BREAKING NEWS
LATEST POSTS
-
Quantum entanglement passes toughest test yet
It’s a bad day both for Albert Einstein and for hackers. The most rigorous test of quantum theory ever carried out has confirmed that the ‘spooky action at a distance’ that the German physicist famously hated — in which manipulating one object instantaneously seems to affect another, far away one — is an inherent part of the quantum world.
http://www.nature.com/news/quantum-spookiness-passes-toughest-test-yet-1.18255
-
Horizon Zero Dawn Are Truly Next-Generation clouds
http://kotaku.com/the-clouds-in-this-ps4-game-are-truly-next-gen-1726461687
[dailymotion x32wuz7_horizon-zero-dawn-time-lapse_videogames
-
18 Ways You are Making Your Life Harder Than It Has To Be
http://www.marcandangel.com/2014/07/27/18-ways-youre-making-your-life-harder-than-it-has-to-be/
You look to everyone else for the answers only you can give yourself.
You let others make you feel guilty for living your life.
You allow toxic people to get the best of you.
You are part of the drama circle.
You assign negative intent to other people’s actions.
You are too worried that people will steal what you have.
You’re trying to compete with everyone else.
You have been too much of a taker.
You focus on popularity over effectiveness.
You keep cutting corners and taking the easy way out.
You focus on every point in time other than now
You are stuck on your mistakes.
You have an “all or nothing” mentality.
You expect life to always be happy
You keep thinking about worst-case scenarios
You’re letting loss devour you
You avoid facing the truth
You put off making decisions
FEATURED POSTS
-
FramePack – Packing Input Frame Context in Next-Frame Prediction Models for Offline Video Generation With Low Resource Requirements
https://lllyasviel.github.io/frame_pack_gitpage/
- Diffuse thousands of frames at full fps-30 with 13B models using 6GB laptop GPU memory.
- Finetune 13B video model at batch size 64 on a single 8xA100/H100 node for personal/lab experiments.
- Personal RTX 4090 generates at speed 2.5 seconds/frame (unoptimized) or 1.5 seconds/frame (teacache).
- No timestep distillation.
- Video diffusion, but feels like image diffusion.
Image-to-5-Seconds (30fps, 150 frames)