this post was submitted on 12 Jul 2023
52 points (96.4% liked)

AI Generated Images

7175 readers
260 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
52
Fairies in different styles (images2.imgbox.com)
submitted 1 year ago* (last edited 1 year ago) by [email protected] to c/[email protected]
 

After my rather dark dieselpunk adventures, I wanted to do something lighter and more my style :)
I've seen some really nice use of different mediums in this community before and I wanted to explore their differences. Below are several fairies, each made with a different medium in their prompt.



Description: This is the base prompt. I chose isometric because it gives a nice viewing angle.
Prompt: isometric view, a fairy sitting among flowers --ar 4:3



Description: This is a clay image. I was really amazed with this one, expecting more of a play-doh effect with a prompt like clay.
Prompt: isometric view, clay, a fairy sitting among flowers --ar 4:3



Description: This is a knitted image. Many of my attempts ended up looking rather fake, but this one turned out really well.
Prompt: isometric view, knitted, a fairy sitting among flowers --ar 4:3



Description: A paper fairy! This is one of my favorites, everything about it looks quite real.
Prompt: isometric view, paper craft, a fairy sitting among flowers --ar 4:3



Description: A porcelain fairy. This one is so nice I wish it was real.
Prompt: isometric view, porcelain, a fairy sitting among flowers --ar 4:3



Description: A tilt-shifted image. Tilt shifting is a camera technique you can use to make normal photos look like miniatures. I guess Midjourney skipped that step and turned everything in a miniature :)
Prompt: isometric view, tilt shift, a fairy sitting among flowers --ar 4:3



Description: And lastly a mix of the previous two. A tilt-shifted porcelain fairy. She looks so delicate. The tilt-shift prompt really has a strong effect.
Prompt: isometric view, porcelain, tilt shift, a fairy sitting among flowers --ar 4:3


That's it. I hope you enjoy them. Sorry if I'm a bit wordy with my posts, I like to add a personal touch with what I share.

edited because my formatting skills suck

top 9 comments
sorted by: hot top controversial new old
[–] Speckle 4 points 1 year ago

Really like these! And I don't mind the words, it's nice to have some context

[–] [email protected] 3 points 1 year ago (1 children)

Those are some great AI images, and I'm really far from loving AI generated stuff. How many attempts does it take to get a result like any of those ones?

[–] [email protected] 4 points 1 year ago* (last edited 1 year ago) (1 children)

Thank you! I consider it high praise, coming from someone who's really not into this kind of thing.

Except for the knitting one, all of them were almost an instant success. I was spoiled for choice to be honest :)
I'm guessing it's because fairies are a common enough subject to generate new pictures for. Though I did try to change the subject as well, and it still gives of nice results. This is the same porcelain prompt, but for an accountant:

Still the same style, but most likely because an accountant is not as well known to be shown in porcelain, it remained white?

Midjourney is really good when you give it the space to make it's own interpretations. I try not to make it do something very specific or I'll spend the rest of the afternoon tweaking a prompt without really knowing if I'm doing the right thing.

Sorry, a little edit because I missed something important.
The isometric view prompt does a lot of heavy lifting here. It really constrains the camera angle and position of the subject.

[–] [email protected] 2 points 1 year ago (1 children)

That's really informative. I'm kind of warming up to give image generation a try after seeing your posts. Thanks for sharing your results~

[–] [email protected] 3 points 1 year ago

You're welcome! Let me know if you have any questions, I'm always happy to help.

[–] j4k3 3 points 1 year ago (1 children)

Tilt shift is an interesting prompt I need to try now.

For something like "clay" I wish there was a way to reverse the image to see the primary sources used.

Thanks for sharing

[–] [email protected] 3 points 1 year ago

Tilt shift is an interesting prompt I need to try now.

You should! I'll be interested to see what you can make with it, if you're willing to share of course.

[–] [email protected] 1 points 1 year ago (1 children)

These are great. Which models are you using? Is there any post-processing with a Lora?

[–] [email protected] 1 points 1 year ago

They were made in Midjourney, the prompt is all it took to generate these.
I don’t know how it works in the background, but Midjourney is very good at producing consistent images.

load more comments
view more: next ›