anaksor-ocr
Sokheng · Kit
Reads Khmer and English text from documents, receipts and photos of signs, using a detector for text lines and a recogniser for each line. Suits developers who…
Turn a text description into an interactive 3D world, delivered as one HTML file that uses Three.js. A small coding model runs in your browser through WebGPU.
3D World Generator WebGPU is a kit in the Developer category, listed by Mindket. It is free. This is version 1, last updated on . Download it on this page, a zip of its files. Nothing in it runs by itself.
pip install -U huggingface_hub pip install gradio python app.py
This Space turns a text description into an interactive 3D world. The result is a self-contained HTML page built with Three.js, the JavaScript library for 3D graphics in the browser.
A 4B-size coding model named Qwen3.5-4B-3D-Coder writes that page. The Q4_K_M build of it runs in your browser through WebGPU and the wllama library, so the generating happens on your own device.
It suits people who want to turn an idea into a small 3D scene without writing the code, and developers who want to see an in-browser language model produce Three.js pages.
| Industry | Who uses it | How they use it | Example |
|---|---|---|---|
| Game development | Indie developers | Describe a scene and look at the generated world | Sketching a level idea before building it |
| Web development | Front-end developers | Use the generated HTML as a starting point | Studying how a Three.js page is laid out |
| Education | Teachers and students | Show how text becomes 3D code | Demonstrating what a small coding model can do |
| AI development | Developers | Read app.py to see how the Space loads the model | Trying the same approach with another model |
Skip it if you need detailed, production-ready 3D scenes, since a small model writes one page at a time.
The app runs in these places.
| Use case | Who | What they get back |
|---|---|---|
| Generate a 3D world from text | Anyone curious | An interactive Three.js page |
| Try the in-browser model | Developers | A language model running on WebGPU |
| Study the Space | Learners | A two-file repository with app.py and a README |
Online you only need a browser that supports WebGPU. A local copy needs these.
pip install -U huggingface_hub pip install gradio python app.py
Put your own value in its key setting first.
Open the Space's page, or run the command below in your copy and open the page the app serves. Then describe the 3D world you want and run it.
python app.py
You open the Space and describe a small scene, such as a field with a few trees. The app generates an interactive Three.js page for it, which you can look around in the browser.
If you are new, open the Space's page in a browser that supports WebGPU and describe a simple scene first. A short description keeps the model's job small.
If you know the field, the model is Qwen3.5-4B-3D-Coder in a split GGUF build, quantised to Q4_K_M and loaded by wllama. Inference runs on the client through WebGPU, so the server only hosts the page. The trade-off is a large model download on first use and a limit set by your device.
The repository has three files in all, with README.md and app.py at the top, and the Space is listed on zero-a10g hardware. The README says the model itself runs in your browser.
Turn a text description into an interactive 3D world, delivered as one HTML file that uses Three.js. A small coding model runs in your browser through WebGPU.
Made by ReallyFloppyPenguin on Hugging Face. These notes are Mindket's, written from its Space page and README; the app's own files and license are on Hugging Face.
What it is: This Space turns a text description into an interactive 3D world. The result is a self-contained HTML page built with Three.js, the JavaScript library for 3D graphics in the browser.
A 4B-size coding model named Qwen3.5-4B-3D-Coder writes that page. The Q4_K_M build of it runs in your browser through WebGPU and the wllama library, so the generating happens on your own device.
Who it suits: It suits people who want to turn an idea into a small 3D scene without writing the code, and developers who want to see an in-browser language model produce Three.js pages.
Industry | Who uses it | How they use it | Example
Game development | Indie developers | Describe a scene and look at the generated world | Sketching a level idea before building it
Web development | Front-end developers | Use the generated HTML as a starting point | Studying how a Three.js page is laid out
Education | Teachers and students | Show how text becomes 3D code | Demonstrating what a small coding model can do
AI development | Developers | Read app.py to see how the Space loads the model | Trying the same approach with another model
Skip it if you need detailed, production-ready 3D scenes, since a small model writes one page at a time.
Where to use it: The app runs in these places.
Use case | Who | What they get back
Generate a 3D world from text | Anyone curious | An interactive Three.js page
Try the in-browser model | Developers | A language model running on WebGPU
Study the Space | Learners | A two-file repository with app.py and a README
How to set it up: Online you only need a browser that supports WebGPU. A local copy needs these.
pip install -U huggingface_hub
pip install gradio
python app.py
Put your own value in its key setting first.
How to use it: Open the Space's page, or run the command below in your copy and open the page the app serves. Then describe the 3D world you want and run it.
python app.py
Example: You open the Space and describe a small scene, such as a field with a few trees. The app generates an interactive Three.js page for it, which you can look around in the browser.
For newcomers and experts: If you are new, open the Space's page in a browser that supports WebGPU and describe a simple scene first. A short description keeps the model's job small.
If you know the field, the model is Qwen3.5-4B-3D-Coder in a split GGUF build, quantised to Q4_K_M and loaded by wllama. Inference runs on the client through WebGPU, so the server only hosts the page. The trade-off is a large model download on first use and a limit set by your device.
Open the Space page in a WebGPU browser
Describe the 3D world in text
The model writes a Three.js HTML page
The world shows and you can explore it
Good to know: The repository has three files in all, with README.md and app.py at the top, and the Space is listed on zero-a10g hardware. The README says the model itself runs in your browser.
Open the Space in your browser, or copy it to your own Hugging Face account from its page. Nothing in this kit runs by itself.
README.md 4 KB
Listed Hugging Face Spaces in the same category that share the most tags with this one.
| Product | Likes | Built with | License | Last change |
|---|---|---|---|---|
| 3D World Generator WebGPU This page | 6 | gradio | apache-2.0 | |
| FLUX.1 [dev]Shares gradio | 9,583 | gradio | mit | |
| InstantIDShares gradio | 3,659 | gradio | apache-2.0 | |
| Chat With Janus-Pro-7BShares gradio | 2,036 | gradio | mit | |
| PhotoMakerShares gradio | 1,960 | gradio | apache-2.0 | |
| Z Image TurboShares gradio | 1,940 | gradio | apache-2.0 |
Sokheng · Kit
Reads Khmer and English text from documents, receipts and photos of signs, using a detector for text lines and a recogniser for each line. Suits developers who…
Qwen · Kit
Qwen2.5-7B-Instruct as GGUF files in eight quantization sizes, to chat with locally through llama.cpp. For people who want a capable 7.6B model on their own co…
ACE-Step · Kit
Generates music from text with a 4B diffusion decoder, 50 steps and guidance control, aiming for higher audio quality than the base. For creators with a GPU of…
alirezarezvani · Skill
Adds 411 ready-made skills for Claude Code and other coding agents, grouped by role from engineering and product to marketing, finance and compliance. Installs…
block · Kit
Self-hostable workspace where people and AI agents share the same rooms, built on a Nostr relay that logs every action as a signed event. For teams that want t…
backnotprop · Kit
Opens your AI coding agent's plans, specs and code changes in a browser so you can annotate or comment on them and send the feedback straight back to the agent.