aws-samples / aws-samples/berkeley-room-designer
Furniture placement algorithms need work
Open
- Dominant language
- TypeScript
- Stars
- 5
- Forks
- 1
- PR merge metrics
- No merged PRs in 30d
Description
The LLM-based furniture placement algorithm isn't very good at placing furniture (at least using our prompt configuration), and the _autointeriorblog_ and _random_ algorithms don't properly place furniture on walls/ceilings yet. Additionally, the _autointeriorblog_ furniture placement algorithm is slow when running in the browser; perhaps it could be tuned when running on the client, and if not, perhaps pushed to some async backend logic.
Contributor guide
Assessment
This issue has not been assessed yet.