ImageNet-512x-512

ImageNet-512x512 is a dataset used to evaluate the performance of generative models, specifically in the context of one- and few-step modeling tasks.

Papers using ImageNet-512x-512 (9)

Simplifying, Stabilizing and Scaling Continuous-Time Consistency Models2024 · 1 citesTerminal Velocity Matching2025Align Your Flow: Scaling Continuous-Time Flow Map Distillation2025Direct Discriminative Optimization: Your Likelihood-Based Visual Generative Model is Secretly a GAN Discriminator2025Diffusion Models Beat GANs on Image Synthesis2021 · 2,173 citesScalable Diffusion Models with Transformers2022 · 42 citesSiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers2024 · 35 citesFast Training of Diffusion Models with Masked Transformers2023 · 8 citesDiffFit: Unlocking Transferability of Large Diffusion Models via Simple Parameter-Efficient Fine-Tuning2023 · 5 cites