This repo collects the native RGBA generation methods:
- Transparent Image Layer Diffusion using Latent Transparency (TOG24),
- FontStudio: Shape-Adaptive Diffusion Model for Coherent and Consistent Font Effect Generation (ECCV 24)
- Alfie: Democratising RGBA Image Generation With No $$$ (ECCV24 workshop),
- ART: Anonymous Region Transformer for Variable Multi-Layer Transparent Image Generation (CVPR25),
- Generative Image Layer Decomposition with Visual Effects (CVPR25)
- TransPixeler: Advancing Text-to-Video Generation with Transparency (CVPR2025)
- Zero-Shot Subject-Centric Generation for Creative Application Using Entropy Fusion (arXiv25)
- TransAnimate: Taming Layer Diffusion to Generate RGBA Video (arXiv25)
- PSDiffusion: Harmonized Multi-Layer Image Generation via Layout and Appearance Alignment (arXiv25),
- DreamLayer: Simultaneous Multi-Layer Generation via Diffusion Model (arXiv25)
- AlphaVAE: Unified End-to-End RGBA Image Reconstruction and Generation with Alpha-Aware Representation Learning (arXiv25)
- PrismLayers: Open Data for High-Quality Multi-Layer Transparent Image Generative Models (May, 2025)
- Qwen-Image-Layered (Dec, 2025)
- PP-Matting
- BEN2[image & video]
- BiRefNet
- RMBG-2.0