Hotshot is a generative AI company working on state of the art image and video generation since 2022.
Website | Technical Report | Model Evals |
A state-of-the-art, large-scale diffusion transformer text-to-video model that generates up to 10 seconds of footage at 720p.
It excels in prompt alignment, consistency, and motion, while being highly extensible to longer durations, higher resolutions, and additional modalities.
Website | Paper | Video |
Follow up to Hotshot-XL, but scaled up: trained to generate 3 second video at 8 fps for 24 frames total. Features higher resolution, improved coherence, and better pop culture knowledge.
Paired with an updated website featuring an all-new design and streamlined user experience.
GitHub | HuggingFace |
Hotshot’s first text-to-video model: open source and built on SDXL.
Trained to generate 1 second, 8 fps videos at 512x512 resolution.
Hotshot iOS was a free app that let you generate pictures of you and your friends.
On sign up you would scan you face and Hotshot would learn what you looked like in a few minutes. Using text-to-image prompts and a selection of styles, Hotshot would generate pictures of you and your friends doing anything you can imagine!