Apple Releases Open Weights Video Model(starflow-v.github.io)
418 points by vessenes | 151 comments
Project page for STARFlow-V, Apple's end-to-end video generative model based on normalizing flows, with links to the paper and code.
#generative-models on Hacker News
9 stories tagged generative-models, newest first.
Show HN: I invented a new generative model and got accepted to ICLR(discrete-distribution-networks.github.io)
625 points by diyer22 | 86 comments
Project page for Discrete Distribution Networks, an ICLR 2025 paper proposing a generative model that outputs multiple samples per forward pass to approximate distributions.
SimpleFold: Folding proteins is simpler than you think(github.com)
453 points by kevlened | 126 comments
GitHub repository from Apple for SimpleFold, a protein folding model accompanying an arXiv paper.
LegoGPT: Generating Physically Stable and Buildable Lego(avalovelace1.github.io)
530 points by nkko | 135 comments
Project page for LegoGPT, a Carnegie Mellon research model that generates physically stable, buildable LEGO structures from text prompts, with paper, code, and demo links.
NeuralSVG: An Implicit Representation for Text-to-Vector Generation(sagipolaczek.github.io)
726 points by lnyan | 69 comments
Project page for NeuralSVG, a research method from Tel Aviv University and MIT CSAIL that generates layered SVG vector graphics from text prompts using an implicit neural representation.
Trellis – 3D mesh generative model(trellis3d.github.io)
400 points by tarr11 | 75 comments
Project page for TRELLIS, a Microsoft Research, Tsinghua, and USTC method using structured 3D latents for scalable, versatile 3D asset generation.
Diffusion models from scratch, from a new theoretical perspective(chenyang.co)
342 points by jxmorris12 | 36 comments
A tutorial blog post by Chenyang Yuan explaining diffusion models from scratch through a new theoretical perspective.
Generative Models: What do they know? Do they know things? Let's find out(intrinsic-lora.github.io)
330 points by corysama | 106 comments
Project page for a research paper from TTIC and Adobe probing whether generative image models encode intrinsic scene properties like normals, depth, albedo and shading.
MeshGPT: Generating triangle meshes with decoder-only transformers(nihalsid.github.io)
684 points by jackcook | 148 comments
Project page for MeshGPT, a research paper from TU Munich, Politecnico di Torino and Audi that generates triangle meshes using decoder-only transformers.