ML Research Wiki / Benchmarks / Text-to-Image Generation / Conceptual Captions

Conceptual Captions

Text-to-Image Generation Benchmark

Performance Over Time

📊 Showing 5 results | 📏 Metric: FID

Top Performing Models

Rank Model Paper FID Date Code
1 Contextual RQ-Transformer Draft-and-Revise: Effective Image Generation with Contextual RQ-Transformer 9.80 2022-06-09 -
2 RQ-Transformer Autoregressive Image Generation using Residual Quantization 12.33 2022-03-03 📦 kakaobrain/rq-vae-transformer 📦 lucidrains/magvit2-pytorch 📦 ai-forever/movqgan 📦 archinetai/bitcodes-pytorch
3 LDM-4 High-Resolution Image Synthesis with Latent Diffusion Models 17.01 2021-12-20 📦 compvis/stable-diffusion 📦 labmlai/annotated_deep_learning_paper_implementations 📦 stability-ai/stablediffusion
4 Image-BART ImageBART: Bidirectional Context with Multinomial Diffusion for Autoregressive Image Synthesis 22.61 2021-08-19 📦 compvis/imagebart
5 VQ-GAN Taming Transformers for High-Resolution Image Synthesis 28.86 2020-12-17 📦 CompVis/taming-transformers 📦 alibaba/EasyNLP 📦 dome272/VQGAN

All Papers (5)