SOTAVerified

Conditional Image Generation

Conditional image generation is the task of generating new images from a dataset conditional on their class.

( Image credit: PixelCNN++ )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–10 of 286 papers

TitleStatusHype
Noise Conditional Variational Score DistillationCode1
Forward-only Diffusion Probabilistic ModelsCode1
Context-Aware Autoregressive Models for Multi-Conditional Image Generation—0
Efficient Flow Matching using Latent Variables—0
VistaDepth: Frequency Modulation With Bias Reweighting For Enhanced Long-Range Depth Estimation—0
PRISM: A Unified Framework for Photorealistic Reconstruction and Intrinsic Scene Modeling—0
PixelFlow: Pixel-Space Generative Models with FlowCode3
A Unified Agentic Framework for Evaluating Conditional Image GenerationCode1
A Hybrid Wavelet-Fourier Method for Next-Generation Conditional Diffusion Models—0
Less-to-More Generalization: Unlocking More Controllability by In-Context GenerationCode5
Show:102550
← PrevPage 1 of 29Next →
All datasetsCIFAR-10ImageNet 128x128ArtBench-10 (32x32)CIFAR-100ImageNet 64x64COCO-AnimalsImageNet 256x256CelebAMask-HQCIFAR-10 LTImageNet-LTTiny ImageNet

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Projected GANFID11.84—Unverified
2BigGAN + CRFID4.65—Unverified
3StyleGAN2FID4.49—Unverified
4BigGAN + DiffAugFID4.06—Unverified
5ReACGAN + DiffAugFID3.18—Unverified
6StyleGAN2 + ADAFID2.63—Unverified