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

Showing 2650 of 6689 papers

TitleStatusHype
HiDream-I1: A High-Efficient Image Generative Foundation Model with Sparse Diffusion TransformerCode7
Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese UnderstandingCode7
Infinity-MM: Scaling Multimodal Performance with Large-Scale and High-Quality Instruction DataCode7
OmniGen2: Exploration to Advanced Multimodal GenerationCode7
Lumina-Next: Making Lumina-T2X Stronger and Faster with Next-DiTCode7
PuLID: Pure and Lightning ID Customization via Contrastive AlignmentCode7
PIXART-δ: Fast and Controllable Image Generation with Latent Consistency ModelsCode7
InfiniteYou: Flexible Photo Recrafting While Preserving Your IdentityCode7
Large Multilingual Models Pivot Zero-Shot Multimodal Learning across LanguagesCode6
Versatile Diffusion: Text, Images and Variations All in One Diffusion ModelCode6
Semi-Parametric Neural Image SynthesisCode6
Pseudo Numerical Methods for Diffusion Models on ManifoldsCode6
StreamDiffusion: A Pipeline-level Solution for Real-time Interactive GenerationCode6
Adversarial Diffusion DistillationCode6
PhotoMaker: Customizing Realistic Human Photos via Stacked ID EmbeddingCode6
Better speech synthesis through scalingCode6
Text-Guided Synthesis of Artistic Images with Retrieval-Augmented Diffusion ModelsCode6
Less-to-More Generalization: Unlocking More Controllability by In-Context GenerationCode5
Consistency ModelsCode5
Magic Clothing: Controllable Garment-Driven Image SynthesisCode5
CogView3: Finer and Faster Text-to-Image Generation via Relay DiffusionCode5
EMMA: Your Text-to-Image Diffusion Model Can Secretly Accept Multi-Modal PromptsCode5
CatVTON: Concatenation Is All You Need for Virtual Try-On with Diffusion ModelsCode5
FasterDiT: Towards Faster Diffusion Transformers Training without Architecture ModificationCode5
Fractal Generative ModelsCode5
Show:102550
← PrevPage 2 of 268Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Improved DDPMFID12.3Unverified
2ADMFID11.84Unverified
3BigGAN-deepFID8.1Unverified
4Polarity-BigGANFID6.82Unverified
5VQGAN+Transformer (k=mixed, p=1.0, a=0.005)FID6.59Unverified
6MaskGITFID6.18Unverified
7VQGAN+Transformer (k=600, p=1.0, a=0.05)FID5.2Unverified
8CDMFID4.88Unverified
9ADM-GFID4.59Unverified
10RINFID4.51Unverified
#ModelMetricClaimedVerifiedStatus
1PresGANFID52.2Unverified
2RESFLOWFID48.29Unverified
3Residual FlowFID46.37Unverified
4GLF+perceptual loss (ours)FID44.6Unverified
5ProdPoly no activation functionsFID40.45Unverified
6ProdPoly no activation functionsFID36.77Unverified
7ACGANFID35.47Unverified
8DenseFlow-74-10FID34.9Unverified
9NVAE w/ flowFID32.53Unverified
10QSNGANFID31.97Unverified
#ModelMetricClaimedVerifiedStatus
1GLIDE + CLSFID30.87Unverified
2GLIDE + CLIPFID30.46Unverified
3GLIDE + CLS-FREEFID29.22Unverified
4GLIDE + CLIP + CLS + CLS-FREEFID29.18Unverified
5PGMGANFID21.73Unverified
6CLR-GANFID20.27Unverified
7FMFID14.45Unverified
8CT (Direct Generation, NFE=1)FID13Unverified
9CT (Direct Generation, NFE=2)FID11.1Unverified
10GLIDE +CLSKID7.95Unverified