Replying to @JasonKPargin
And smells. You smell
different to them. Way worse.
Jonathan Fischoff
29.9K posts
Jonathan Fischoff
@jfischoff
Computer person. AI @fal
- This paper is wild. Create a camera with cheap terrible camera lens, but train a diffusion model to recreate a much better image. arxiv.org/abs/2408.07541
- Replying to @toonhound and @JasonKParginDude I can smell you from here
- Replying to @CartoonsHateHerthe power dynamics are messed up because he can collect social security and she can’t
- Replying to @cloneofsimoI mostly see VCs bothered. They want to believe OpenAI, etc have a secret sauce that will ensure they have high margins forever. The space is fast moving and competitive, and they are not as clued in as researchers are, so were caught off guard.
- This is the most exciting paper I've read in a while. Alternate title could have been: "One weird trick to increase your depth map inference 200x." arxiv: arxiv.org/abs/2409.11355 github: github.com/VisualComputin… Let's go through the details 🧵 1/9
- Using Photoshop’s generative fill to extend star wars so it works vertically
00:00 - Replying to @HotForMootcan't believe he didn't laugh at that one
- Replying to @CartoonsHateHerReminds me when I was dating 12 years ago and I would ask girls who their celebrity crush was. Top answer by a long shot: Jack Black.
- “Animate Anyone” was released last night for making pose guide videos. Lets dive in. Paper: arxiv.org/abs/2311.17117 Project: humanaigc.github.io/animate-anyone/ 🧵1/
- Replying to @GarettJonesWasn’t Bohr ultimately embarrassed by his atomic model?
00:00- 🚨 Major FLUX training update! A week ago @fal dropped a bombshell with sub-five minute LoRA training. Today we doubled the speed. Same step count, same great quality, but now you can train a LoRA in 2-3 minutes. $2 for ~ 2 minutes. Best deal around.
