diffusion
4 lessons tagged diffusion: free, quiz-checked micro-lessons.
Native 3D Generative Models: MeshGPT, Trellis, Hunyuan3D
The shift from 2D-lifting to native 3D generation. Autoregressive mesh transformers (MeshGPT, MeshAnything) and flow-matching latent models (Trellis, Hunyuan3D-2, TripoSG). Architectures, tokenization, conditioning, and which ones are actually usable in 2026.
How Image- and Text-to-3D Actually Works in 2026
The end-to-end production pipeline behind Meshy, Tripo, Rodin, and the open-source SOTA: multi-view diffusion, feed-forward reconstruction, mesh extraction, and the failure modes that still bite. Names the models, not just the concepts.
AI Texturing and PBR for Generated Meshes
How modern 3D generation paints a mesh after it's built. UV unwrapping, multi-view diffusion for texture, view-consistency, PBR map decomposition, and the workflow Meshy and Tripo expose to users in 2026.
Video generation models: Sora, Veo, Runway, and what they actually do
How diffusion-based video models turn a text prompt into a moving image, why consistency is so hard, and the practical patterns you need to know before generating anything longer than a few seconds.