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 2351–2400 of 6689 papers

TitleStatusHype
Do DALL-E and Flamingo Understand Each Other?—0
DOCCI: Descriptions of Connected and Contrasting Images—0
Cheap-fake Detection with LLM using Prompt Engineering—0
Are handcrafted filters helpful for attributing AI-generated images?—0
Generative Probabilistic Image Colorization—0
Divide, Evaluate, and Refine: Evaluating and Improving Text-to-Image Alignment with Iterative VQA Feedback—0
ChatScratch: An AI-Augmented System Toward Autonomous Visual Programming Learning for Children Aged 6-12—0
Generative Image Modeling using Style and Structure Adversarial Networks—0
Divide and Conquer: Language Models can Plan and Self-Correct for Compositional Text-to-Image Generation—0
DIVE: Taming DINO for Subject-Driven Video Editing—0
ChatPainter: Improving Text to Image Generation using Dialogue—0
Are generative models fair? A study of racial bias in dermatological image generation—0
Generative Model for Zero-Shot Sketch-Based Image Retrieval—0
Diversity Regularized Adversarial Learning—0
ChatGen: Automatic Text-to-Image Generation From FreeStyle Chatting—0
Diversity and Diffusion: Observations on Synthetic Image Distributions with Stable Diffusion—0
Accelerating Diffusion Models via Pre-segmentation Diffusion Sampling for Medical Image Segmentation—0
ChatAnything: Facetime Chat with LLM-Enhanced Personas—0
Diversify, Don't Fine-Tune: Scaling Up Visual Recognition Training with Synthetic Images—0
Are Conditional Latent Diffusion Models Effective for Image Restoration?—0
Diverse Single Image Generation with Controllable Global Structure—0
Adversarially robust segmentation models learn perceptually-aligned gradients—0
Generative Image Modeling Using Spatial LSTMs—0
Character Generation through Self-Supervised Vectorization—0
Generative Flows with Invertible Attentions—0
Are conditional GANs explicitly conditional?—0
Adversarially Perturbed Wavelet-based Morphed Face Generation—0
Generative Guiding Block: Synthesizing Realistic Looking Variants Capable of Even Large Change Demands—0
DiverseFlow: Sample-Efficient Diverse Mode Coverage in Flows—0
Diverse Diffusion: Enhancing Image Diversity in Text-to-Image Generation—0
A Recipe for Scaling up Text-to-Video Generation with Text-free Videos—0
PixCell: A generative foundation model for digital histopathology images—0
Diverse and Tailored Image Generation for Zero-shot Multi-label Classification—0
DiverGAN: An Efficient and Effective Single-Stage Framework for Diverse Text-to-Image Generation—0
DivCon: Divide and Conquer for Progressive Text-to-Image Generation—0
DiVAE: Photorealistic Images Synthesis with Denoising Diffusion Decoder—0
Ditto: Accelerating Diffusion Model via Temporal Value Similarity—0
DiTFastAttnV2: Head-wise Attention Compression for Multi-Modality Diffusion Transformers—0
Chain-of-Jailbreak Attack for Image Generation Models via Editing Step by Step—0
FreqPolicy: Efficient Flow-based Visuomotor Policy via Frequency Consistency—0
Generative Modeling of Individual Behavior at Scale—0
DiTFastAttn: Attention Compression for Diffusion Transformer Models—0
Adversarially Approximated Autoencoder for Image Generation and Manipulation—0
DiT-Air: Revisiting the Efficiency of Diffusion Model Architecture Design in Text to Image Generation—0
DiT4SR: Taming Diffusion Transformer for Real-World Image Super-Resolution—0
CGOF++: Controllable 3D Face Synthesis with Conditional Generative Occupancy Fields—0
EIUP: A Training-Free Approach to Erase Non-Compliant Concepts Conditioned on Implicit Unsafe Prompts—0
DiT4Edit: Diffusion Transformer for Image Editing—0
CG-NeRF: Conditional Generative Neural Radiance Fields—0
Adversarial Learning of Semantic Relevance in Text to Image Synthesis—0
Show:102550
← PrevPage 48 of 134Next →
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