GhostlyStock

AI

generative image search

SHOW HN2022

190points
105comments
#305of 2,570 in 2022
Top 12%of 2022 by points

How HN took it

MixedNo clear lean

9 positive, 19 neutral or asking, 4 mixed, 29 critical, out of 61 comments about the project. Thread score -0.34.

Execution: 0 for, 11 againstPerformance: 5 for, 5 againstIdea: 4 for, 2 againstPrivacy: 0 for, 5 againstDesign: 0 for, 5 against

The thread, comment by comment

Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.

positive neutral or mixed critical about another commenter or something else the maker

What HN said

What people liked

  • Some generated landscape and object images look striking

    From 2 comments
    • The landscape and city photos are stunning. The ones with people and animals tend to have distorted faces or bodies. But keep up the good work. There’s a definitely a market for…
      awb on HN
    • Whoa this is cool and I would def used a more refined version of it. The images with people are a little bit... freaky but objects and animals look fine. I wonder if this exists…
      ericmcer on HN
  • Related-result suggestions and the concept are interesting

    From 2 comments
    • I really like this idea! Related results work fairly well. Tons of potential here! Ideas: Allow voting for prompts. Allow voting for results. (But try to prevent the rich get…
      jtxt on HN
    • Gotta love some of these suggestions: "The Ethereum logo glowing above wet pavement, with a bull charging"
      napsterbr on HN

Objections

  • Search returns unrelated or odd images; poor matching of prompts

    From 4 comments
    • Doesnt work. I type my prompt and it gives results for something different.
      poopnugget on HN
    • Not sure I understand how to use this. I searched for "monkey on car" and these are the "categories" I get: "a dead monkey", "a monkey dancing", "a dead monkey" (again), "a ca"
      barbazoo on HN
    • If I search for "bicycle repair shop", all I see are images for car repair shops.
      Alex3917 on HN
    • It's sort of interesting, given the undeniable power that these new AI techniques have, just how limited the output is at the moment. Only 512x512 images. I tried a specific…
      bscphil on HN
  • Human faces and bodies are distorted and creepy

    From 3 comments
    • Some of these are a bit nightmarish! https://replicate.com/api/models/stability-ai/stable-diffusion/files/b17d6f04-8d89-45a4-b2d1-7104c6318591/out-2.png…
      nostromo on HN
    • The landscape and city photos are stunning. The ones with people and animals tend to have distorted faces or bodies. But keep up the good work. There’s a definitely a market for…
      awb on HN
    • It still has trouble understanding sentences, it feels to me that it just generates images based on keywords and not the meaning of my sentence. For example, I tried "attractive…
      rany_ on HN
  • Not a functional stock photo platform yet; lacks human curation

    From 2 comments
    • Not sure how to evaluate that. Maybe it's kinda fun, but… I mean, generating crappy images from text isn't exactly new by now. It may be "an early version" (and this is exactly…
      krick on HN
    • Actual stock photo websites have human reviewers and it's a big part of their value proposition.
      bambax on HN
  • Images are only 512x512 and too low resolution for stock use

    From 2 comments
    • 512x512 is standard for SD generated images, but seems pretty low res when you look at it as a stock photo. Might be good to provide an AI upscaled version of the image for…
      needle0 on HN
    • It's sort of interesting, given the undeniable power that these new AI techniques have, just how limited the output is at the moment. Only 512x512 images. I tried a specific…
      bscphil on HN
  • Slow generation with no loading indicator

    From 1 comment
    • They take too long to generate, but there is no clear indication of that. You should add a spinning mouse or other thing that shows that the server is working. (A robot paining a…
      gus_massa on HN

Requests

  • Voting and curation of images and prompts

    From 3 comments
    • In V2 we're planning to add a voting system and additional filtering/tagging to solve for a lot of these unusual/nightmareish summoned images. I for one am sorry for your…
      jarrenae on HN
    • We're going to add voting to help empower users to sort between better/worse summoned images. And an API tool for devs to leverage is planned as well.
      jarrenae on HN
    • You're spot on with the curation! I'm really exciting to add voting and weighing to the images. I think that's where this'll really start to shine. "Girl reading in a coffee…
      jarrenae on HN
  • Better tags and filtering

    From 2 comments
    • In V2 we're planning to add a voting system and additional filtering/tagging to solve for a lot of these unusual/nightmareish summoned images. I for one am sorry for your…
      jarrenae on HN
    • That's one of the things I've found deeply interesting about the current generation of tools, there's little (if any) comprehension going on, it's really just trying to "enhance"…
      jarrenae on HN
  • Non-square aspect ratios such as 16:9

    From 2 comments
    • Would love the option to not just have square images, but other formats as well (especially 16:9)
      omwow on HN
    • Spot on. In my initial sketches for the site I had vertical/horizontal sorting for images, and I think we'll be able to add that pretty quickly.
      jarrenae on HN
  • Upscaling of images

    From 2 comments
    • 512x512 is standard for SD generated images, but seems pretty low res when you look at it as a stock photo. Might be good to provide an AI upscaled version of the image for…
      needle0 on HN
    • Upsizing is something I'm really hoping to bring in the next version of the site. I'm imagining a variety of different tools to improve the images, so ideally if an image is good…
      jarrenae on HN
  • URL-based API for fetching photos

    From 2 comments
    • A simple url-argument-based API to get back a photo, similar to source.unsplash.com’s behavior would be terrific.
      bredren on HN
    • 100% Agreed on this one. I was really hoping we'd have that feature ready before launching today. Hopefully we'll have an early version up in the next week or so.
      jarrenae on HN

Questions

  • Whether Stable Diffusion output avoids copyrighted training data

    From 1 comment
    • How safe is it to use those stock photos? How sure can one be that stable diffusion does not create any copyrighted work? Is the training data all freely licenced or is there a…
      riedel on HN
  • Whether the search button and UX work on mobile

    From 1 comment
    • Having a button in the search bar that's a blue circle that says Photo, etc, and then not having it start the generation process when clicked feels odd to me. Took me about 30…
      CameronBanga on HN

Alternatives named

  • Unsplash

    From 2 comments
    • Thanks for the feedback, and I totally agree. I'd really hoped to fill out the landing page a bit more before we launched today, but we weren't able to roll it out in time.…
      jarrenae on HN
    • This is definitely a fair assessment. I think a lot of the "wow" factor is just seeing the generated images in the first place. In truth I think a lot of value will be added as…
      jarrenae on HN
  • Getty Images and Adobe Stock

    From 1 comment
    • Omg I cannot wait for human faces to become non-freaky with this technology. People pay real money to sites like Getty or Adobe (the former of which is owned by a corp that you…
      wheresmycraisin on HN
  • Lexica

    From 1 comment
    • Use the Lexica API and show images from them as well! https://lexica.art/docs
      JimWestergren on HN

Category, keywords, summaries and labels on this page were made by AI (Thread Reader v2) and not checked by hand. Each point links to the comments it came from.

Add a badge to your READMEShown on HackerShow
[![Shown on HackerShow](https://hackershow.org/badge.svg)](https://hackershow.org/show/33038117)