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 1–25 of 6689 papers

TitleStatusHype
Open-Sora: Democratizing Efficient Video Production for AllCode13
InstantID: Zero-shot Identity-Preserving Generation in SecondsCode11
Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model ScalingCode11
Emerging Properties in Unified Multimodal PretrainingCode9
Infinity: Scaling Bitwise AutoRegressive Modeling for High-Resolution Image SynthesisCode9
OOTDiffusion: Outfitting Fusion based Latent Diffusion for Controllable Virtual Try-onCode9
HART: Efficient Visual Generation with Hybrid Autoregressive TransformerCode9
SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion TransformerCode9
SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion TransformersCode9
Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale PredictionCode9
MaskSketch: Unpaired Structure-guided Masked Image GenerationCode7
InstantStyle: Free Lunch towards Style-Preserving in Text-to-Image GenerationCode7
Lumina-Next: Making Lumina-T2X Stronger and Faster with Next-DiTCode7
Learning Multi-dimensional Human Preference for Text-to-Image GenerationCode7
Chameleon: Mixed-Modal Early-Fusion Foundation ModelsCode7
InfiniteYou: Flexible Photo Recrafting While Preserving Your IdentityCode7
Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese UnderstandingCode7
In-Context LoRA for Diffusion TransformersCode7
OmniGen2: Exploration to Advanced Multimodal GenerationCode7
Improving Sample Quality of Diffusion Models Using Self-Attention GuidanceCode7
Goku: Flow Based Video Generative Foundation ModelsCode7
Infinity-MM: Scaling Multimodal Performance with Large-Scale and High-Quality Instruction DataCode7
Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative PretrainingCode7
DialogGen: Multi-modal Interactive Dialogue System for Multi-turn Text-to-Image GenerationCode7
Adding Conditional Control to Text-to-Image Diffusion ModelsCode7
Show:102550
← PrevPage 1 of 268Next →

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