Open Source AI Models

Wan2.2 is a major upgrade to the Wan series of open and advanced large-scale video generative models, incorporating cutting-edge innovations to boost video generation quality and efficiency. It introduces a Mixture-of-Experts (MoE) architecture that splits the denoising process across specialized expert models, increasing total model capacity without raising computational costs. Wan2.2 integrates meticulously curated cinematic aesthetic data, enabling precise control over lighting, composition, color tone, and more, for high-quality, customizable video styles. The model is trained on significantly larger datasets than its predecessor, greatly enhancing motion complexity, semantic understanding, and aesthetic diversity. Wan2.2 also open-sources a 5-billion parameter high-compression VAE-based hybrid text-image-to-video (TI2V) model that supports 720P video generation at 24fps on consumer-grade GPUs like the RTX 4090. It supports multiple video generation tasks including text-to-video.

HunyuanWorld-Voyager is a next-generation video diffusion framework developed by Tencent-Hunyuan for generating world-consistent 3D scene videos from a single input image. By leveraging user-defined camera paths, it enables immersive scene exploration and supports controllable video synthesis with high realism. The system jointly produces aligned RGB and depth video sequences, making it directly applicable to 3D reconstruction tasks. At its core, Voyager integrates a world-consistent video diffusion model with an efficient long-range world exploration engine powered by auto-regressive inference. To support training, the team built a scalable data engine that automatically curates large video datasets with camera pose estimation and metric depth prediction. As a result, Voyager delivers state-of-the-art performance on world exploration benchmarks while maintaining photometric, style, and 3D consistency.

Wan2.1 is a foundational open-source large-scale video generative model developed by the Wan team, providing high-quality video generation from text and images. It employs advanced diffusion-based architectures to produce coherent, temporally consistent videos with realistic motion and visual fidelity. Wan2.1 focuses on efficient video synthesis while maintaining rich semantic and aesthetic detail, enabling applications in content creation, entertainment, and research. The model supports text-to-video and image-to-video generation tasks with flexible resolution options suitable for various GPU hardware configurations. Wan2.1’s architecture balances generation quality and inference cost, paving the way for later improvements seen in Wan2.2 such as Mixture-of-Experts and enhanced aesthetics. It was trained on large-scale video and image datasets, providing generalization across diverse scenes and motion patterns.

HunyuanVideo-I2V is a customizable image-to-video generation framework from Tencent Hunyuan, built on their HunyuanVideo foundation. It extends video generation so that given a static reference image plus an optional prompt, it generates a video sequence that preserves the reference image’s identity (especially in the first frame) and allows stylized effects via LoRA adapters. The repository includes pretrained weights, inference and sampling scripts, training code for LoRA effects, and support for parallel inference via xDiT. Resolution, video length, stability mode, flow shift, seed, CPU offload etc. Parallel inference support using xDiT for multi-GPU speedups. LoRA training / fine-tuning support to add special effects or customize generation.

HunyuanCustom is a multimodal video customization framework by Tencent Hunyuan, aimed at generating customized videos featuring particular subjects (people, characters) under flexible conditions, while maintaining subject/identity consistency. It supports conditioning via image, audio, video, and text, and can perform subject replacement in videos, generate avatars speaking given audio, or combine multiple subject images. The architecture builds on HunyuanVideo, with added modules for identity reinforcement and modality-specific condition injection. Text-image fusion module based on LLaVA for improved multimodal understanding. Applicable to single- and multi-subject scenarios, video editing/replacement, singing avatars etc.

HunyuanVideo-Avatar is a multimodal diffusion transformer (MM-DiT) model by Tencent Hunyuan for animating static avatar images into dynamic, emotion-controllable, and multi-character dialogue videos, conditioned on audio. It addresses challenges of motion realism, identity consistency, and emotional alignment. Innovations include a character image injection module, an Audio Emotion Module for transferring emotion cues, and a Face-Aware Audio Adapter to isolate audio effects on faces, enabling multiple characters to be animated in a scene. Character image injection module for better consistency between training and inference conditioning. Emotion control by extracting emotion reference images and transferring emotional style into video sequences.