Quantized Codes

6 citations · 6 across the 1 of their papers we have counts for

collaborators

1 paper

cs.CV2021★ 6 cited

Unleashing Transformers: Parallel Token Prediction with Discrete Absorbing Diffusion for Fast High-Resolution Image Generation from Vector-Quantized Codes

Sam Bond-Taylor, Peter Hessey, Hiroshi Sasaki +2

Whilst diffusion probabilistic models can generate high quality image content, key limitations remain in terms of both generating high-resolution imagery and their associated high…