SOTAVerified

Image Generation

Image Generation (synthesis) is the task of generating new images from an existing dataset.

  • Unconditional generation refers to generating samples unconditionally from the dataset, i.e. $p(y)$
  • Conditional image generation (subtask) refers to generating samples conditionally from the dataset, based on a label, i.e. $p(y|x)$.

In this section, you can find state-of-the-art leaderboards for unconditional generation. For conditional generation, and other types of image generations, refer to the subtasks.

( Image credit: StyleGAN )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 5651–5675 of 6689 papers

TitleStatusHype
Simple Drop-in LoRA Conditioning on Attention Layers Will Improve Your Diffusion Model—0
Simpler Diffusion: 1.5 FID on ImageNet512 with Pixel-space Diffusion—0
Simpler Diffusion (SiD2): 1.5 FID on ImageNet512 with pixel-space diffusion—0
Simple Transparent Adversarial Examples—0
Simple U-net Based Synthetic Polyp Image Generation: Polyp to Negative and Negative to Polyp—0
Simplex Autoencoders—0
Simplifying Models with Unlabeled Output Data—0
Simulation of an Elevator Group Control Using Generative Adversarial Networks and Related AI Tools—0
Simultaneous Multiple-Prompt Guided Generation Using Differentiable Optimal Transport—0
Simultaneous Super-Resolution and Cross-Modality Synthesis of 3D Medical Images using Weakly-Supervised Joint Convolutional Sparse Coding—0
Vector Quantized Image-to-Image Translation—0
YoChameleon: Personalized Vision and Language Generation—0
Adversarial Attacks on Image Generation With Made-Up Words—0
VehicleGAN: Pair-flexible Pose Guided Image Synthesis for Vehicle Re-identification—0
Vehicle Image Generation Going Well with The Surroundings—0
Single-Image 3D Human Digitization with Shape-Guided Diffusion—0
VeRi3D: Generative Vertex-based Radiance Fields for 3D Controllable Human Image Synthesis—0
Adversarial Attack Against Images Classification based on Generative Adversarial Networks—0
Verisimilar Image Synthesis for Accurate Detection and Recognition of Texts in Scenes—0
SingleInsert: Inserting New Concepts from a Single Image into Text-to-Image Models for Flexible Editing—0
Advancing Video Quality Assessment for AIGC—0
Single Stage Multi-Pose Virtual Try-On—0
Single Underwater Image Enhancement Using an Analysis-Synthesis Network—0
Single-View Height Estimation with Conditional Diffusion Probabilistic Models—0
Advancing Urban Renewal: An Automated Approach to Generating Historical Arcade Facades with Stable Diffusion Models—0
Show:102550
← PrevPage 227 of 268Next →
All datasetsImageNet 256x256CIFAR-10ImageNet 64x64ImageNet 512x512FFHQ 256 x 256CelebA 64x64ImageNet 32x32LSUN Bedroom 256 x 256STL-10LSUN Churches 256 x 256ImageNet 128x128FFHQ 1024 x 1024

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Improved DDPMFID12.3—Unverified
2ADMFID11.84—Unverified
3BigGAN-deepFID8.1—Unverified
4Polarity-BigGANFID6.82—Unverified
5VQGAN+Transformer (k=mixed, p=1.0, a=0.005)FID6.59—Unverified
6MaskGITFID6.18—Unverified
7VQGAN+Transformer (k=600, p=1.0, a=0.05)FID5.2—Unverified
8CDMFID4.88—Unverified
9ADM-GFID4.59—Unverified
10RINFID4.51—Unverified
#ModelMetricClaimedVerifiedStatus
1PresGANFID52.2—Unverified
2RESFLOWFID48.29—Unverified
3Residual FlowFID46.37—Unverified
4GLF+perceptual loss (ours)FID44.6—Unverified
5ProdPoly no activation functionsFID40.45—Unverified
6ProdPoly no activation functionsFID36.77—Unverified
7ACGANFID35.47—Unverified
8DenseFlow-74-10FID34.9—Unverified
9NVAE w/ flowFID32.53—Unverified
10QSNGANFID31.97—Unverified
#ModelMetricClaimedVerifiedStatus
1GLIDE + CLSFID30.87—Unverified
2GLIDE + CLIPFID30.46—Unverified
3GLIDE + CLS-FREEFID29.22—Unverified
4GLIDE + CLIP + CLS + CLS-FREEFID29.18—Unverified
5PGMGANFID21.73—Unverified
6CLR-GANFID20.27—Unverified
7FMFID14.45—Unverified
8CT (Direct Generation, NFE=1)FID13—Unverified
9CT (Direct Generation, NFE=2)FID11.1—Unverified
10GLIDE +CLSKID7.95—Unverified