RoAR-VAE improves latent diffusability via robust prediction
It beats the strongest baseline tokenizer by 2.19 points and FLUX.1-VAE small-text accuracy by 16.93 points.
Stories per day · 30 days
3 RSS
3 stories, newest first · one card per story
Stories tagged #visual-tokenizer
QuadTok: Quadtree Visual Tokenizer for Autoregressive Image Generation
QuadTok's quadtree tokenizer lets a 947M model reach 2.08 gFID while using fewer tokens.
StableVQ: Practical Guidelines for Stable Vector-Quantized Tokenizer Training
StableVQ provides practical guidelines for stable Vector-Quantized tokenizer training, addressing instability between encoder and codebook optimization.