Been working on a short film for almost a month and keep having to redo it because AI tech just keeps getting better and better. Amazing what we can do locally now.
Another AI rendering test with my guardian/spider animation. Using CogVidX. The scene was animated in blender and I exported only the depth pass for this rendering.
Thanks to the Latent Consistency Model (LCM), we're nearing real-time image diffusion. I've made a simple MJPEG server for generation stream using diffusers img2img pipeline. It's really fun to play with it. Can't wait for the ControlNet version.
try it: https://t.co/Hf47hV4fl4
LooseControl was just released and it's so good! 🔥
It enables depth-map conditioned image generation, but unlike ControlNet, the 3D boxes enable less strict control with simple bounding boxes. And look at how stable it is across frames!
More examples (with code) below ⬇️⬇️
The state of Washington just eliminated the bar exam requirement to become a lawyer in the name of DEI. We’re now entering the post-woke era where anti-meritocratic policies have become so normalized they are met with eye rolls and shrugs instead of shock and outrage.
America is founded on merit. Meritocracy and “equity” are incompatible. Restore colorblind meritocracy.