A new open-source tool called Paperdoll has been developed for local-first character customization, primarily aimed at visual novel and indie game developers. The pipeline extracts body and wardrobe layers from character images, allowing users to mix and match outfits. It then uses an AI pipeline to generate new garments, tagging them by slot (e.g., topwear, bottomwear) and running without cloud services or GPU rentals on systems with as little as 16GB of memory. The approach focuses on per-garment generation and utilizes Stable Diffusion 1.5, a 19-class anime SAM, and IP-Adapter. AI
IMPACT Enables character asset generation for game developers on consumer hardware, potentially lowering the barrier to entry for indie game creation.
RANK_REASON This is a user-developed tool leveraging existing AI models for a specific application, not a release from a frontier lab or a significant industry-wide event.
- DPM++ 2M Karras
- FastAPI
- IP-Adapter
- Paperdoll
- RealESRGAN-anime
- SAM
- Shitagaki Lab
- SmilingWolf
- Spellbrush
- Stable Diffusion 1.5
- UPenn
- WD-tagger v3
- xinntao
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →