Credentials. The generation step needs your fal FAL_KEY in a local .env file, so keep that file out of version control and do not paste the key into an agent prompt.
Who it is forA designer or developer who needs a custom 3D hero object for a page and does not have a 3D modelling workflow.
The problemModelling a detailed product object by hand is slow, and the raw AI output is too heavy for a web page.
The outcomeA set of generated images and an optimized GLB file in public/models/, ready for a Dioramas page.
What you need first
- Git and Node.js with npm, to clone the repo and run the dev server
- A desktop GPU, which the README recommends for 60 fps
- About 330 MB of disk space for the repo, since models ship in the clone (no LFS)
- A fal account and FAL_KEY, only if you want to generate new models or images
Steps
- Run
cp .env.example .envand add your key as FAL_KEY in the .env file. - Add your object prompts as JSON job files in assets/jobs/, following the examples there.
- Run
node scripts/gen.mjs all assets/jobs/ .jsonto generate images and meshes. The README says this step is resumable. - Run
node scripts/optimize-all.mjsto weld, compress and convert the models into public/models/. - Point your example's main.js at the new GLB in public/models/ and check it with
npm run dev.
Prompt for your agent
In the blendi-remade/dioramas repo, add a job for <object description> to assets/jobs/ following the existing job files, then run the generation and optimize scripts from the README. Expected output: a new optimized GLB in public/models/ and the generated image in the job output. Verify by confirming the GLB file size is in the 3 to 8 MB range the README gives for optimized models.
Caveat. The README gives an approximate cost of about $1.20 per textured model and says the whole collection cost roughly $90, so check your fal usage before running a full batch.
Get 5 new use cases every morning. Free, one short email, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Disclaimer
Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page