@FinanceYF5: No 3D models, no textures, not even audio files—just code can generate a soothing meadow like this. Developer Glitter Gal created a dynamic meadow scene with Three.js, featuring 186,000 blades of grass, wildflowers, gentle breezes, and birdsong. The entire project in Google Ant…

X AI KOLs Following News

Summary

Developer Glitter Gal used Three.js to generate a soothing, animated meadow scene entirely in code, featuring 186,000 blades of grass, wildflowers, gentle breezes, and birdsong, with no 3D models, textures, or audio files used at any stage. The project was orchestrated by Gemini 4 Carbon in Google Antigravity.

No 3D models, no textures, not even audio files—just code can generate a soothing meadow like this. 🌿 Developer Glitter Gal created a dynamic meadow scene using Three.js, featuring 186,000 blades of grass, wildflowers, a gentle breeze, and birdsong. The entire project was completed in Google Antigravity, with Gemini 4 Carbon handling agent orchestration alongside Swarm collaboration. From grass blades swaying in the wind to natural ambient sounds, everything is generated through mathematical calculations and code.
Original Article
View Cached Full Text

Cached at: 11/19/26, 03:42 PM

No 3D models, no textures, not even audio files—just code can generate a soothing meadow like this. 🌿

Developer Glitter Gal created a dynamic meadow scene with Three.js, featuring 186,000 blades of grass, wildflowers, a gentle breeze, and birdsong.

The entire project was completed in Google Antigravity, with Gemini 4 Carbon handling agent orchestration alongside Swarm collaboration.

Everything, from the grass swaying in the wind to the ambient sounds of nature, is generated through mathematical calculations and code.

Similar Articles

@FinanceYF5: In just one year, AI-generated 3D scenes using Three.js have evolved from crude low-poly graphics to visuals rivaling AAA games. Developer Scott shared a set of comparison images: a year ago it was simple deserts, palm trees, and geometric models; today it can render detailed Chinese architecture, complex lighting...

X AI KOLs Timeline

A set of comparison images shared by developer Scott shows that in just one year, AI-generated 3D scenes using Three.js have evolved from crude low-poly graphics to visuals rivaling AAA games, featuring detailed Chinese architecture and cinematic lighting.

@FinanceYF5: A Chinese open-source model can reconstruct 3D scenes in real-time from any video. Just one camera, no LiDAR needed, handles over 10,000 frames without crashing, and runs at 20fps on a single GPU. Its benchmark scores surpass traditional optimization-based methods, tested on drone aerial photography, dashcams, and indoor tours. And it's fully open-source.

X AI KOLs Timeline

A Chinese open-source model reconstructs 3D scenes in real-time from a single camera video, no LiDAR required, achieves 20fps on a single GPU with performance superior to traditional optimization methods. Fully open-source.

@oragnes: Wow, just dug up this amazing tool map3d on GitHub! Based on OpenStreetMap, you select an area on the web page, and it automatically fetches real building and road data, rendering a 3D city model with heights in one click! The craziest part is it can directly export GLB files for use in Blender or game engines…

X AI KOLs Timeline

Introduces two open-source tools on GitHub: map3d, which automatically generates 3D city models from OpenStreetMap and exports GLB files; and Voice-Pro, a local tool integrating video download, voice separation, subtitle recognition, translation, voice cloning dubbing, and video synthesis.

@FinanceYF5: One sentence to Fable 5: Write a single-file HTML that creates a realistic American flag fluttering in the wind. It directly outputs 644 lines of code, with the flag's folds, lighting, and fluttering rhythm all correct, done in one pass without back-and-forth modifications.

X AI KOLs Timeline

Fable 5 model generates a 644-line single-file HTML from a one-sentence description, achieving a realistic American flag fluttering effect including folds, lighting, and rhythm, all in one shot without any revision, demonstrating the AI's capability in complex code generation.