Diatech Studio vs Kerf

Diatech Studio is an AI workspace for jewelry teams to develop, find, price, review, and present designs in one project. Users can start with text, speech, sketches, reference photos, CAD files, Pinterest boards, or WhatsApp messages. Search includes natural-language and reverse-image options, with tags, filters, and version control for design archives. Studio can generate model or hand photos, product copy, and product videos of 5, 10, or 15 seconds with audio; images can be upscaled to 4K. Its browser-based 3D tools create models from 2D images, render and clean meshes, and export OBJ or STL files. Costing features include spreadsheet import, AI price estimates, a shared price book, and stone inventory matching. Boards, calendars, tasks, assignees, due dates, mentions, and notifications support team coordination. Each generated image uses one image allowance, and each video second uses one video-second, drawing from the same monthly allowance. Free costs nothing and includes 25 images; Basic is $99 a month, Pro is $399 a month, and Enterprise is $1,199 a month.

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.