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 1–50 of 286 papers

TitleStatusHype
MaskSketch: Unpaired Structure-guided Masked Image GenerationCode7
Less-to-More Generalization: Unlocking More Controllability by In-Context GenerationCode5
OminiControl2: Efficient Conditioning for Diffusion TransformersCode5
EMMA: Your Text-to-Image Diffusion Model Can Secretly Accept Multi-Modal PromptsCode5
Autoregressive Model Beats Diffusion: Llama for Scalable Image GenerationCode5
Fine-Tuning Image-Conditional Diffusion Models is Easier than You ThinkCode4
AnimateLCM: Computation-Efficient Personalized Style Video Generation without Personalized Video DataCode4
PixelFlow: Pixel-Space Generative Models with FlowCode3
DICEPTION: A Generalist Diffusion Model for Visual Perceptual TasksCode3
Normalizing Flows are Capable Generative ModelsCode3
CtrLoRA: An Extensible and Efficient Framework for Controllable Image GenerationCode3
Scaling Diffusion Transformers to 16 Billion ParametersCode3
All are Worth Words: A ViT Backbone for Diffusion ModelsCode3
Hierarchical Text-Conditional Image Generation with CLIP LatentsCode3
Autoregressive Image Generation using Residual QuantizationCode3
Autoregressive Image Generation with Randomized Parallel DecodingCode2
Diffusion Models without Classifier-free GuidanceCode2
Compressed Image Generation with Denoising Diffusion Codebook ModelsCode2
Adversarial Score identity Distillation: Rapidly Surpassing the Teacher in One StepCode2
BiGR: Harnessing Binary Latent Codes for Image Generation and Improved Visual Representation CapabilitiesCode2
Stabilize the Latent Space for Image Autoregressive Modeling: A Unified PerspectiveCode2
MaskBit: Embedding-free Image Generation via Bit TokensCode2
HumanRefiner: Benchmarking Abnormal Human Generation and Refining with Coarse-to-fine Pose-Reversible GuidanceCode2
Medical Vision Generalist: Unifying Medical Imaging Tasks in ContextCode2
Scalable Diffusion Models with State Space BackboneCode2
Return of Unconditional Generation: A Self-supervised Representation Generation MethodCode2
Simple diffusion: End-to-end diffusion for high resolution imagesCode2
A Novel Sampling Scheme for Text- and Image-Conditional Image Synthesis in Quantized Latent SpacesCode2
The ArtBench Dataset: Benchmarking Generative Models with ArtworksCode2
Conditional GANs with Auxiliary Discriminative ClassifierCode2
Diffusion Models Beat GANs on Image SynthesisCode2
Training Generative Adversarial Networks with Limited DataCode2
Noise Conditional Variational Score DistillationCode1
Forward-only Diffusion Probabilistic ModelsCode1
A Unified Agentic Framework for Evaluating Conditional Image GenerationCode1
IQA-Adapter: Exploring Knowledge Transfer from Image Quality Assessment to Diffusion-based Generative ModelsCode1
ChatHouseDiffusion: Prompt-Guided Generation and Editing of Floor PlansCode1
Frame Interpolation with Consecutive Brownian Bridge DiffusionCode1
Benchmarking Counterfactual Image GenerationCode1
CLIP-VQDiffusion : Langauge Free Training of Text To Image generation using CLIP and vector quantized diffusion modelCode1
FineDiffusion: Scaling up Diffusion Models for Fine-grained Image Generation with 10,000 ClassesCode1
Stochastic Conditional Diffusion Models for Robust Semantic Image SynthesisCode1
VIEScore: Towards Explainable Metrics for Conditional Image Synthesis EvaluationCode1
GIVT: Generative Infinite-Vocabulary TransformersCode1
Tell2Design: A Dataset for Language-Guided Floor Plan GenerationCode1
Particle Guidance: non-I.I.D. Diverse Sampling with Diffusion ModelsCode1
Elucidating The Design Space of Classifier-Guided Diffusion GenerationCode1
ImagenHub: Standardizing the evaluation of conditional image generation modelsCode1
Practical and Asymptotically Exact Conditional Sampling in Diffusion ModelsCode1
DiffBlender: Scalable and Composable Multimodal Text-to-Image Diffusion ModelsCode1
Show:102550
← PrevPage 1 of 6Next →
All datasetsCIFAR-10ImageNet 128x128ArtBench-10 (32x32)CIFAR-100ImageNet 64x64COCO-AnimalsImageNet 256x256CelebAMask-HQCIFAR-10 LTImageNet-LTTiny ImageNet

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Projection DiscriminatorFID17.5—Unverified
2BigGANFID14.73—Unverified
3CR-BigGANFID11.67—Unverified
4ContraGANFID10.3—Unverified
5NDAFID9.42—Unverified
6Splitting GANInception score8.87—Unverified
7WGAN-GPInception score8.67—Unverified
8SGANInception score8.59—Unverified
9AC-GANInception score8.25—Unverified
10Improved GANInception score8.09—Unverified
#ModelMetricClaimedVerifiedStatus
1AC-GANInception score28.5—Unverified
2Projection DiscriminatorFID27.62—Unverified
3SAGANFID18.65—Unverified
4Your Local GANFID15.94—Unverified
5HamGANFID14.8—Unverified
6FQ-GANFID13.77—Unverified
7BigGAN + instance selectionFID9.61—Unverified
8IC-GAN + DAFID9.5—Unverified
9Omni-GANFID8.3—Unverified
10ReACGANFID8.21—Unverified
#ModelMetricClaimedVerifiedStatus
1Projected GANFID11.84—Unverified
2BigGAN + CRFID4.65—Unverified
3StyleGAN2FID4.49—Unverified
4BigGAN + DiffAugFID4.06—Unverified
5ReACGAN + DiffAugFID3.18—Unverified
6StyleGAN2 + ADAFID2.63—Unverified
#ModelMetricClaimedVerifiedStatus
1MHingeGANFID17.3—Unverified
2aw-BigGANFID10.23—Unverified
3ADC-GANFID8.12—Unverified
4TAC-GANFID7.22—Unverified
5FQ-GANFID7.15—Unverified
6DLSMFID3.86—Unverified
#ModelMetricClaimedVerifiedStatus
1FQ-GANFID9.67—Unverified
2SAGAN + instance selectionFID9.07—Unverified
3IC-GAN + DAFID6.7—Unverified
#ModelMetricClaimedVerifiedStatus
1BigGANFID16.37—Unverified
2U-Net GANFID13.73—Unverified
#ModelMetricClaimedVerifiedStatus
1BigGAN+ [Brock et al.] (chx96)FID8.1—Unverified
2DiGITFID3.39—Unverified
#ModelMetricClaimedVerifiedStatus
1SCDMFID17.4—Unverified
#ModelMetricClaimedVerifiedStatus
1BigGAN + gSRFID12.03—Unverified
#ModelMetricClaimedVerifiedStatus
1StyleGAN2 + NoisyTwinsFID21.29—Unverified
#ModelMetricClaimedVerifiedStatus
1ADC-GANFID19.02—Unverified