Cusuh @cusuh_

Research Scientist @ Adobe | ML PhD from Georgia Tech | previously Google Research, MPI cusuh.github.io Joined April 2010

Tweets

136
Followers

880
Following

200
Likes

895

AK @_akhaliq

7 months ago

MotionCanvas Cinematic Shot Design with Controllable Image-to-Video Generation

1 7 41 12K 28

Download Video

I've had so much fun experimenting with our latest @Adobe Firefly Video model - coming from a background in film, I've loved exploring the world of generative cinematography. A few of my favorite shots:

1 3 7 4K 2

Download Video

Adobe Video & Motion @AdobeVideo

a year ago

We’re excited to share progress on the all-new Firefly Video Model with Text to Video & Image to Video capabilities across @creativecloud, @AdobeExpCloud & @AdobeExpress workflows - all designed to be commercially safe & available in beta later this year. adobe.ly/4eebxFi

3 8 27 7K 7

Aseem Agarwala @aseemaa

a year ago

After a nearly 20 month journey we are finally going public with our work on video generative models at Adobe! This work started in Adobe Research and then became a collaboration with the Adobe Firefly team who brought it over the finish line. Super proud of everyone involved,

1 1 8 581 1

Cusuh @cusuh_

a year ago

I'll be presenting our work tomorrow (6/19) 5-630pm in Arch 4A-E (poster #329)! #CVPR2024

Cusuh @cusuh_

a year ago

I'll be presenting our work tomorrow (6/19) 5-630pm in Arch 4A-E (poster #329)! #CVPR2024

2 6 21 6K 5

Download Image

1 3 22 4K 1

AK @_akhaliq

a year ago

Personalized Residuals for Concept-Driven Text-to-Image Generation We present personalized residuals and localized attention-guided sampling for efficient concept-driven generation using text-to-image diffusion models. Our method first represents concepts by freezing the