(ICLR 2025) Qihoo-T2X

This is the official reproduction of Qihoo-T2X, which represents a groundbreaking DiT architecture paradigm designed for Text-to-Any tasks.

QIHOO-T2X: AN EFFICIENT PROXY-TOKENIZED DIFFUSION TRANSFORMER FOR TEXT-TO-ANY-TASK
Jing Wang*, Ao Ma*†, Jiasong Feng*, Dawei Leng‡, Yuhui Yin, Xiaodan Liang‡(*Equal Contribution, †Project Lead, ‡Corresponding Authors)

📰 News

• [2025.02.11] 🔥 We have open-sourced our model and inference code in Ascend/MindSpeed-MM.
• [2025.01.22] 🔥 Our paper has been accepted for presentation at ICLR 2025.
• [2024.09.12] We created a project homepage featuring galleries for Qihoo-T2X

We Are Hiring

We are seeking academic interns in the AIGC field. If interested, please send your resume to [email protected].

BibTeX

@misc{wang2024qihoot2xefficiencyfocuseddiffusiontransformer,
                title={Qihoo-T2X: An Efficiency-Focused Diffusion Transformer via Proxy Tokens for Text-to-Any-Task}, 
                author={Jing Wang and Ao Ma and Jiasong Feng and Dawei Leng and Yuhui Yin and Xiaodan Liang},
                year={2024},
                eprint={2409.04005},
                archivePrefix={arXiv},
                primaryClass={cs.CV},
                url={https://arxiv.org/abs/2409.04005}, 
}