SynVAR: Synergizing Spatial and Semantic Alignment in Visual Autoregressive Model

Benchmark Model Rank Results
text-to-image-generation-on-t2i-compbenchSwitti + SynVAR#5Color: 0.7854Texture: 0.681Shape: 0.5467
text-to-image-generation-on-t2i-compbenchInfinity + SynVAR#7Spatial: 0.46Complex: 0.3902
text-to-image-generation-on-genevalInfinity + SynVAR#133Overall: 0.7079