Idol turns one image into a 3D model in 14.5 s on my RTX 5090. A 16 GB RTX 5060 Ti does…
This is a dev post classified by AGK Intelligence as Other (a tool drop), kept by the Dev Radar because it carries real work, not commentary.
This is so cool! Idol turns one image into a 3D model in 14.5 s on my RTX 5090. A 16 GB RTX 5060 Ti does it in 57.4 s. RTX 5090 (32 GB): Per image, 262,144 Gaussians: 14.5 s Per image, 1,048,576 Gaussians: 15.1 s First image, compile included: 22.1 s Peak VRAM: 7.5 GiB RTX 5060 Ti (16 GB): Per image, 262,144 Gaussians: 57.4 s Per image, 1,048,576 Gaussians: 59.8 s First image, compile included: 73.3 s Peak VRAM: 7.0 GiB Output: a 3D Gaussian splat Steps: 50 Seed: 42 Fast path: the author's default (torch.compile, batched guidance, cuDNN attention, TF32) Precision: mostly FP16 and bf16, s
Posted by Niklas (2.3k followers) 1 h ago · 12 likes · 577 views · view the original post on X. Kept by the Dev Radar as Other.
More dev work like this
- So ... this isn't even the real game, just a combat PoC — @ryanflorence
- Understanding Self Organizing Map Neural Network. #BigData #Analytics #DataScience #AI… — @gp_pulipaka
- Explaining XGBoost! #BigData #Analytics #DataScience #AI #MachineLearning #IoT #IIoT… — @gp_pulipaka
- Innovations and Advances in Cognitive Systems! #BigData #Analytics #DataScience #AI… — @gp_pulipaka
- Artificial Intelligence and Quantum Computing! #BigData #Analytics #DataScience #AI… — @gp_pulipaka
- AlpineBSD is building a free operating system with a strict ban on AI-generated code. — @twtayaan
- 做闲鱼虚拟货源的，多半都被手动发货折磨过。 — @bkdgiffug
- 3D pixel games with Claude Opus 5.5 (OS) — @AmirMushich
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 31.2k posts from 5k X accounts over the last 21 days, 8.9k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-10-31 15:57 UTC. Full method.