GenEval

GenEval is a benchmark used to evaluate the performance of text-to-image synthesis models.

Papers using GenEval (6)

SVG-T2I: Scaling Up Text-to-Image Latent Diffusion Model Without Variational Autoencoder2025DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation2025PixelDiT: Pixel Diffusion Transformers for Image Generation2025Controlling Latent Diffusion Using Latent CLIP2025Optimal Stepsize for Diffusion Sampling2025Reflect-DiT: Inference-Time Scaling for Text-to-Image Diffusion Transformers via In-Context Reflection2025