它为实现数字永生和AI克隆提供了实用基础，能够从一张照片自动生成可定制的3D人体数字容器。
Your next life begins with an upload.
This application is a Python-based web API designed to procedurally generate 3D bodies and avatars. It leverages a headless instance of Blender in combination with the MPFB2 (MakeHuman Plugin for Blender) plugin to construct these assets, with the entire pipeline containerized within Docker for seamless deployment.
Since the application is fully containerized, you do not need to install Blender or Python locally. Ensure you have Docker and Docker Compose installed on your system (e.g., Debian, Ubuntu, or your preferred Linux distribution).
git clone [https://github.com/Yvonta/body-factory.git](https://github.com/Yvonta/body-factory.git)
cd body-factory
docker build -t yvonta-body-factory .
docker run -d -p 8090:8090 --name body-factory yvonta-body-factory
The API will now be accessible at http://localhost:8090.
The application exposes a RESTful web API that generates .glb 3D models from face images and applies fitted clothing to the generated avatars.
Submit a face image alongside macro parameters (gender, age, weight) to generate the base body. The API returns the 3D .glb file and provides a unique X-Avatar-Id in the response headers for future modifications.
curl -sS -D headers.txt -o avatar.glb \
-F "gender=0.0" \
-F "age=0.4" \
-F "weight=0.5" \
-F "file=@path/to/face.jpg" \
"http://localhost:8090/v1/avatar/generate"
Check headers.txt for your X-Avatar-Id.
Using the X-Avatar-Id returned in step 1, you can request specific garments. The API runs a headless Blender process to fit the clothing to your exact avatar's proportions and caches the result for near-instant subsequent requests.
curl -sS -o clothing_1.glb \
"http://localhost:8090/v1/avatar//clothing/toigo_basic_tucked_t-shirt"
*Tip: You can load both avatar.glb and clothing_1.glb together into a viewer like glTF Viewer to verify that the garment lines up
Your next life begins with an upload
根据分类、Topic 和编程语言匹配的相似项目。
Harness Engineering is a methodology for improving coding agent outputs by carefully crafting the environment around them—providing curated context, tools, and executable constraints that encode an organization’s nonfunctional requirements and cumulative lessons.
A 28.9 million parameter language model runs on an $8 ESP32-S3 microcontroller entirely on-device, generating simple stories at about 9.5 tokens per second.
mimic captures traffic from any iOS or web app and automatically generates a Python client library that lets you call the app's API like a regular library.