{"slug": "show-hn-fabivo-furniture-design-from-a-photo-to-a-numbered-cut-list", "title": "Show HN: Fabivo – Furniture design from a photo to a numbered cut list", "summary": "Developer Fabivo released Fabivo, a free browser-based furniture planner whose image-to-JSON CAD harness converts a photo of real furniture into an editable parametric model in millimeters and a numbered cut list. In a self-run benchmark of 17 photos of real furniture across three models using the same harness, medium reasoning and the same tools, GPT-6.1 Terra averaged 9.5 seconds, 30,409 input tokens, 632 output tokens and 1.06 tool calls per photo, versus 13.6 seconds, 50,167 input tokens, 1,592 output tokens and 1.18 tool calls for Claude Sonnet 5.5 and 34.9 seconds, 66,786 input tokens, 6,658 output tokens and 2.35 tool calls for Claude Haiku 5.5. The developer said Terra was both cheaper per photo and the most consistent to his liking, and that Sonnet was close on quality while Haiku needed far more tool calls to get there.", "body_md": "Hello all,\n\nIve been building Fabivo, a free furniture planner that runs in the browser. You sketch it simply by drawing it, (by far my favorite feature of this app), clicking for boards or just selecting some starting designs.\n\nBut what i think separates fabivo from others its the image to model ai assistant, which took me a looong time to develop and get some quirks fixed, thanks god latest models are focusing on 3d, thats been helping too!\n\nThe photo part is an image to JSON CAD harness: the model returns a parametric furniture model in mm that the app can build and edit. That harness is also what i benchmark, and honestly its the reason the app exists. I wanted to see if a photo could turn into a plan i could take to the saw.\n\nAlso finetuned some image models and found interesting stuff, that was a first. My intention was to basically reuse the drawing feature to convert a 2d line sketch from image models like gpt image / nano banana to my parametric model, which \"worked\", and was actually thinking of using that for prod, but then cheaper/better models at 3d launched, but anyways, i learned a lot!\n\nIm getting better performance from my harness than from plain 3js, tho this is anecdotally and havent actually benchmarked it...\n\nHappy to answer anything, especially about the harness or the cut order.\n\nedit: Adding the numbers, missed them.\n\n17 photos of real furniture, three models, same harness, medium reasoning, same tools. Scored on how close the returned structure and boards are to the gold model, so its my own set. (tho i have a hard time making a good scoring metric... just usually go by look!)\n\nModel (medium reasoning) Avg. time / photo Avg. input tokens / photo Avg. output tokens / photo Avg. tool calls / photo GPT-6.1 Terra 9.5 s 30,409 632 1.06 Claude Sonnet 5.5 13.6 s 50,167 1,592 1.18 Claude Haiku 5.5 34.9 s 66,786 6,658 2.35\n\nTerra was both cheaper per photo and the most consistent to my likings. Sonnet was close on quality, Haiku needed way more tool calls to get there.\n\nComments URL: [https://news.ycombinator.com/item?id=50284856](https://news.ycombinator.com/item?id=50284856)\n\nPoints: 1\n\n# Comments: 0", "url": "https://wpnews.pro/news/show-hn-fabivo-furniture-design-from-a-photo-to-a-numbered-cut-list", "canonical_source": "https://www.fabivo.app/en", "published_at": "2026-10-29 05:21:10+00:00", "updated_at": "2026-10-29 05:44:22.938340+00:00", "lang": "en", "topics": ["artificial-intelligence", "generative-ai", "ai-tools", "computer-vision"], "entities": ["Fabivo", "GPT-6.1 Terra", "Claude Sonnet 5.5", "Claude Haiku 5.5", "Hacker News"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/show-hn-fabivo-furniture-design-from-a-photo-to-a-numbered-cut-list", "markdown": "https://wpnews.pro/news/show-hn-fabivo-furniture-design-from-a-photo-to-a-numbered-cut-list.md", "text": "https://wpnews.pro/news/show-hn-fabivo-furniture-design-from-a-photo-to-a-numbered-cut-list.txt", "jsonld": "https://wpnews.pro/news/show-hn-fabivo-furniture-design-from-a-photo-to-a-numbered-cut-list.jsonld"}}