Diffusion Model 2

Open-source MoE AI video generation with cinematic control. Wan2.2 is the world's first open-source MoE (Mixture-of-Experts) video generation model developed by Alibaba Tongyi Lab. It enables users to create professional cinematic videos from text (text-to-video) or images (image-to-video) at 720P resolution with 24fps. Key features include advanced motion understanding, stable video synthesis, and fine-grained cinematic control over lighting, color, and composition. It is fully open-source with complete model weights, optimized for performance, and can run efficiently on consumer-grade GPUs.

Next-Gen AI image generator with superior text rendering and hybrid architecture. GLM Image is a cutting-edge, next-generation AI image generator that utilizes a hybrid architecture combining a 9B autoregressive generator with a 7B diffusion decoder to produce unmatched image quality. It excels in superior text rendering within images using Glyph-byT5 technology, making it ideal for creating posters and infographics. It offers fast generation speeds (5-20 seconds), supports multilingual prompts, and provides a powerful API for application integration.