It's my turn to set the Community Challenge for this week...
Theme
This week we're doing theme via creative constraint. Make whatever you want, you just can't use characters. More specifically, no characters, named or unnamed, from any stories, songs, games, etc. That includes mash ups.
You can definitely still have people, you can still use tropes, and even create your own totally original characters. Just no reusing existing characters, or obvious derivatives
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)
At the end of the week each post will be scored according to the following grid
Prize
Points
Most upvoted
+3 points
Second most upvoted
+1 point
Theme is clear
+1 point
OP’s favorite (me, this week)
+1 point
Most original
+1 point
Last entry (to compensate for less time to vote)
+1 point
Prompt and workflow included
+1 point
Posts that are ex aequo (tied) will both get the points
Winner gets to pick next theme! Good luck everyone and have fun!
Prompt: vistavision movie still of a sorceress wandering through a wasteland, leaning on a staff, leading a giant hamster-like creature --ar 16:9 --s 75
All hail Crochet Lord Squishy! They will destroy all who dare not to hook! (People who crochet often call themselves hookers)
Made in Dall-E via Chat GPT. I went through several prompt iterations but here is my final version: Create an image of a multicolored octopus made out of crochet who is stomping through downtown of a big city and is the size of a building, have it rampaging and knocking down buildings with military shooting at it, make it aggressive and intense with an incredibly dynamic camera angle that conveys motion and energy
Here are other versions as I went through iterations
In the beginning were the words, and the words made the world. I am the words. The words are everything. Where the words end, the world ends. You cannot go forward in the absence of space. Repeat.
Prompt: "Headshot of a Scottish woman with striking green eyes. She is in her mid 30s and wearing a tartan scarf. Light exposure across her face. She has freckles on her face and red hair. She looks interested. She is standing in front of green hills that are out of focus. Mist swirls around her. Photorealistic. Detailed textures"
I´ve deleted my first entry as i did not understand the rules correctly.
Here is the new one:
Prompt:
-- Positive: In a biomechanical landscape, a young boy with short, tousled brown hair and blue eyes, dressed in old, patched brown shorts and a grey shirt, collects glowing pebbles. Nearby, a young girl with long, neat blonde braids and green eyes, wearing a faded, worn blue dress, observes with a cautious yet curious gaze.
-- Negative: None. I made this with the new per-neg comfyui node
Prompt :
A silver spaceship, lands in the forest, at night, mysterious blue-halo, full moon on the background, high quality, canon eos 7D, photography
Negative prompt
person, low quality
Size 768 × 768px
Guidance scale 7
Steps 30
Seed 1165628483
Sampler Euler
AI model RealVisXL V2.0
As my PC starts to get to old to run XL, I used getimg.ai, the cool feature is that one call buy credits packages rather than monthly subscription, which is great for hobby usage
BingAI Prompt: create a photorealistic vistavision movie still of a a taikonaut cresting a rise on an alien planet. There is strange tentacled plant life, and odd flying creatures with 6 wings. The taikonaut is riding a giant horned capybara with a lizard tail.
(Then I used Fotor to upscale it)
For a moment I was afraid I had to think of a prompt using only emoji's, then I realized you meant the other kind of characters :)
Just for clarity, could you give some examples of what is and isn't allowed for this challenge?
Like, can you still use a prompt using "a person who..." or are we more talking landscape and object images?
Yeah you can definitely still have people, you can still use tropes, and even create your own totally original characters. Just no reusing existing characters, or obvious derivatives
Process: While browsing Artbreeder, I came upon a random pic of a model with some big sunglasses. As a joke, I fed the image back into Collager(which uses Stable Diffusion), threw some gradients over it, and used a prompt I've been throwing at stuff lately.
Prompt: 2000s pop art, i wear my sunglasses at night, so i can, so i can, keep track of the visions in my eyes
Insprired by the new Warhammer 40 K game: a corrupted follower of slaanesh
The comfyui Workflow should be embedded in the picture.
Prompt (Created with chatgpt 4.0) : A photograph-style image of an androgynous, otherworldly beautiful slaanesh boy, sitting on a throne. He is barefooted with purple, pink, and black hair, and bright pink eyes, grinning with an evil seductive expression. The throne, crafted from expensive materials, is adorned with intricate carvings and predominantly features black, purple, and pink colors. The throne room is non-Euclidean in design. He wears a cultist robe in purple, black, and pink, embellished with chaos symbols. Purple and pink tentacles are wriggling on the floor around the throne.