search

YangRui2015 / RiC

Code for the ICML 2024 paper "Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment"
48 stars 4 forks source link

Code related to Stable Diffusion #12

Open EvaFlower opened 1 month ago

EvaFlower commented 1 month ago

Hi, interesting work.

I wonder if you will release the code of the text-to-image task in the near future?

I am interested in reproducing the results on that part. How do you incorporate the condition of rewards into Stable Diffusion?

Best,

YangRui2015 commented 1 month ago

Thank you for your interest in our work. The implementation details are in Appendix C.1. We also have updated the code in the ric_txt2img directory.

EvaFlower commented 1 month ago

Thanks for your update. I will look into them.

EvaFlower commented 1 month ago

Hi,

I have looked into the code. May you provide the file indicated in the train.sh export TRAIN_JSON="/mnt/aigc_cq/private/amandaaluo/dataset/multi_obj/multi_obj_with_clip_base.json".

Also, I wonder if you could release your trained model checkpoints for ease of evaluation.

Best,

YangRui2015 commented 1 month ago

@amandaluof will have a look into this soon.

amandaluof commented 4 weeks ago

Hi,

I have looked into the code. May you provide the file indicated in the train.sh export TRAIN_JSON="/mnt/aigc_cq/private/amandaaluo/dataset/multi_obj/multi_obj_with_clip_base.json".

Also, I wonder if you could release your trained model checkpoints for ease of evaluation.

Best,

Thanks for your attention. We have released our checkpoint and give an instruction in README.md.