@0xCheshire: Another open-source toolkit for converting photos to Three.js models: img2threejs. It continuously compares the rendering result with the original image to automatically calibrate reconstruction quality, especially suitable for hard-surface objects like machinery, equipment, and product casings. It seems everyone is working on similar directions. However, I'm more curious about when AI will be able to...
Summary
Introduces a new open-source toolkit, img2threejs, that converts photos into Three.js models and automatically compares the rendering result with the original image to calibrate reconstruction quality, especially suitable for hard-surface objects.
View Cached Full Text
Cached at: 07/20/26, 01:28 PM
Another open-source toolkit for converting photos into Three.js models: img2threejs.
It continuously compares the rendering result with the original image and automatically calibrates the reconstruction quality, making it especially suitable for hard-surface objects like machinery, equipment, and product casings.
Seems like everyone is working in a similar direction.
But what I care more about is: when will AI be able to model a 3D character with bones from a single sentence? https://x.com/NickDevFE/status/2078380705504166272/video/1…
Cheshire🔔|Crypto+AI Plus (@0xCheshire): 3D modelers are about to lose their jobs.
This person used GPT-5.6 Sol to create a skill:
Just throw any photo at it, and it directly reverse-engineers the objects in the image into a 3D model built entirely with code.
The effect is shown in the video, and the project is fully open source.
Completely free.
Similar Articles
@servasyy_ai: Bros! As promised, the open-source release is here tonight. Currently, the image-to-3D model integration supports only the online service: http://tripo3d.ai. You can also modify it to use other providers or local models. Don’t forget to like and follow, and if you find it useful, drop a star on GitHub: https://github.com/hu…
The developer announces the open-sourcing of an image-to-3D model tool that currently integrates with the Tripo3D API, encouraging users to adapt it for other services or local models.
@Saccc_c: To provide a more intuitive overview of my valuable AI outputs, I've pinned this long post for my followers and clients to view. It will be updated regularly. Current key outputs include: 1) 360-degree panoramic images created with Image 2.0 + Three.js; 2) Videos created with Image 2.0 + Seedance…
This post introduces a collection of AI outputs created by the author using tools such as Image 2.0, Three.js, Seedance 2.0, and Codex/Claude Code, aiming to showcase their current primary work.
@NickDevFE: img2threejs v1.3 is now available. One photo → procedural Three.js code. No meshes. No manual modeling. GitHub: https:/…
img2threejs v1.3 is a tool that converts a single photo into procedural Three.js code without meshes or manual modeling, with major improvements to geometry reconstruction and material generation.
@op7418: https://x.com/op7418/status/2074728162018152817
The user released an open-source AI illustration skill called guizang-material-illustration, based on GPT-Image 2.0 and Codex Agent, which can generate 3D material explanation diagrams with Chinese labels, suitable for articles, weekly reports, PPTs, etc.
@axichuhai: This free and open-source 3D motion capture tool, freemocap, has garnered 9K stars on GitHub. No professional capture equipment needed, just a few ordinary cameras. It transforms multi-view geometry problems into computer vision tasks, using spatial calibration algorithms + deep learning models to extract precise 3D human skeleton data from 2D footage of multiple ordinary cameras…
Freemocap is a free and open-source 3D motion capture tool. It requires only ordinary cameras to reconstruct precise 3D human skeleton data using spatial calibration and deep learning models, supporting multiple export formats.