Canvas Studio takes a coloring-book canvas from an idea to a live, game-ready asset in one browser tab. It covers generation, review, approval, assembly, and publishing. Before, this took six or seven hand-offs across Photoshop, AI image tools, shared drives, SVN, and the CMS.
Click any chapter to jump to that part of the walkthrough.
There are three stages, and each one ends in a deliberate lock, so downstream work is never built on art that might still change.
| Before (legacy) | Now (Canvas Studio) | |
|---|---|---|
| Where the work happens | Photoshop, external AI generators, Drive, scripts, SVN, CMS | One web app |
| Hand-offs | 6–7 manual stages | 3 guided stages + one-click publish |
| Region names & colors | By hand in Photoshop | AI-suggested, then confirmed by the artist |
| Spawner placement | Manual icon placement | Automatic; only about 1–5% need a touch-up |
| Review | Screenshots & messages | In-context comments, @-mentions, Slack |
| Shipping | Export → SVN → CMS build by hand | Publish does all three and reports build status |
The player sees a line drawing, taps paint-brush icons (spawners) on each region, and picks colors to bring the scene to life. Three images make that possible.
Before Canvas Studio, an artist built all of this by hand in Photoshop with our custom DH Tools panel. The artist layered generated images into a template, cut masks, placed spawner icons, ran export scripts, and uploaded the results by hand.
Create and pick the three source images. Every pick is reviewed in place and locked before moving on.








Approval locks the set for the rest of the pipeline. If something has to change later, Reopen sends the images back, and the rebuild replaces the assembly, which prevents half-updated canvases.
This stage replaces most of the old Photoshop work. One click builds a fully named, pre-colored, interactive canvas.



The game loads one texture and reads everything from its color channels, which keeps download size and memory small:
Other views help with checking the work:


One click takes the canvas to the game.

<initials>_<location>_canvasRepublishing reuses the same CMS entry and SVN folder, so fixes ship without duplicates.


The building blocks behind Canvas Studio.
| Layer | What powers it |
|---|---|
| Image generation | Adobe Firefly with Design Home–trained custom models (separate interior and exterior models); a line-art style block distilled from about 80 shipped backgrounds |
| Image understanding | Vision AI models that segment the cryptomatte, label every region, and score style quality |
| Color matching | AI-proposed colors snapped to the nearest paint brush in the live CMS color catalog |
| Game format | A single packed composite (R = region masks, G = line art) plus per-spawner data (region value, palette, icon position), delivered as the same coloring-book RoomRender type the earlier Photoshop pipeline produced |
| Collaboration | Threaded comments with @-mentions and area markers on every asset; Slack notifications for review and approval |
| Delivery | Automated SVN import, CMS RoomRender creation, and a Unity asset-bundle build, with status reported in the UI |
| Tracking | planned → in progress → ready → approved, with dashboard roll-ups of counts, total assets, and average style score |