{"slug": "queueink", "title": "QueueInk", "summary": "A developer built QueueInk, an open-source inquiry-desk tool for solo tattoo artists that uses a small open-weight model to extract fields from client DMs and draft replies while ordinary code handles budget parsing, missing-info flags and decline decisions based on the artist's own rules. The model never accepts jobs, sets prices or creates artwork, and because the weights are open, artists can run it entirely locally with no per-message API cost. The developer reports inference time dropped from 90.8 seconds locally to 3.7 seconds on Hugging Face Spaces with ZeroGPU, and cautions the tool was tested on only 10 inquiries and relies on keyword matching that can miss unusual wording.", "body_md": "*This is a submission for the [Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle](https://dev.to/challenges/hacktoberfest-week2-2026-10-12)*\n\nA tattoo inquiry usually shows up as a vague DM: \"small fox on my forearm, kinda fine line, budget around 400Rs, need it before the 20th.\" Size, references and exact placement are often missing, and some requests are things the artist simply doesn't do. Answering every one by hand takes time, and so does saying no.\n\n**QueueInk** is an inquiry desk for solo tattoo artists. The artist sets their own rules once: styles they don't do, placements they avoid, a minimum price, and whether they take cover-ups. Then they paste an inquiry and get:\n\nThe AI never accepts a job, never sets a price and never creates artwork. It only reads text and drafts a message that the artist edits.\n\n**Who would pay?** \n\nI think solo artists who book through DMs could, since it saves repetitive replies. I haven't tested whether they'd pay. \n\nDeployed link : [https://huggingface.co/spaces/nikisded/queueInk](https://huggingface.co/spaces/nikisded/queueInk)\n\nSample video: [Link to your video, if you made one]\n\n*The sample message on the demo is made up. Please don't paste real client messages into the hosted version (see \"Why Does Open Innovation Matter?\").*\n\nThe design choice that mattered most: **the model has a narrow job.** Budget parsing, flags, \"what's missing\" and the decline decision are ordinary code driven by the artist's settings. The model only extracts a few fields and writes a friendly reply. That keeps decisions predictable, makes declines instant (no model call), and means a small model is enough.\n\nA few details I'm happy with:\n\n**Performance, honestly:** my first run on my local space took 90.8s. But after having it hosted on HuggingSpace with ZeroGPU that time came to be 3.7s\n\n**What it can't do:** the rules use keyword matching, so unusual wording can slip through and some phrases false-alarm. A small model gets fields wrong sometimes, which is why every field is editable. I tested it on 10 inquiries, not at scale.\n\nTattoo clients send personal details, and sometimes health or age information. Because the model is open-weight, an artist can run QueueInk **entirely on their own computer**:\n\n```\npip install -r requirements.txt\npython app.py\n```\n\nAfter the first model download, nothing needs to leave the machine, there's no per-message API bill, and nobody can change the price or switch the model off. Because the weights are open, the model can also be swapped or tuned later for how artists actually write.\n\nI want to be clear about the limits:\n\nOverall", "url": "https://wpnews.pro/news/queueink", "canonical_source": "https://dev.to/nikitha_s_3a42baaa72fd15a/queueink-5e2a", "published_at": "2026-10-19 05:06:29+00:00", "updated_at": "2026-10-19 05:18:11.473114+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-tools", "large-language-models", "ai-agents"], "entities": ["QueueInk", "Hugging Face", "ZeroGPU", "Hacktoberfest"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/queueink", "markdown": "https://wpnews.pro/news/queueink.md", "text": "https://wpnews.pro/news/queueink.txt", "jsonld": "https://wpnews.pro/news/queueink.jsonld"}}