this post was submitted on 06 Oct 2023
355 points (98.1% liked)

AI Generated Images

7136 readers
412 users here now

Community for AI image generation. Any models are allowed. Creativity is valuable! It is recommended to post the model used for reference, but not a rule.

No explicit violence, gore, or nudity.

This is not a NSFW community although exceptions are sometimes made. Any NSFW posts must be marked as NSFW and may be removed at any moderator's discretion. Any suggestive imagery may be removed at any time.

Refer to https://lemmynsfw.com/ for any NSFW imagery.

No misconduct: Harassment, Abuse or assault, Bullying, Illegal activity, Discrimination, Racism, Trolling, Bigotry.

AI Generated Videos are allowed under the same rules. Photosensitivity warning required for any flashing videos.

To embed images type:

“![](put image url in here)”

Follow all sh.itjust.works rules.


Community Challenge Past Entries

Related communities:

founded 1 year ago
MODERATORS
355
Forest (lemmy.world)
submitted 1 year ago* (last edited 1 year ago) by myfaceistupid@lemmy.world to c/imageai@sh.itjust.works
 

Generated using SD1.5 RealisticVision Checkpoint. Additional "effects" were achieved using qrcode monster controlnet model.

top 17 comments
sorted by: hot top controversial new old
[–] finn_der_mensch@discuss.tchncs.de 47 points 1 year ago (1 children)
[–] RotaryKeyboard@lemmy.ninja 17 points 1 year ago

This is absolutely brilliant! I’ve tried to get results like this With starter images, but I have gotten nothing as nuanced and subtle as this! Great work!

[–] sixCats@lemmy.dbzer0.com 14 points 1 year ago (1 children)

It’s not just me right? If I squint I see a skull? Very cool

[–] itwasawednesday@lemmy.world 7 points 1 year ago

Stand well back from the screen if on a pc, like at thumbnail size it's actually exceptional.

[–] topinambour_rex@lemmy.world 10 points 1 year ago (1 children)

What kind of prompt do you use for such result ?

[–] rikudou@lemmings.world 7 points 1 year ago (1 children)
[–] myfaceistupid@lemmy.world 7 points 1 year ago (1 children)

The effect was achieved using qrcode monster controlnet model

[–] jon@lemmy.tf 2 points 1 year ago (1 children)

What settings are you using to get it this subtle, and have a full background? Most of my outputs wind up with only the controlnet image filled in, and solid backgrounds. Invert preprocessor doesn't help...

[–] myfaceistupid@lemmy.world 2 points 1 year ago

This image was made using Automatic 1111.

Controlnet model is qrcode monster: https://huggingface.co/monster-labs/control_v1p_sd15_qrcode_monster

Settings used is: Pixel Perfect, Balanced, control weight: 1.2

The controlnet image was a photo of skull i found on google that I applied a black and white filter to.

[–] alucard@sopuli.xyz 8 points 1 year ago

Grimms’ Fairy Tales are strong with this one

[–] Fjern@lemmy.world 8 points 1 year ago (2 children)
[–] Blackdoomax@sh.itjust.works 2 points 1 year ago

Yeah, that's the weak part of the picture.

[–] Usernameblankface@lemmy.world 7 points 1 year ago

Ah, neat picture. Well done faces.

Scrolls

WAIT.

Scroll back.

squint

What WHAT? Ok, that's awesome.

[–] lwe@feddit.de 5 points 1 year ago

This one is fantastic. Dark, but fantastic.

[–] TropicalDingdong@lemmy.world 2 points 1 year ago

I am not getting this good of results with controlnet.