dalle.party

AI

image generation

SHOW HN2023

587points
149comments
#38of 3,109 in 2023
Top 2%of 2023 by points

How HN took it

MixedNo clear lean

40 positive, 46 neutral or asking, 2 mixed, 20 critical, out of 108 comments about the project. Thread score +0.10.

Execution: 13 for, 11 againstIdea: 16 for, 3 againstDesign: 1 for, 2 againstPricing: 2 for, 1 againstPrivacy: 0 for, 3 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

  • Fun to watch prompts drift into surreal or absurd results

    From 4 comments
    • It's pretty fun to mess with the prompt and see what you can make happen over the series of images. Inspired by a recent Twitter post[1], I set this one up to increase the…
      epiccoleman on HN
    • Here's a custom prompt that I enjoyed: "Think hard about every single detail of the image, conceptualize it including the style, colors, and lighting. Final step, condensing this…
      andrelaszlo on HN
    • Wow that meme about everything becoming cosmic/space themed is real isn't it?
      morkalork on HN
    • These are fantastic
      nathanfig on HN
  • Shadows and reflections in the images look surprisingly correct

    From 2 comments
    • The thing that is truly mindboggling to me is that THE SHADOWS IN THE IMAGES ARE CORRECT. How is that possible??? Does DALL-E actually have a shadow-tracing component?
      Blammar on HN
    • Yes! It can also get reflections and refractions mostly correct.
      jiggawatts on HN

Objections

  • Images are often noisy or wrong, with people frequently mangled

    From 2 comments
    • I randomly checked a few links here and shadows were correct in 2 images out of a dozen... and any people tend to be horrifying in many
      throwaway290 on HN
    • My results are disappoitingly noisy but I love the concept https://dalle.party/?party=bxrPClVg https://dalle.party/?party=mmBxT8G- https://dalle.party/?party=kxra0OKY (the last…
      andrelaszlo on HN
  • Rate limits and content-filter errors make runs frustrating

    From 3 comments
    • The "create text version of image" prompt matters a ton. I tried three, demo here: default ``` https://dalle.party/?party=JfiwmJra ``` hyper-long + max detail + compression -…
      epivosism on HN
    • The default limit for an account that was not used much is one image per minute, can you please add support for timeouts?
      AvImd on HN
    • I purposely gave it some weird instructions to show the progress of the universe from the Big Bang to present day Earth. It showed the 8 stages from my prompt in each image and…
      toxic72 on HN
  • Users are reluctant to paste API keys into a third-party site

    From 2 comments
    • Question: how are you protecting those API keys? I'm reluctant to enter mine into what could easily be an API Key scraper.
      rexreed on HN
    • I would never paste my API key into an app or website.
      fassssst on HN

Requests

  • Start the loop from an uploaded image rather than a prompt

    From 3 comments
    • It’d be interesting to start with an image rather than a prompt, though I am afraid of what it’d do if I started with a selfie.
      i-use-nixos-btw on HN
    • I'd like to be able to begin it with an image rather than a prompt.
      bbreier on HN
    • This is fun, thanks for sharing! It would be interesting to upload the initial image from a camera to see where the chain takes it.
      blopker on HN
  • Run it with local models or provide source code

    From 2 comments
    • Pretty interesting. I would love to see a version of this running locally with local models.
      robblbobbl on HN
    • A clever idea that I'd love to play around with, but not without a source link so I could feel better about trusting it and host it myself.
      edfletcher_t137 on HN

Questions

  • Whether the image-to-text model really understands the pictures

    From 1 comment
    • The #1 phenomenon I see here is that the image-to-text model doesn't have any idea what the pictures actually contain. It looks like it's just matching patterns that it has in…
      nerdponx on HN
  • How many iterations before the loop converges to a fixed point

    From 1 comment
    • Very cool, I'm rather curious how many iterations it would typically take for a feedback loop to converge on a stable fixed-point. I also wonder if the fixed points tend to be…
      neuronexmachina on HN

Alternatives named

  • Translation Party

    From 1 comment
    • Hey, I'm one of the creators of Translation Party, thanks for the shout out, I really like this. My co-creator had the idea to limit the number of words for the generated image…
      unclehighbrow1 on HN
  • Telestrations and Scrawl party games

    From 2 comments
    • This reminds me of the party game Telestrations where players go back and forth between drawing and writing what they see. It's hilarious to see the result because you anticipate…
      rbates on HN
    • I haven't tried this yet, but I assume its similar to a game you can buy commercially as Scrawl [1]. You pass paper in a circle and have to either turn your neighbor's writing…
      oarfish on HN
  • Pictograph family game

    From 1 comment
    • Interesting how similar this is to my family's favorite game: pictograph. 1. You start by describing a thing. 2. The next person draws a picture of it. 3. The next next person…
      indymike 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/38432486)