this post was submitted on 30 Jul 2023
27 points (100.0% liked)

AI Generated Images

7171 readers
175 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
[email protected]
[email protected]
[email protected]
[email protected]
[email protected]
[email protected]
[email protected]
27
[Community Challenge] Week 4 “Fairy Tales” (sh.itjust.works)
submitted 1 year ago by [email protected] to c/[email protected]
19 comments fedilink hide all child comments
 

This is the AI Image Generation Community Challenge post, the theme is:

Fairy Tales

Suggested here by @late_[email protected]:

https://sh.itjust.works/comment/1610760

Comment your submissions on this post.

You can submit your AI generated images to be voted on for the contest by commenting and embedding your images.

Please use "![](imgurl)" format to embed the image in the comment so users don't have to go to other websites.

You don't have to upload the image to sh.itjust.works specifically, and can use imgur links and other webhosting sites as well.

Strict simple rules to make this more enjoyable for everyone:

Contest will begin immediately when this post is made and will end the following Friday at 1pm EDT

One comment per user

3 images maximum

Must follow this community's and sh.itjust.works rules

No links to other websites, must be embedded and viewable here

The top 3 winners are the top 3 root comments with the most upvotes

The top 3 winners (9 images total potentially) will be featured as a pinned post as the contest winning images with user names

If you want to edit your image choices you must delete your old comment and make a new comment

all 20 comments
sorted by: hot top controversial new old
[–] [email protected] 8 points 1 year ago

Little red riding hood
Little Red Riding Hood, meeting the wolf in the forest.
I loved the shadow play images, unfortunately it didn’t translate as well for the other fairy tales.

PromptShadow play, big bad wolf, little red riding hood, forest, flowers

Frog
The frog prince.
I wanted to include the gold ball but the AI refused to put it in the right spot. It ended up everywhere except where it needed to be :)

PromptUkiyo - e style, frog wearing a crown, gold ball in a pond, panoramic shot

Cinderella
Cinderella dancing with her prince charming.
As fairy tale as I could get it. It’s gorgeous, I just wanted to include it.

Prompt
Oil painting style, 1800s style, cinderella, wearing blue dress and crown, dancing with the prince, at a ball

[–] [email protected] 7 points 1 year ago

Jack and the Beanstalk.

[–] [email protected] 6 points 1 year ago (2 children)

Hansel and Gretel

two children running toward a gingerbread house, candy trees

And the little red riding hood

a stylized illustration of a girl wearing a red hat in a forest with a wolf next to her and a squirrel on the other side

Although as much as I love this last image and the really cool illustration style, I'm annoyed by it because my prompt was simply "hello", meaning that I could not replicate this style if I wanted to.

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

You may be able to find an artist with a similar style here https://www.midlibrary.io/categories/illustrators

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

Ooh thank you, I didn't know about this library

[–] [email protected] 2 points 1 year ago

Those are adorable, too bad you couldn’t replicate the style. I would have loved to see a whole series of these.

[–] [email protected] 6 points 1 year ago* (last edited 1 year ago) (2 children)

It was very challenging not to get a furry red little hood. I was able to get what I wanted with some tricks. I first asked for one little red wood and a villager, without any wolf. Then I inpainted the villager into a wolf with the prompt "wolf". I liked the outfit.

Another challenging one. The model to make the background is ToonYou. I like the style. But this model does not know what a f**king mermaid is! So I inpainted a mermaid with another model (epicrealism) and the "lora:add_detail:-1" (to flatten the details).

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

Recognize this invalidates your comment from winning as per the rules. If you'd like to make a new comment then you are free to do so, but you must delete this comment as well. As for the slight mermaid nudity, I'll allow this edit for the sake of the art, but I'd prefer going no further with it.

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

Concerning the votes, maybe you should have a jury (you? three persons ?). It would be fair compared to the current voting system. You could reward only the pictures you like (not 3 pictures) based on different criterias : the overall impression, the composition, the tricky prompt/explaination of the tricky process/explaination of the issues, etc. This may invite contestants to share more than a picture ?

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

That would be interesting, but I can't dedicate more time to organizing a more in-depth challenge. You can always start a challenge of your own within the rules. The voting here isn't meant to be taken seriously beyond a fun community challenge. I just did what was simplest using the current system of upvotes/downvotes.

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

No problem. I do it to progress. (Also, the actual voting system is wonky. The early posts get more upvotes than late ones. Not that it should be taken seriously, since Lemmy allows you to rig the votes. And there are way too few votes).

[–] [email protected] 6 points 1 year ago (2 children)

Goldilocks' Rude Awakening

Midjourney provided the proper composition and SD (RealCartoon3D) jazzed it up.

The Truly Ugly Duckling

All Midjourney for this - in the style of Arthur Adams.

The Longings of Rapunzel

For this one, SDXL provided the composition and it was greatly improved with the Fruit Explosion model.

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

The ugly duckling is remarkable

[–] [email protected] 2 points 1 year ago

Thanks, it was a little difficult to get it because Midjourney kept blocking my prompts because of words like 'disfigured'. Kind of ridiculous. It was also hard to get a blonde woman in a bed without it getting blocked.

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

LOL the ugly duckling, awesome.

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

I call this one "Out for revenge". Its based on Little Red Riding Hood. Took a while to get what I wanted. At first I tried to show the wolf some how, but the AI kept making Little Red into a furry so i nixed the wolf.

Out For Revenge

Out For Revenge

Out For Revenge

Prompts and Model used

model: nightmareshaper

count: 4

guidance: 9.0

steps: 50

sampler: dpmpp_2m_karras

seed: 51072720

upscale: 2

lora1_strength: 0.7

lora2_strength: 0.7

prompt: A Vengeful angry (wavy dark red hair) (fair skin) emotional heroine wearing a (long red velvet hooded cloak cottage-core long dress with black boots) holding a (small sharp glinting silver dagger)+ (inside a dark fairy-tale forest). Nighttime, Close up, (full body portrait), fairy-tale, revenge, enchanting, teary-eyed, realistic, lifelike, real, 8k uhd, dslr, soft lighting, high quality, film grain, Fujifilm XT3, HD,

negative_prompt: ugly, tiling, poorly drawn hands, poorly drawn feet, poorly drawn face, out of frame, extra limbs, disfigured, deformed, body out of frame, blurry, bad anatomy, blurred, watermark, grainy, signature, cut off, draft, censored, ears, cleavage, exposed skin, lewd, more than two arms, more than two legs, more than two hands, merged body parts

[–] [email protected] 3 points 1 year ago* (last edited 1 year ago)

Took a while to get what I wanted. At first I tried to show the wolf some how, but the AI kept making Little Red into a furry so i nixed the wolf

Hehe. That was my issue too. The wolf's ears on the girl are driving me crazy!! STOP IT damn AI! I like this challenge because it's hard but I am making progress to get what I want.

[–] Itrytoblenderrender 2 points 1 year ago

Forest Fairy:

[–] [email protected] 2 points 1 year ago

"Oh, but, grandmother, what a terrible big mouth you have."

"The better to eat you with."