Crynux Network
Truly Permissionless DeAI on GPU@home
Crynux is the truly permissionless AI infrastructure everyone can join and use right away.
The key component of Crynux is a robust consensus protocol that enables the permissionless joining and using of the decentralized network by millions. The ability to identify and penalize all the malicious behaviors ensures the ecosystem's sustainability and facilitates healthy growth in a long term.
As the foundation layer, Crynux Network is composed of the decentralized nodes who contribute their spare AI computing power to the network in exchange for token rewards. The computing power is then grouped and dispatched to run the AI tasks from the developers and applications.
On top of the computing network, a decentralized model/dataset hosting service is provided to better support the various AI use cases.
The applications could easily connect to the Crynux Network using API, use Crynux Network to generate images or texts, and bring AI power to their users with no extra need for the hardware and development.
The developers could write codes to train/fine-tune their models on the dataset provided by the network, using the computing power of the network. The developed model could also be hosted on the network as a service for others.
By utilizing the Blockchain, Zero-knowledge Proofs and Privacy Preserving Computation technologies, Crynux aims to build a completely decentralized and trustless infrastructure that is always accessible to everyone.
Helium Network
Helium Network is the latest testnet of the Crynux Network. Helium Network implements a decentralized AI task execution engine that supports running the Stable Diffusion image generation tasks and the GPT text generation tasks.
Although called a testnet, the featured consensus protocol is robust enough to allow everyone to join at this moment. Everyone has an Nvidia GPU, or Mac with the Apple Silicon chips (M1, M2 and M3 series), could have already joined the network using our node software.
Stable Diffusion Image Generation
The applications could now send the Stable Diffusion image generation tasks to the network using the inference API, and get the images back instantly.
A showcase application has been developed to demonstrate the abilities. The app provides a web interface (just like stable-diffusion-webui) for the users to generate images in the browser. Thanks to the Helium Network, the users could use the application on any devices that do not have a capable GPU integrated.
The complexity of the blockchain and tokens are taken care of at the backend using Crynux Bridge. To the end users, this is just a traditional easy-to-use web application, nothing special.
Give it a try at https://ig.crynux.ai
GPT Text Generation
The applications could also execute the GPT text generation tasks using most of the LLM models on Huggingface, such as LLaMa 2, using the inference API of the Helium Network.
A chatbot web application has been developed as an example for the developers. The web application provides a simple chat UI in the browser, and connects to the Crynux Bridge at the backend to interact with the Crynux Network.
The chatbot can be accessed at https://chat.crynux.ai
To read more about the Helium Network release, go to the following page:
pageHelium NetworkGetting Started
Start a Node
Fill a form to tell us your GPU type, location, network bandwidth[No application form, no sign up, you don’t need to tell us]Join waitlist and wait for the email from us[No waitlist, just install the Crynux Node app, you can start earning CNX tokens right away]Just download the package according to your platform, and follow the tutorials below:
| Platform | Requirements | Download Link |
|---|---|---|
Windows | Nvidia GPU with 8GB VRAM | |
Mac | M1/M2/M3 and later | |
Linux | Nvidia GPU with 8GB VRAM |
To start a node on your Windows computer:
pageStart a Node - WindowsIf you are using Mac with Apple Silicon Chips (M1/M2/M3 and later):
pageStart a Node - MacTo start a node on Linux (such as Ubuntu):
pageStart a Node - LinuxTo start a node on cloud services based on Docker, such as Vast.ai:
pageStart a Node - VastYou can also start the node using Docker:
pageStart a Node - DockerDevelop an application
If you are an application developer who want to utilize the AI abilities provided by the Crynux Network, follow the tutorial below:
pageApplication WorkflowResearch
Checkout our latest research paper about Crynux Network here:
Links
Join the Crynux community on Discord:
All the codes are open sourced at GitHub, feel free to submit issues and PRs:
The Crynux Blog contains the technical explanations and our latest progress:
And follow us on Twitter:
Last updated
