FormaNova AI Jewelry CAD vs Kerf

FormaNova AI Jewelry CAD is a browser service for creating jewelry imagery and editable 3D CAD models. Upload product images to receive photoshoot renders on realistic models or mannequins, or describe a design in text or provide a reference image to generate CAD. The built-in studio allows adjustments to materials, lighting and other design details. Models use editable parametric NURBS geometry with separate bodies for bands, heads, prongs and galleries. Exports include native .3dm files for Rhino and MatrixGold and GLB meshes for rendering and visualization. The photoshoot studio supports rings, necklaces, earrings, bracelets and watches. Selected images can be exported to a connected Shopify store as draft products; FormaNova says that integration does not request or intentionally collect customer, order, payment, shipping or checkout data. It says uploads and outputs are not used to train models without explicit consent. One-time credit packs start at 2.00 USD for 50 credits.

Kerf is a free, open-source CAD workspace that runs on the user's own machine and supports work across 37 engineering domains. Users can describe design changes in plain language or use the Python kerf-sdk and JSON-RPC API. Mechanical design tools include constraint-based sketching, parametric feature history, validated B-rep geometry, drawings, and persistent face references. The workspace also includes FEM analysis, topology optimization, SPICE and RF analysis, CAM toolpaths, and G-code output. Listed outputs include STEP, STL, 3MF, IFC4, Gerber, PDF, DXF, BOM CSV, Touchstone, GDS-II, and firmware binaries. The site describes workflows for mechanical and electronics engineers, BIM architects, jewelry designers, and other engineering users. Kerf runs locally without accounts and keeps Git history for file revisions. Workshop content can be used offline once pinned. Installation options include source or Docker, with release archives listed for macOS arm64, macOS x64, and Linux x64; source installation requires Python 3.11 or later. The chat workflow can use a bring-your-own LLM; no bundled model or paid hosted plan is listed.