* Equal contributions, ✦ Corresponding Author
Official code of "ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment".
- [2024.3.11] 🔥 Release DPG-Bench! Welcome to try!
- [2024.3.7] Initial update
The guideline of DPG-Bench:
-
Generate your images according to our prompts.
It is recommended to generate 4 images per prompt and grid them to 2x2 format. Please Make sure your generated image's filename is the same with the prompt's filename.
-
Run the following command to conduct evaluation.
bash dpg_bench/dist_eval.sh $YOUR_IMAGE_PATH $RESOLUTION
Thanks to the excellent work of DSG sincerely, we follow their instructions to generate questions and answers of DPG-Bench.
🥹 We are sorry that due to our company's review process, the release of the checkpoint and inference code will be slightly delayed. We appreciate your patience and PLEASE STAY TUNED.
- release checkpoint
- release inference code
- release DPG-Bench
We have also found LaVi-Bridge, another independent but similar work completed almost concurrently, which offers additional insights not covered by ELLA. The difference between ELLA and LaVi-Bridge can be found in issue 13. We are delighted to welcome other researchers and community users to promote the development of this field.
If you find ELLA useful for your research and applications, please cite us using this BibTeX:
@misc{hu2024ella,
title={ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment},
author={Xiwei Hu and Rui Wang and Yixiao Fang and Bin Fu and Pei Cheng and Gang Yu},
year={2024},
eprint={2403.05135},
archivePrefix={arXiv},
primaryClass={cs.CV}
}