GenEval

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

Papers using GenEval (7)

Reflect-DiT: Inference-Time Scaling for Text-to-Image Diffusion Transformers via In-Context Reflection2025 · 33 citesDeeply Supervised Flow-Based Generative Models2025 · 13 citesDiT-Air: Revisiting the Efficiency of Diffusion Model Architecture Design in Text to Image Generation2025 · 1 citesSVG-T2I: Scaling Up Text-to-Image Latent Diffusion Model Without Variational Autoencoder2025PixelDiT: Pixel Diffusion Transformers for Image Generation2025Controlling Latent Diffusion Using Latent CLIP2025Optimal Stepsize for Diffusion Sampling2025