Spline is a free 3D design software that allows you to create interactive web experiences. With Spline, you can design, animate, and integrate 3D objects into your web pages. This tool is perfect for adding a new dimension to your projects and engaging users with interactive elements. - Source: dev.to / 4 days ago

Before UX, I was an Industrial Designer. I used Solidworks and KeyShot (and some Unreal Engine for Arch Viz). If you don't plan on doing Arch Viz or serious ID, then you should look at other 3D programs that's easier to learn. Check out: https://spline.design/, Adobe's (I forgot which one), or Vectary. I personally prefer Spline. I haven't touched it in awhile though cos I have been coding more lately. Source: 7 months ago

You could start with Spline right from a web browser for free. It’s fairly new but very approachable for a total 3D newbie and you could offer your work to web builder who need to inject 3D into their websites with ease, and you can export AR experiences for iOS devices. Then you can move up to Blender to create more complex scenes. https://spline.design. Source: 11 months ago

I just started making 3d models and stumbled upon https://spline.design/, this thing is like the Figma of 3D but it paid and I cannot export my models, I have a shitty low-end laptop but it works well (i3 10 gen, 8GB, and SSD) please recommend a tool that has the same functionality keeping in mind my restraints. (I just want to make 3d assets for websites or games and export them in gltf, glb, stl formats). Source: about 1 year ago

It's just a cool tech demo that pushes CSS to its limits, but it's completely useless if you want to create usable 3d models. If you want to model in the browser, you can check out vectary, playcanvas, or spline. Source: about 1 year ago

3. Minimize cross-entropy loss between predicted and actual next tokens. (This is equivalent to trying to minimize encoding length.) ViT don't have quantization baked into the algorithm, but NNs are being moved towards quantization in general. ----- I think it's pretty interesting how closely related generation and compression are. ClosedAI's Sora[^1] model uses a denoising vision transformer, and is the... - Source: Hacker News / about 2 months ago

Did you miss the fish?[0] You should see the error in first viewing What about the woman with glasses? Her face literally "jumps"[1] Same with this guy's hands[2] Interesting, we notice that [1] has "sora" in the name though I think it is a reference to the main image on sora[3] Not sure if the gallery is weird to anyone else, but it doesn't exactly show new images and the position indicator is wonky. The thing... - Source: Hacker News / 2 months ago