awesome-text-to-image-studies

Why we included this project

Anyone starting out in text-to-image generation will get more from this than from a bare list of links, because the papers are actually organized. Entries are grouped by research direction, publication year, and venue, so you can trace how diffusion-based image synthesis developed through the major vision conferences, or jump straight to a narrower thread like Diffusion Transformers, LLM-integrated diffusion, or Mamba-based methods. A separate topics section covers adjacent work, such as diffusion models applied to other tasks or combined with federated learning, which helps you see where the field's boundaries sit. It is a curated reading guide rather than software, so think of it as a map for assembling your own literature review and reference list, not something to deploy.