search

sled-group / InfEdit

[CVPR 2024] Official implementation of CVPR 2024 paper: "Inversion-Free Image Editing with Natural Language"
https://sled-group.github.io/InfEdit/
Other
242 stars 7 forks source link

Code release? #7

Closed ZhangYang-UCAS closed 3 months ago

ZhangYang-UCAS commented 6 months ago

good work！！！ your project looks very interesting, do you have a date for it's release?

SihanXU commented 6 months ago

Hi our code is currently available at https://huggingface.co/spaces/sled-umich/InfEdit/tree/main. For the GitHub version, we are still cleaning our code and will release the code soon.

Decem-Y commented 4 months ago

Hi our code is currently available at https://huggingface.co/spaces/sled-umich/InfEdit/tree/main. For the GitHub version, we are still cleaning our code and will release the code soon.

When will the train code resources be open-sourced?

SihanXU commented 4 months ago

It’s a training free method so I don’t think it’s possible to release any training code here🥲

Decem-Y commented 4 months ago

It’s a training free method so I don’t think it’s possible to release any training code here🥲

Thanks for your reply. About the training dataset, is there some suggested datasets to use?

Mars-tin commented 3 months ago

To train/finetune a diffusion model you will need your own text-image pair datasets. Our method is training-free and does not reply on any dataset. My personal recommendation is: https://github.com/timothybrooks/instruct-pix2pix