Open-source projects tagged “diffusion-model”

Open-source 5B-parameter text-to-image diffusion transformer with strong in-image text rendering and JSON layout control.

Open-source large-scale video generative models for text-to-video, image-to-video, speech-to-video and character animation.

Open-source framework for real-time, audio-driven avatar video generation that streams with effectively unlimited length, built on a 14B Wan2.2-S2V base model.

Open-source 6B-parameter models that generate complete visual designs from text and split flattened design images into editable transparent layers.