OmniSVG is the first family of end-to-end multimodal SVG generators that leverage pre-trained Vis...

Lumina-mGPT 2.0: Stand-alone Autoregressive Image Modeling

The fastest knowledge base for growing teams. Beautiful, realtime collaborative, feature packed, ...

[ICLR 2025] Animate-X: Universal Character Image Animation with Enhanced Motion Representation

YuE: Open Full-song Generation Foundation Model, something similar to Suno.ai but open

Illumination Drawing Tools for Text-to-Image Diffusion Models

Generate a transcript for your favourite Manga: Detect manga characters, text blocks and panels. ...

Official repository of In-Context LoRA for Diffusion Transformers