this post was submitted on 22 Dec 2023
83 points (91.1% liked)

Technology

72956 readers
2674 users here now

This is a most excellent place for technology news and articles.


Our Rules


  1. Follow the lemmy.world rules.
  2. Only tech related news or articles.
  3. Be excellent to each other!
  4. Mod approved content bots can post up to 10 articles per day.
  5. Threads asking for personal tech support may be deleted.
  6. Politics threads may be removed.
  7. No memes allowed as posts, OK to post as comments.
  8. Only approved bots from the list below, this includes using AI responses and summaries. To ask if your bot can be added please contact a mod.
  9. Check for duplicates before posting, duplicates may be removed
  10. Accounts 7 days and younger will have their posts automatically removed.

Approved Bots


founded 2 years ago
MODERATORS
top 5 comments
sorted by: hot top controversial new old
[–] Swarming@lemmy.world 14 points 2 years ago (3 children)

Midjourney is already by far the best imo. Never managed to get results out of the others anywhere near as good.

[–] Grimy@lemmy.world 11 points 2 years ago* (last edited 2 years ago)

It has a great quality to it's photos but it seems to be the less controllable out of all them. There's also a filter.

Stable diff is free, open source, highly controllable and has video now. No contest in my opinion.

[–] simple@lemm.ee 6 points 2 years ago (1 children)

It's fantastic in most areas but it has a certain style to it. It struggles to make simpler art in my experience and always ends up hyperdetailed.

[–] Swarming@lemmy.world 3 points 2 years ago

Yeah it may depend what you're after. I always use it for illustrations/paintings, sometimes anime but other times for artwork, concept art, landscapes in different painted styles and it works really well for that

[–] Gutless2615@ttrpg.network 5 points 2 years ago* (last edited 2 years ago)

Hard disagree. It certainly has strengths and outperforms Dalle3 in some ways but in other ways Dalle3 is still the best handler of text and prompt interpretation. And neither have the flexibility of stable diffusion/SDXL