# Wan-Video/Wan2.2

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/wan-video-wan2-2).**

14,283 stars · 1,704 forks · Python · apache-2.0

## Links

- GitHub: https://github.com/Wan-Video/Wan2.2
- Homepage: https://wan.video
- awesome-repositories: https://awesome-repositories.com/repository/wan-video-wan2-2.md

## Topics

`aigc` `video-generation`

## Description

Wan2.2 is a generative video artificial intelligence system designed to synthesize visual media by interpreting natural language instructions. It functions as a text-to-video diffusion model that transforms written concepts into coherent motion sequences through deep learning and latent space manipulation.

The system utilizes a transformer-based architecture to process video data as a series of tokens, allowing it to capture complex spatial and temporal relationships. By employing a temporal attention mechanism, the model maintains visual consistency across frames, while its latent space approach reduces computational overhead during the generation process.

The engine supports automated video production and content creation by converting descriptive text prompts into high-quality video sequences. It incorporates multi-stage upscaling to refine initial outputs into high-fidelity media and uses classifier-free guidance to ensure the generated content adheres to user-provided prompts.

## Tags

### Artificial Intelligence & ML

- [Text-to-Video Generators](https://awesome-repositories.com/f/artificial-intelligence-ml/generative-ai-resources/diffusion-visual-models/generative-ai-pipelines/text-to-video-generators.md) — Converts descriptive text prompts into high-quality video sequences using generative AI. ([source](https://alidocs.dingtalk.com/i/nodes/EpGBa2Lm8aZxe5myC99MelA2WgN7R35y))
- [Automated Video Generators](https://awesome-repositories.com/f/artificial-intelligence-ml/automated-video-generators.md) — Streamlines video production by automatically synthesizing visual content from text-based scripts and prompts.
- [Automated Video Synthesis](https://awesome-repositories.com/f/artificial-intelligence-ml/automated-video-synthesis.md) — Transforms written concepts into visual content through deep learning and latent space manipulation.
- [Latent Diffusion Models](https://awesome-repositories.com/f/artificial-intelligence-ml/generative-ai-resources/diffusion-visual-models/generative-models/latent-diffusion-models.md) — Utilizes latent diffusion models to transform noise into coherent video frames through iterative denoising in compressed latent space.
- [Attention Mechanisms](https://awesome-repositories.com/f/artificial-intelligence-ml/attention-mechanisms.md) — Implements temporal attention mechanisms to maintain visual consistency across video frames by calculating pixel dependencies.
- [Latent Space Generative Models](https://awesome-repositories.com/f/artificial-intelligence-ml/generative-ai-resources/diffusion-visual-models/generative-ai-models/latent-space-generative-models.md) — Encodes high-resolution visual data into a compact latent space to reduce computational overhead during video synthesis.
- [Automated Content Creation Tools](https://awesome-repositories.com/f/artificial-intelligence-ml/generative-ai-resources/speech-synthesis/automated-content-creation-tools.md) — Automates the production of original visual media assets for storytelling and entertainment through generative AI.
- [Generative Upscalers](https://awesome-repositories.com/f/artificial-intelligence-ml/generative-upscalers.md) — Employs generative upscaling techniques to refine initial low-resolution outputs into high-fidelity video sequences.
- [Variational Autoencoders](https://awesome-repositories.com/f/artificial-intelligence-ml/model-training/variational-autoencoders.md) — Applies variational autoencoder compression to map high-resolution visual data into compact latent spaces for efficient processing.
- [Guidance Steering](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/language-tools/text-classification/text-classifier-initializers/automated-classifiers/guidance-steering.md) — Implements classifier-free guidance to steer generative model outputs by comparing conditional and unconditional generation paths.
- [Sequence Modeling](https://awesome-repositories.com/f/artificial-intelligence-ml/sequence-modeling.md) — Uses transformer-based sequence modeling to process video data as tokens for capturing complex spatial and temporal relationships.