Work in progress: 181,232 of 181,233 sites checked so far, more every week · updated 2 Nov 2026Missing a blog? Tell us

Top all-time · #9019

K

Kevin Frans

Personal blog · kvfrans.comaiscience

Kevin Frans writes kevin frans blog, a personal blog at kvfrans.com about ai and science. Since 2016, 9 different Hacker News readers have linked it 10 times, most often “CLIPDraw: Exploring Text-to-Drawing Synthesis”. It is still writing: the last post was on 2025-05-28, and you can follow it by feed.

Visit the blog
10mentions?
9HN people?
2016–2024first – last linked?
Links on Hacker News per year · peak 4 in 2017

Too few sampled comments (2) to say how often HN recommends it.?

Why HN links it

Commenters cite Kevin Frans's GAN work on automatically colouring and shading anime and line art as an example of neural networks applied to images. No comment praises the posts directly.

Summarised by Claude from a sample of 2 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.

Most-linked posts?

  1. CLIPDraw: Exploring Text-to-Drawing Synthesis
    2 people · 2 mentions · first linked 2021-06-29
  2. Generative adversial networks explained
    2 people · 2 mentions · first linked 2016-06-29
  3. Variational Autoencoders Explained
    2 people · 2 mentions · first linked 2017-03-03
  4. Deepcolor: automatic coloring and shading of manga-style lineart
    2 people · 2 mentions · first linked 2017-04-04

What Hacker News says?

  1. Neural Networks are really good at identifying patterns in data. As a classic example, if you wanted to predict housing prices, you could build a data set that maps features about houses (square feet, location, proximity to Caltrain, etc) onto their actual price, and then train a network to recognize the complex relationship between features and pricing. Training happens by feeding the network features, letting it m…

    Comment linking /generative-adversial-networks-explained/

    on “Progressive Growing of GANs for Improved Quality, Stability, Variation [video]”
  2. Submitted Deepcolor: automatic coloring and shading of manga-style lineart as a story · 3 points

    HN discussion
  3. Creating images with radar sounds like a fun GAN project. I mean we are already coloring animes [1] and line-arts [2, 3]. [1] http://kvfrans.com/coloring-and-shading-line-art-automatical... [2] https://arxiv.org/pdf/1808.03240.pdf [3] https://github.com/lllyasviel/style2paints

    Comment linking /coloring-and-shading-line-art-automatically-through-conditional-gans/

    on “Google’s Project Soli radar is sensitive enough to count sheets of paper”
  4. Submitted A Mathematical Definition of Interestingness as a story · 2 points

    HN discussion
  5. Submitted Variational Autoencoders Explained as a story · 2 points

    HN discussion
  6. Submitted Generative adversial networks explained as a story · 2 points

    HN discussion
  7. Submitted To extract information from language models, optimize for causal response as a story · 1 points

    HN discussion
  8. Submitted CLIPDraw: Exploring Text-to-Drawing Synthesis as a story · 1 points

    HN discussion
  9. Submitted CLIPDraw: Exploring Text-to-Drawing Synthesis as a story · 1 points

    HN discussion
  10. Submitted Variational Autoencoders Explained as a story · 1 points

    HN discussion

Search all of HN for kvfrans.com

Linked by the same people?