This repository is a curated collection of papers and resources focused on controllable generation using diffusion models, specifically addressing techniques for adding conditional controls to text-to-image (T2I) diffusion models. It serves researchers and practitioners in the field of AI-generated content (AIGC) by providing a centralized, up-to-date overview of advancements like ControlNet, DreamBooth, and IP-Adapter.

How It Works

The repository functions as a living bibliography, categorizing research papers by year and providing links to their project pages, official papers, and code repositories. It highlights key advancements in adding conditional controls to diffusion models, enabling more precise and nuanced image generation based on various inputs beyond text prompts.

Quick Start & Requirements

This is a curated list of research papers and resources, not a runnable software project. No installation or execution is required.

Highlighted Details

• Comprehensive coverage of controllable diffusion techniques, including instance-level control, style adaptation, and multi-concept customization.
• Features prominent methods such as ControlNet, DreamBooth, IP-Adapter, StyleDrop, and GLIGEN.
• Organizes papers by year (2023, 2024, and upcoming 2025), facilitating tracking of recent developments.
• Includes links to project pages, papers, and code for most listed research.

Maintenance & Community

The list is maintained by Armando Fortes and welcomes community contributions for adding new papers or updating existing entries. It also links to other relevant "Awesome Lists" in AI research.

Licensing & Compatibility

The repository itself is not software and does not have a license. The linked papers and code repositories will have their own respective licenses.

Limitations & Caveats

This is a reference list and does not provide any implementation or tooling. Users must refer to individual paper repositories for code, dependencies, and usage instructions.