AI Generated Images

Prompt: A woman showing off her multiple fingers --ar 4:3 --v 6.1

Theme

It's time to forget all you've learned on how to make believable images and go back to the jankiness of older AI images. We have all seen it, the weirdness AI can create when you least want to. But for this week's theme, try to create an image with the AI mistake (extra fingers, weird posture, you name it) as it's main attraction.

Embrace the jank and turn it into something beautiful! :)

A bonus point can be earned by anyone who can make their image without explicitly describing the weirdness they want to see in the prompt. Just like when you don't want to see these kinds of fails. For example: If you try to create a man with multiple legs, then a man with three legs wouldn't count, but a man running really fast with his legs would. Consider it an extra challenge to see how well you know your model and if you can push it exactly to the desired breaking point :)

As before, take your time! Some of you can be super fast (me included) and I've noticed that the early bird usually catches the worm. So for this challenge I'm subtracting a point for anyone who posts within 24 hours.

Rules

• Follow the community’s rules above all else
• One comment and image per user
• Embed image directly in the post (no external link)
• Workflow/Prompt sharing encouraged (we’re all here for fun and learning)
• Posts that are tied will both get the points
• The challenge runs for 7 days from now on
• Down votes will not be counted

Scores

At the end of the challenge each post will be scored: | Prize | Points | |---|---| | Most upvoted | +3 points | | Second most upvoted | +2 point | | Third most upvoted | +1 point | | Most original | +1 point | | AI jank present | +1 point | | No explicit AI jank instructions in prompt | +1 point | | Last two entries (to compensate for less time to vote) | +1 point | | Prompt and workflow included | +1 point | | Post within 24 hours | -1 point |

It's a bit of a different challenge, but I hope you'll enjoy it!

The winner gets to pick the next theme. As always, have fun everyone! Previous entries

(Not in response to the previous post; it’s an honest weird coincidence)

!Honorable Mention

Prompt Text:

4k photo of a diorama depicting a coastal town lighthouse. A detailed woman stands waiting. She watches a tiny distant ship on stormy glass horizon. Well lit distant lighting posed out of focus. Figurine windy woman has wind blown pose. Modest clothes ruffle. Model trees.

Bing

Bing

I made this image by prompting Flux-dev with the Image, Decision and Fifth Yao texts from the 64th hexagram (Wei Ji) in Alfred Huang's translation of the I Ching.

Bing

edit: this was just to study region-specific prompting

strangely when the guidance is low (2), the result is closer to what was prompted

of course, every model had its own ideas about what a soccer ball may be. I started with "football" but that gave some american results

Bing

Prompt: cat wearing an army helmet, driving in a large cardboard tank with threads and a gun turret made from a cardboard tube, down a busy sidewalk, natural lighting --ar 4:3 --v 6.1

This was one of the final contesters for a logo for an app I've made. It's really cool being able to create a logo yourself even if you lack the necessary graphical skills.

Had too much fun making AI jank for the contest.

Bing

I'm trying to generate an image and I've tried a few generators. Out of the 10 or so I've tried, only Leap will actually place items where I want them.

Eg: vaporwave wireframe mountains with a purple sun in the upper right corner of the image

Most of the time every generator will put the sun in the middle of the image.

Is it a matter of being bad at asking for what I want? Is it just that most of them won't follow simple commands about where things should go?

Any advice would be greatly appreciated!

Bing

Using copilot: > generate and image of Shrek opening a can of beans, but unexpectedly Mac & cheese flies out and lands on the donkey

Unholy union of ai memes