🔥 News

2024.10: We propose an iterative feedback learning method to enhance compositionality in a closed-loop manner, enabling the progressive self-refinement of both the base diffusion model and reward models over multiple iterations.paper:https://arxiv.org/abs/2410.07171 , code:https://huggingface.co/comin/IterComp
2024.09: 🎉 Our papers is accepted by Neurips2024. code:https://github.com/YangLing0818/RealCompo
2023.11: 🎉 Our papers is accepted by AAAI 2024
2023.10: 🎉 Our papers is accepted by WACV 2024
2023.4: 🔥 We have released a more controllable AIGC product named Promeai : www.promeai.com where you can fully unleash your creativity . If you are interested in this and would like to learn more about us, or if you have any feedback, you can send me an email. We welcome discussions ~