-
Notifications
You must be signed in to change notification settings - Fork 521
Add video-to-video task #1772
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
base: main
Are you sure you want to change the base?
Add video-to-video task #1772
Conversation
MrShahzebKhoso
commented
Sep 27, 2025
- Added about.md with a definition and summary of the task.
- Added data.ts with task metadata:
- Datasets (VIRESET, LongV-EVAL, SeedVR_VideoDemos)
- Models (e.g., Lucy-Edit-Dev, SeedVR2, Shape-for-Motion, etc.)
- Demo Spaces (lucy-edit-dev, SeedVR2-3B)
- Task summary describing scope and applications.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
very neat and thanks a ton for opening this PR!
these pages are targeted for devs to get started from scratch so let's explain a bit better and from scratch!
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks for the contribution! I agree with Merve's suggestions and just leaving a few additional minor nits :)
Co-authored-by: Merve Noyan <[email protected]>
Co-authored-by: Merve Noyan <[email protected]>
Co-authored-by: Merve Noyan <[email protected]>
Co-authored-by: Merve Noyan <[email protected]>
Co-authored-by: Merve Noyan <[email protected]>
Co-authored-by: Merve Noyan <[email protected]>
Co-authored-by: Merve Noyan <[email protected]>
Co-authored-by: Merve Noyan <[email protected]>
Co-authored-by: Sergio Paniego Blanco <[email protected]>
Co-authored-by: Sergio Paniego Blanco <[email protected]>
Thank you for considering this PR and taking time to review. Updated both the about.md and data.ts files based on all the helpful feedback from @merveenoyan and @sergiopaniego — thank you both for the detailed and thoughtful reviews. Really appreciate the guidance. Also added a Video Super-Resolution demo (low-res to high-res) via PR #10 Everything is now cleaned up, clarified, and aligned with the review suggestions. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
make sure that the changes reflect here: as well packages/tasks/src/tasks/index.ts
cc: @merveenoyan
Thanks for catching that, @Vaibhavs10! |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
thank you for re-iterating!
Thank you, @merveenoyan for the review. I have made the changes including:
|
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
thank you! we can merge after these ones are addressed
- [VIRES](https://github.com/suimuc/VIRES) - Implementation for sketch- and text-guided video instance repainting. | ||
- [ECCV2022-RIFE: Video Frame Interpolation](https://github.com/hzwer/ECCV2022-RIFE)- Real-time video frame interpolation via intermediate flow estimation. | ||
- [StableVSR: Enhancing Perceptual Quality in Video](https://github.com/claudiom4sir/StableVSR)- Super-resolution method to enhance perceptual video quality. | ||
|
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
we can remove these lines below
id: "ByteDance-Seed/SeedVR2-7B", | ||
}, | ||
{ | ||
description: "Framework that uses 3D mesh proxies for precise, consistent video editing.", |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
we try to add most used ones, let's exclude this
}, | ||
{ | ||
description: "Model for relighting videos by manipulating illumination distributions.", | ||
id: "TeslaYang123/TC-Light", |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
this one as well. would be nice to find more used ones