Run Hunyuan3D TURBO Locally (NVIDIA GPU) These AI models are super fast indeed! Depending on machine (details in thread) it takes: - Mesh Generation: just 1~5sec - Mesh + Texture Generation: 30~100sec And now, the Hunyuan3D-GP gradio app supports them. Run on your PC!
We are thrilled to announce a 30x acceleration in white model generation speed across the entire Hunyuan3D 2.0 family, reducing the processing time from 30 seconds to just 1 second. pic.twitter.com/wYWSKVvj2e
— Hunyuan (@TencentHunyuan) March 19, 2025
New users: get it on https://t.co/Nq7yThvSpD Existing users: click "update" WHen you update, you should see a nested menu that lets you pick either the original model or the turbo model. Pick turbo.
RTX 4090 results (via @deepbeepmeep) mini-turbo - mesh only: 1.7sec - mesh+texture: 32sec original-turbo - mesh only: 2.4sec - mesh+texture: 34sec
4070Ti (12GB VRAM) / 32GB RAM (via Morpheus) mini-turbo - mesh only: 3 sec - mesh + texture: 44 sec mv-turbo (multi view) - mesh only: 5 sec - mesh + texture: 31 sec original-turbo: - mesh only: 5 sec - mesh + texture: 44 sec