Docs / Demo projects
Demo projects
Complete projects to get started: what each demo shows, its flows, what it needs and how to run it on your workers.
Demo projects are complete projects made to show what EsaSim does and to get you started: each has a readme, ready-made blueprints numbered in the order to try them, and the blocks they use. Copy one into your workspace and run it on your own workers.
Use a demo
- Open Projects > Demos. Someone with no projects yet lands there.
- Open a demo. It opens like any project, with all its tabs: its readme, its blueprints with every block, setting and the code of its blocks.
- Open flow 1 in the Blueprint and press Run. It runs as it is, on your own workers.
A demo is seen through your own workspace. Its Compute, Runs, Results, Data and Analytics tabs show your workers, your runs and your results, never those of its makers, and its makers do not see yours. You need no GitHub account to open or run a demo.
The demo itself does not change: to change its blueprints, choose Clone into my workspace. A copy goes into your current workspace (its readme and pictures, cover, blueprints and blocks), saved to a private GitHub repository of yours, so link GitHub first (Profile > GitHub). The copy is your own project: change it, run it, work on it with colleagues through branches and pull requests, or ask an AI assistant to adapt it to your case. It brings no data, results, team or keys of the original; it tells you which blocks need a dataset or a place for their outputs in your workspace.
Which demos appear depends on what the platform admins choose to show (a project's Settings > Demo for everyone). The pages of this section describe the current set.
The demos
| Demo | What it shows |
|---|---|
| Text to image | Open text-to-image models turn one prompt into any number of pictures on your worker, shown live as they are made, and compared from small to large. |
| Text to video | Open text-to-video models make short clips on your NVIDIA GPU, each streamed live and played whole as it is made; keep the good ones and browse them. |
| Data curation | From a raw pile of images to a training-ready set: quality, duplicates, embeddings, label checks, a review grid, a split and a before and after report. |
| CT to 3D anatomy | CT scans become coloured 3D models of every organ, bone and vessel to turn around, cut through and print, and a soft-tissue model that moves under gravity. |
| Warehouse fleet | A goods-to-person warehouse run live in 3D with up to fifty robots, then sweeps that find how many robots it needs and which layout works best. |
| Booster landing | A rocket booster learns to land on a drone ship by reinforcement learning on your GPU, then launches and lands live in 3D with onboard cameras. |