Instant-Style: Style-Preservation in Text-to-Image Generation
Over the past few years, tuning-based diffusion models have demonstrated remarkable progress…
POKELLMON: A Human-Parity Agent for Pokemon Battles with LLMs
Large Language Models and Generative AI have demonstrated unprecedented success on a…
Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction
The advent of GPT models, along with other autoregressive or AR large…
InstructIR: High-Quality Image Restoration Following Human Instructions
An image can convey a great deal, yet it may also be…
DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors
Computer vision is one of the most exciting and well-researched fields within…