Yutong-Zhou-cv/Awesome-Text-to-Image

Curated collection of papers, datasets, evaluation metrics, and implementation resources organized across text-to-image synthesis subtasks including face generation, image editing, and domain-specific applications. Covers diffusion models, GANs, transformer-based architectures, and vision-language approaches like CLIP integration. Maintains chronological and topic-organized paper lists with code implementations, alongside benchmarking datasets (MS-COCO, CelebA-HQ) and quantitative metrics (FID, Inception Score, LPIPS).

2,430 stars.