@TomLikesRobots @nptacek @EMostaque What we really need to figure out is how to generate the “back” portion of the object in a way that is both consistent with the front and merges with it gracefully.

RT @TomLikesRobots: Simple Stable Diffusion to Blender:
1. Use Automatic1111’s depth map extension (https://t.co/3i4QhbvAV8) to create imag…

Now. How would George Orwell look in a movie by Wes Anderson?

Like this. At least according to #stablediffusion2.

(yes, it’s impressive, thanks to @wavymulder’s Analog Diffusion fine tuning. No inpainting, no photoshop.) https://t.co/SUDdLoxZeJ

@scale_AI As a former industry analyst, I can say with absolute certainty: 53 questions is *a lot* of questions.

RT @percyliang: 📣 CRFM announces PubMedGPT, a new 2.7B language model that achieves a new SOTA on the US medical licensing exam. The recip…

RT @sama: “AI needs to do whatever i ask” and “i asked the AI to be sexist and it was, look how awful!” are incompatible positions.

somewh…

This is SO good. Thanks to the @carperai team for sharing this invaluable library. https://t.co/MbBB7S1gTD

I don’t understand. You guys only like “fail fast” when it’s about software development?

RT @0xgaut: how did we let this happen https://t.co/W4tUrsaYkc

“There is only one way, that we know of, to discern falsehoods from truths, one way to see if our model of the world has errors. That method is to actively seek evidence that contradicts our beliefs.”

A Thousand Brains (Jeff Hawkins)