Archives de catégorie : Conception

COMFYUI – AI for Architecture Case Study 01 : Render from basic 3D

Task

ComfyUI Tutorial for Architecture: From Sketch to Realistic Render with ControlNet Canny

If you want to transform a simple sketch or plan into a detailed and realistic architectural render, ComfyUI, with its modular structure, is the perfect tool for this. In this tutorial, we will explore a simple yet powerful workflow using ControlNet Canny to turn a basic drawing into a high-quality image.

This tutorial is designed for beginners with ComfyUI. We will walk through each step, from importing models to achieving the final result.

Continuer la lecture de COMFYUI – AI for Architecture Case Study 01 : Render from basic 3D

Grasshopper – Swordfish tutorial – 01

Introduction

Grasshopper

Grasshopper est un plugin de modélisation paramétrique pour Rhinoceros 3D. Il permet de générer des formes complexes à l’aide d’une approche visuelle basée sur des nœuds et des connexions, plutôt que par des scripts de programmation. Très utilisé en architecture, en design et en ingénierie, il offre une grande flexibilité pour la conception et l’optimisation des formes.

Swordfish

Swordfish est un outil de calcul et d’analyse spécialisé pour l’architecture navale. Il permet d’évaluer la stabilité, la résistance structurelle et la performance hydrodynamique des navires. Son intégration avec Grasshopper permet une approche paramétrique de la conception navale, facilitant l’exploration de multiples itérations et optimisations. A télécharger ici. Continuer la lecture de Grasshopper – Swordfish tutorial – 01

IA-project workflow part10

Image to 3D

Trellis

A novel 3D generation method is introduced, enabling versatile and high-quality 3D asset creation. At its core is a unified Structured LATent (SLAT) representation, which supports decoding into multiple output formats, including Radiance Fields, 3D Gaussians, and meshes. This is achieved by combining a sparsely-populated 3D grid with dense multiview visual features extracted from a robust vision foundation model, effectively capturing both structural (geometry) and textural (appearance) information while preserving decoding flexibility.

Structured 3D Latents for Scalable and Versatile 3D Generation (https://trellis3d.github.io/) Continuer la lecture de IA-project workflow part10