ImageNet 256
Emerging14papers using it
2022first seen
ImageNet-256 is a dataset used to evaluate image generation models, containing a subset of images from the larger ImageNet dataset, specifically resized to 256x256 pixels.
Papers using ImageNet 256 (14)
- CAR-Flow: Condition-Aware Reparameterization Aligns Source and Target for Better Flow MatchingConservative Flows: A New Paradigm of Generative ModelsUnlearning for One-Step Generative Models via Unbalanced Optimal TransportPixelGen: Improving Pixel Diffusion with Perceptual SupervisionGuiding Token-Sparse Diffusion ModelsBoosting Latent Diffusion Models via Disentangled Representation AlignmentPixelDiT: Pixel Diffusion Transformers for Image GenerationAdversarial Flow ModelsThere is No VAE: End-to-End Pixel-Space Generative Modeling via Self-Supervised Pre-trainingDiffusion Models without Classifier-free GuidanceSimpler Diffusion (SiD2): 1.5 FID on ImageNet512 with pixel-space
diffusionImproving Diffusion Model Efficiency Through PatchingAccelerating Guided Diffusion Sampling with Splitting Numerical MethodsHigh Fidelity Image Synthesis With Deep VAEs In Latent Space