ModelScopeAlibaba Cloud
|
||||||
Related Products
|
||||||
About
This model is based on a multi-stage text-to-video generation diffusion model, which inputs a description text and returns a video that matches the text description. Only English input is supported.
This model is based on a multi-stage text-to-video generation diffusion model, which inputs a description text and returns a video that matches the text description. Only English input is supported.
The text-to-video generation diffusion model consists of three sub-networks: text feature extraction, text feature-to-video latent space diffusion model, and video latent space to video visual space. The overall model parameters are about 1.7 billion. Support English input. The diffusion model adopts the Unet3D structure, and realizes the function of video generation through the iterative denoising process from the pure Gaussian noise video.
|
About
Nexa AI enables developers and consumers to run state-of-the-art AI models locally on CPUs, GPUs, and NPUs, removing the reliance on cloud infrastructure. Its flagship Nexa SDK allows developers to deploy any AI model across devices in minutes, supporting compression for efficiency and acceleration on NPUs. For consumers, Hyperlink acts as a private offline AI agent that can search local files, provide insights, and ensure complete data privacy. Nexa’s technology emphasizes three pillars: absolute privacy, predictable cost with pay-per-device licensing, and offline reliability for use in secure or disconnected environments. Proprietary innovations like the NexaML Engine ensure performance optimization across hardware, from PCs to IoT devices. By combining flexibility, security, and speed, Nexa AI brings modern AI capabilities directly to the edge.
|
|||||
Platforms Supported
Windows
Not Supported
Mac
Not Supported
Linux
Not Supported
Cloud
Supported
On-Premises
Not Supported
iPhone
Not Supported
iPad
Not Supported
Android
Not Supported
Chromebook
Not Supported
|
Platforms Supported
Windows
Supported
Mac
Supported
Linux
Supported
Cloud
Not Supported
On-Premises
Supported
iPhone
Not Supported
iPad
Not Supported
Android
Not Supported
Chromebook
Not Supported
|
|||||
Audience
Users interested in an open source text-to-video AI video generation model
|
Audience
Developers, enterprises, and privacy-conscious consumers seeking high-performance, offline AI solutions that run across devices without cloud dependence
|
|||||
Support
Phone Support
Not Supported
24/7 Live Support
Not Supported
Online
Not Supported
|
Support
Phone Support
Not Supported
24/7 Live Support
Not Supported
Online
Supported
|
|||||
API
Offers API
Not Supported
|
API
Offers API
Not Supported
|
|||||
Screenshots and Videos |
Screenshots and Videos |
|||||
Pricing
Free
Free Version
Supported
Free Trial
Not Supported
|
Pricing
No information available.
Free Version
Not Supported
Free Trial
Not Supported
|
|||||
Reviews/
|
Reviews/
|
|||||
Training
Documentation
Supported
Webinars
Not Supported
Live Online
Not Supported
In Person
Not Supported
|
Training
Documentation
Not Supported
Webinars
Not Supported
Live Online
Not Supported
In Person
Not Supported
|
|||||
Company InformationAlibaba Cloud
China
modelscope.cn/
|
Company InformationNexa AI
United States
nexa.ai/
|
|||||
Alternatives |
Alternatives |
|||||
|
|
||||||
|
|
||||||
|
|
|
|||||
Categories |
Categories |
|||||
Integrations
01.AI
Supported
Qwen 4
Supported
Qwen-7B
Supported
Qwen-Image
Supported
Qwen2-VL
Supported
Qwen2.5-1M
Supported
Qwen2.5-Max
Supported
Qwen2.5-VL
Supported
Qwen3
Supported
Qwen3.6
Supported
|
Integrations
01.AI
Not Supported
Qwen 4
Not Supported
Qwen-7B
Not Supported
Qwen-Image
Not Supported
Qwen2-VL
Not Supported
Qwen2.5-1M
Not Supported
Qwen2.5-Max
Not Supported
Qwen2.5-VL
Not Supported
Qwen3
Not Supported
Qwen3.6
Not Supported
|
|||||
|
|
|