Tavi Halperin

[Yoav HaCohen @yoavhacohen]

LTX-Video Paper Release 🚀

1/ We’re thrilled to release our LTX-Video paper! 🎉
What makes LTX-Video so much faster than other video generation models? 🤔
The answer lies in our novel design choices, now explained in our just-released paper: https://t.co/Gn3Ocva20v.
A 🧵:

[Naomi Ken Korem @noamiKenKorem]

LongAnimateDiff: Our new AnimateDiff model that supports up to 64 frames!

We are excited to announce the launch of our advanced motion module, designed for long video generation.

This cutting-edge module, developed based on the #AnimateDiff model (v2) for Stable Diffusion, now enables video generation of up to 64 frames, surpassing the industry's current maximum of 25 frames set by @stability.ai's #SVD. Moreover, our model offers enhanced flexibility, allowing for a variety of video lengths ranging from 16 to 64 frames.

For creators and developers, the model is now available in #ComfyUI.

code: https://t.co/DochHCjKIr @HuggingFace: https://t.co/Khg3qrDlgJ

@s_weissbuch Daniel Shalem @yoavhacohen @ofirbb @Lightricks

[Tavi Halperin @davidhalpe]

@nomivin liked this one: A hamster is riding a bicycle on the road

[Tavi Halperin @davidhalpe]

@nomivin Amazing stuff!!

[Tavi Halperin @davidhalpe]

@photoleap_ai brick wall

[Tavi Halperin @davidhalpe]

@photoleap_ai beautiful mandala!

[AK @_akhaliq]

Endless Loops: Detecting and Animating Periodic Patterns in Still Images
project page: https://t.co/R3gClQ0A1J

[Tavi Halperin @davidhalpe]

@jaakkolehtinen @iiausk What's a good prefiltering before downsampling with area? I understand that it's not simply blurring with a gaussian

[Tavi Halperin @davidhalpe]

Vinyl episode listen party. Forgot that these records have two sides. Obviously started from side B. Didn't notice anything weird @BradyHaran

[Tavi Halperin @davidhalpe]

#timhotdrop hand made glass hotstoppers @BradyHaran @HelloInternetFM

[Seamless @shiropen2]

ヘブライ大学、動画内の口の動きに合わせて別音声を適合させる自動合成法を発表 https://t.co/1SBsyyclXv 動画では、入れ替わった男女の声を確認できます。