from Hacker News

DALL-E Chess in Jungle and Dunes

by emadehsan on 7/30/22, 10:25 PM with 55 comments

• by fab1an on 7/31/22, 1:13 PM

  Amazed we haven't seen more DALL-E / Midjourney on HN. Probably the most astonishing new tech I've used since booting up a computer in the 90s.

  Just generating images is barely doing the tools justice though - you can create entire mini movies with it, like SALT (a 70s sci-fi adventure happening on Twitter): https://twitter.com/SALT_VERSE/status/1536799731774537733

  DALL-E's inpainting feature is incredibly powerful to generate very large scenes: https://twitter.com/fabianstelzer/status/1545752145273802752

  Hard to believe that we're only beginning to scratch the surface here...

• by quadcore on 7/31/22, 1:33 PM

  I dont know how artists feel about DALL-E but as an amateur I feel bad. "This should be forbidden" bad. I guess the root of this feeling is the same as the one Copilot gives OSS programmers, it feels like theft and copyright enfringement. The pictures in this case uses techniques and colors scheme widely used by illustrator in the entertainment industries. Some of them are even above the average quality and that's scary too.

  Do we know if regulators are looking into Copilot and DALL-E? To which extent do we want computer doing what human do? I mean.. Art? Feels like bad taste to me.

• by status200 on 7/31/22, 3:32 PM

  During the beta, i must have done thousands of requests and was initially blown away, but now i can tell the "look" of a Dall-e generated image... it has these weird blurry spots that make it seem like a memory of a dream - the main schema is there but if you focus on any one point, the illusion is broken. Looking forward to the day that it is so polished that I cannot differentiate it from a human art piece.

• by gus_massa on 7/30/22, 10:37 PM

  Did you use the same prompt for all the images? How much cherrypicking did you do? How many images did you generate to get this set?

• by sklargh on 7/31/22, 1:49 PM

  Does anyone know if there is a company or team focused on outputting CAD using a tool like DALL-E?

• by seestem on 7/31/22, 2:19 PM

  Is DALL-E deterministic, like if I type the same phrase it will always generate the same images?

• by dimmuborgir on 7/31/22, 2:32 PM

  Lots of weird artifacts which are very hard to fix.

  The argument that users can now generate professional grade art by bypassing artists entirely feels so strange. I have access to Dall-E. To generate images without artifacts, you have to do one of these: a) Do a lot of cherry-picking which can be expensive. b) Prompt should be about an abstract concept which can "tolerate" any number of artifacts. c) Prompt should be about a common/generic concept that you have already seen a lot of times on the internet.

  I think the biggest use case of Dall-E will be in removing creative block for artists.

• by heliophobicdude on 7/31/22, 3:16 PM

  I believe the next evolution in generative images is stringing them together!

  If you can come up with the key frames with descriptions of the same style, a neat little program can interpolate them and produce a generative movie!

• by la64710 on 7/31/22, 1:30 PM

  Somehow I find the Dall-E and othe AI generated pictures revolting … is it the choice of colors or what I don’t know? It’s like looking at an art piece without a soul ..

• by heliophobicdude on 7/31/22, 3:19 PM

  Generating images seems almost a solved problem. What’s the next big problem to solve in this space?