Show HN: Feedback on Sketch Colourisation Hi I am looking for some feedback on our new project "Sketch Colourisation". The envisioned UI and objectives are -- * An artist should have greater control on how to colour a sketch. While a text-to-image model lacks this fine-grained control, a per-pixel colourisation pipeline makes sketch colourisation a laborious process with high-entry barrier. * What if an artist only draws a mask for a local region and specifies the colour palette for that local region? Then a neural network figures out how to colour the overall sketch -- while maintaining those local colour palette. [I would really like a feedback if the above UI (i.e., mask and local colour palette) makes sense to users/designers. As researchers, we often have the wrong idea of what is desired by end-users.] * On the exact implementation of the above concept, we designed a no-training based neural network framework -- and also make sure it runs on a Nvidia 4090. In other words, I will try to avoid any expensive training or inference -- which defeats the purpose of being useful to people (not just some research labs). * Note, I am not so bothered about the exact implementation (or whether it is "novel") -- as long as it is useful. * A shameless advertisement: The codebase ( https://ift.tt/gfDFqhE ) is MIT License. It is no way near to being useful to people -- but I would really like to pursue this direction and your feedback/criticism will be immensely helpful. Thanks https://ift.tt/OXsqwm3 June 22, 2024 at 05:03PM
Show HN: Feedback on Sketch Colourisation https://ift.tt/8suBU9Q
Related Articles
Show HN: Vessel – Your Passport for the Internet https://ift.tt/EIxFs67Show HN: Vessel – Your Passport for the Internet https://www.vessel.xy… Read More
Show HN: I built a site that summarizes articles and PDFs using NLP https://ift.tt/cdFnQK3Show HN: I built a site that summarizes articles and PDFs using NLP ht… Read More
Show HN: Optimal Stock Weights in a Portfolio, Tangency & Global Min Variance. https://ift.tt/iKqGT8fShow HN: Optimal Stock Weights in a Portfolio, Tangency & Global M… Read More
Show HN: A new way to write and publish research https://ift.tt/qfwIKrOShow HN: A new way to write and publish research https://dystr.com May… Read More
Show HN: TypeHub – A GitHub like platform to model open data specifications https://ift.tt/v0Iykb5Show HN: TypeHub – A GitHub like platform to model open data specifica… Read More
Show HN: Mitmproxy2swagger – Automagically reverse-engineer REST APIs https://ift.tt/Dqmia54Show HN: Mitmproxy2swagger – Automagically reverse-engineer REST APIs … Read More
Show HN: A simple but effective chess engine in JavaScript https://ift.tt/VtOcYfbShow HN: A simple but effective chess engine in JavaScript https://ift… Read More
Show HN: Pythondocs.xyz – live search for Python documentation https://ift.tt/SGgdHc8Show HN: Pythondocs.xyz – live search for Python documentation https:/… Read More
0 Comments: