ShineChen1024/MagicClothing

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

1543 stars · 154 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Official PyTorch implementation of Magic Clothing, a diffusion-based model for controllable garment-driven image synthesis (virtual try-on), published at ACM Multimedia 2024. It generates images of people wearing a reference garment, with optional face identity (IP-Adapter-FaceID) and pose (ControlNet-Openpose) conditioning, and ships Gradio demos.

Use cases

• generate images of a person wearing a specific garment
• virtual try-on from a clothing photo
• try on clothes while preserving a face identity from a portrait
• pose-controlled garment synthesis using a reference pose image
• run a virtual try-on demo locally with gradio
• research baseline for garment-driven image synthesis

When to choose

• you need research-grade virtual try-on with text-prompt control over the output
• you want face identity or pose conditioning in addition to the garment
• you want to reproduce or build on an academic paper's method

When to avoid

• you need a production-ready e-commerce try-on service with commercial licensing (license is non-standard)
• you lack a GPU and cannot run diffusion inference locally
• you need a simple hosted API rather than self-hosted model weights

Facets

library · maturity active

image-processing machine-learning deep-learning image-processing artificial-intelligence e-commerce python cross-platform virtual-try-on diffusion-models garment-driven-synthesis stable-diffusion ip-adapter controlnet gradio research-code gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="ShineChen1024/MagicClothing")