AI Paper Atlas

Research map / Benchmarks / CelebA-HQ 256×256

CelebA-HQ 256×256 leaderboard

13 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on CelebA-HQ 256×256. Best FID: 3.15 (RDM, ICLR 2024).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

CelebA-HQ 256×256 · FID

13 papers, each with its best reported number for its own method; lower is better.

#FID ↓MethodPaperTopic
13.15RDMRelay Diffusion: Unifying diffusion process across resolutions for image synthesis
ICLR 2024 · Table: Unconditional CelebA-HQ
Autoregressive and latent generation
23.22ConPreDiffImproving Diffusion-Based Image Synthesis with Context Prediction
NeurIPS 2023 · Table: Evaluation results for
Autoregressive and latent generation
33.25StyleSwinStyleSwin: Transformer-Based GAN for High-Resolution Image Generation
CVPR 2022 · Main results table
GANs
44.62DiMSUMDiMSUM: Diffusion Mamba - A Scalable and Unified Spatial-Frequency Method for Image Generation
NeurIPS 2024 · text
Autoregressive and latent generation
55.48LDM w/ SMD
LDM
Soft Mixture Denoising: Beyond the Expressive Bottleneck of Diffusion Models
ICLR 2024 · Table: SMD improves LDM genera
Fast diffusion sampling
65.94Wavelet Diffusion + W-Generator
DDGAN
Wavelet Diffusion Models Are Fast and Scalable Image Generators
CVPR 2023 · CelebA-HQ 256×256 results tabl
Fast diffusion sampling
76.24Binary Latent Diffusion, 64 stepsBinary Latent Diffusion
CVPR 2023 · Table: unconditional image gen
Autoregressive and latent generation
86.91P2 (500step)
ADM
Perception Prioritized Training of Diffusion Models
CVPR 2022 · Table 2
Fast diffusion sampling
97.16UNCSN++ (RVE) + ST
UNCSN++ (RVE)
Soft Truncation: A Universal Training Technique of Score-based Diffusion Model for High Precision Score Estimation
ICML 2022 · Table: Performance comparisons
Fast diffusion sampling
108.76TFMQ-DM
LDM-4
TFMQ-DM: Temporal Feature Maintenance Quantization for Diffusion Models
CVPR 2024 · Table 2
Fast diffusion sampling
3 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.