Mora
Mora copied to clipboard
Mora: More like Sora for Generalist Video Generation
Thank you for your great work! Do you have plans to open source training code, or inference code and checkpoint?
Good job!👍 Is the dataset required for training open source? If it's not open source, can you tell me how the dataset is made?😊
Thanks for your great work! When will you plan to release the whole inference pipeline of Mora?
Thanks for your contribution. I've been closely following the development of Mora and am very impressed with the work so far! I am particularly interested in the full inference pipeline...
I hope this message finds you well. I wanted to take a moment to discuss the code present in the ``` https://github.com/lichao-sun/Mora ``` GitHub repository. While I appreciate the effort...
I had an looking like this post: https://stackoverflow.com/questions/58468944/image-object-has-no-attribute-read So I change the notebook to allow the first frame to open differently. It's mostly a dirty trick in my opinion but...
Dear Authors, We have recently been working on extending videos using the Mora framework. Specifically, we have been following the techniques described in Mora's paper and implementing the stable-video-diffusion-img2vid-xt-1-1 (SVD)...
I tested it out, and generated a 5-second video where the first second of the video was smooth, but the rest of the video was the same frame repeated. https://github.com/user-attachments/assets/341523f6-816e-44aa-b0be-27ce34dfd3d1
I was able to run the code exactly Somehow getting bad quality outputs and are not matching with the repo results These are some outputs I got for Text-conditional image-to-video...
Cloning into 'Mora'... remote: Enumerating objects: 342, done. remote: Counting objects: 100% (271/271), done. remote: Compressing objects: 100% (233/233), done. remote: Total 342 (delta 76), reused 201 (delta 37), pack-reused...