This repo collects the native RGBA generation methods:

Papers

1. Transparent Image Layer Diffusion using Latent Transparency (TOG24),
2. FontStudio: Shape-Adaptive Diffusion Model for Coherent and Consistent Font Effect Generation (ECCV 24)
3. Alfie: Democratising RGBA Image Generation With No $$$ (ECCV24 workshop),
4. ART: Anonymous Region Transformer for Variable Multi-Layer Transparent Image Generation (CVPR25),
5. Generative Image Layer Decomposition with Visual Effects (CVPR25)
6. TransPixeler: Advancing Text-to-Video Generation with Transparency (CVPR2025)
7. Zero-Shot Subject-Centric Generation for Creative Application Using Entropy Fusion (arXiv25)
8. TransAnimate: Taming Layer Diffusion to Generate RGBA Video (arXiv25)
9. PSDiffusion: Harmonized Multi-Layer Image Generation via Layout and Appearance Alignment (arXiv25),
10. DreamLayer: Simultaneous Multi-Layer Generation via Diffusion Model (arXiv25)
11. AlphaVAE: Unified End-to-End RGBA Image Reconstruction and Generation with Alpha-Aware Representation Learning (arXiv25)
12. PrismLayers: Open Data for High-Quality Multi-Layer Transparent Image Generative Models (May, 2025)
13. Qwen-Image-Layered (Dec, 2025)

Repos

1. LayerDiffuse(Flux version),
2. LayerDiffuse_DiffusersCLI (SDXL version),
3. DeepGrabCut-PyTorch,

Products

1. OpenAI 4o Image Generation

Matting/Segmentation papers

1. PP-Matting
2. BEN2[image & video]
3. BiRefNet
4. RMBG-2.0