← Latest products

Lemon Slice Live

Have a video call with a transformer model. We’ve trained a custom diffusion transformer (DiT) model that achieves video streaming at 25fps and wrapped it into a demo that allows anyone to turn a photo into a real-time, talking avatar.

Visit news.ycombinator.comexternal site

Reactions (1)

Similar products

by description similarity

  1. Hotshot

    hotshot.co

    4 Person Team Builds a State of the Art Video Model

    Hacker News26 pts

  2. LemonSlice

    news.ycombinator.com

    Upgrade your voice agents to real-time video

    Hacker News133 pts

  3. DynamiCrafter

    github.com

    Animating open-domain images with video diffusion priors

    Hacker News40 pts

  4. less than 650 LOC trainable GPT only using NumPy

    github.com

    Absolute minimalistic implementation of a GPT-like transformer using only numpy (<650 lines).

    Hacker News90 pts

  5. Audio-to-Video with LTX-2

    magichour.ai

    LTX-2 is an open-source diffusion model that combines video and audio.

    Hacker News23 pts