this post was submitted on 03 Jan 2024
607 points (93.5% liked)

Technology

58055 readers
4884 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 content.
  3. Be excellent to each another!
  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, to ask if your bot can be added please contact us.
  9. Check for duplicates before posting, duplicates may be removed

Approved Bots

founded 1 year ago
MODERATORS
L3s@lemmy.world
enu@lemm.ee
L4s@lemmy.world
fry@fry.gs
L3s@fry.gs
enu@lemmy.world
L4s@fry.gs
607
AI-generated images now appearing in Google image search results (lemmy.ml)
submitted 8 months ago by heyfrancis@lemmy.ml to c/technology@lemmy.world
142 comments fedilink hide all child comments
 

Found it first here - https://mastodon.social/@BonehouseWasps/111692479718694120

Not sure if this is the right community to discuss here in Lemmy?

you are viewing a single comment's thread
view the rest of the comments
[–] helenslunch@feddit.nl 8 points 8 months ago (1 children)

They need AI to detect the AI images

[–] wewbull@feddit.uk 0 points 8 months ago (3 children)

This is why Stable diffusion images are digitally watermarked. To avoid training it on itself.

[–] zwaetschgeraeuber@lemmy.world 3 points 8 months ago (1 children)

Thats not how it works at all

[–] wewbull@feddit.uk 0 points 8 months ago* (last edited 8 months ago) (1 children)
[–] zwaetschgeraeuber@lemmy.world 2 points 8 months ago (1 children)

thats almost a year old. and their github 2 years. also i did train multiple loras with only ai generated images with sd1.5 and XL without any issue

[–] wewbull@feddit.uk 2 points 8 months ago (1 children)

It's not that you can't train using generated images, but the watermarking is there to allow you to filter training data for them.

[–] zwaetschgeraeuber@lemmy.world 1 points 8 months ago

Still its neither implemented in a1111,fooocus and comfyui. I acknowledge, it exists and certainly works, but was not adapted by any tool i know of

[–] verity_kindle@sh.itjust.works 1 points 8 months ago (1 children)

I have the option to download the images I created with Stable Diffusion with or without a watermark overlay.

[–] helenslunch@feddit.nl 1 points 8 months ago

I imagine there are lots of reasons.