Repository navigation
Model Timeline聽#3
Description
Activity
@metildachee
Thanks for your interest to our work. It will be ready in about one month.Reacted by metildachee@iFighting Got it, thanks so much for your hard work, looking forward! 馃殌
@metildachee Thank you for your interest in our work! The model锛宱nline demo, and evaluation scripts have already been released, and the training code will be released within a week. Welcome to try them out!
Yes I've just seen it, its really fantastic! May I please enquire if you have the script(s) for in-image modification? I.e. this particular example in the paper. Thanks so much and looking forward! 馃槉
Reacted by Ben CaffeeReacted by Haochen Wang@metildachee looking forward for the training code.
Yes I've just seen it, its really fantastic! May I please enquire if you have the script(s) for in-image modification? I.e. this particular example in the paper. Thanks so much and looking forward! 馃槉
Thank you for your attention! Currently, the released model has only been trained for text-to-image generation and does not possess image editing capabilities. We are considering releasing a version of the model that has been fine-tuned for image-to-image tasks in the future. Stay tuned for updates! 馃殌
Reacted by metildachee@metildachee looking forward for the training code.
Thank you for your attention! We have already released the data preprocessing and pretraining code. The code for multi-resolution training and SFT will be released soon.
Reacted by metildachee@metildachee looking forward for the training code.
Thank you for your attention! We have already released the data preprocessing and pretraining code. The code for multi-resolution training and SFT will be released soon.
@wjf5203 hello, any update for sft code release ? thank u ~~
Dear authors,
Fascinating piece of work! 馃槉 Was wondering if the authors have decided on the approximate release timeline for model and code? Thank you in advance!