Prompt: a distortion in the fabric of space and time, photo of a hand which devolves and transitions into twisted fractal dimensions at the edges --ar 4:3
I tried to do subtle, but I guess I'm just not the subtle type :)
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:
Prompt: a distortion in the fabric of space and time, photo of a hand which devolves and transitions into twisted fractal dimensions at the edges --ar 4:3
I tried to do subtle, but I guess I'm just not the subtle type :)
And a couple of runner-ups:
I'm really bad these kinds of technical challenges, but it was fun to try.
This looks rad! Quite spooky as well
Thanks!
Beautiful and disgusting at the same time. I don't want to look at it but I can't look away.
Yea, sorry about that.. It wasn't my intention to turn to body horror, but I do love the end result.
Like happy trees, no accidents, just happy terrifying visages!
Ever dipped your hand into a pot of heated mozzarella?
not THAT hot!
I mean.. erm... no.. never..
Prompt:the world slowly splintering into fragments, city being ripped apart on the molecular level shot on 70mm film stock --v 6.0
I had a feeling that Stable Diffusion wouldn't be able to generate what I was looking for, and I was right. So I turned to Dalle, which gave me some okay, but bland images. Then I took ideas from those and went to MidJourney where I got some beautiful images, but just not quite right. But I got some more stylizing ideas from those. Back to Dalle and got a good, but still bland image. Now it's SD to the rescue!
I started with inpainting the the surrounding cityscape bit by bit using one of my favorite realistic models Photon. Then with the Unstable Diffusers Nihilmania SDXL model, I proceeded to fix up the crack in the street. First the outline of the cracks, and then the inside with the Pixel Art XL lora.
Original Dalle prompt:
realistic digital art, a deserted city street at dusk, shimmering with the soft glow of street lamps, parts of the asphalt crack wide open, subtly revealing bright, pulsating binary code beneath, widescreen aspect ratio
Digimon vibes
Holy crap that's beautiful! I clearly still have so much to learn.
Thanks! Endless youtube videos and experimentation for a year help a bit
Am still early in that cycle then! I hope to be there soon.
Btw, I forgot to mention that the pixels of the tree being pulled away looks really cool.
Considering the syncing problems with lemmy.world, I've recalculated the scores. Taking @BallShapedMan@lemmy.world's scores for workflow, most original and favorite into account.
| Name | Image | Upvotes | Awards | Points | Upvote score | Total score | |
|
| ------- | ------ |
| ------------ | ----------- | | @thelsim@sh.itjust.works | Cheese Hand | 10 |Workflow, Most Original, Most upvotes | 2 | 3 | 5 | | @theUnlikely@sopuli.xyz | Road pixel crack | 9 | Workflow, 2nd most upvotes | 1 | 2 | 3 | | @3volver@lemmy.world |Splintered window | 8 | Workflow, 3rd most upvotes | 1 | 1 | 2| | @dumbass@lemy.lol | City torn apart | 7 | Workflow | 1 | 0 | 1 | | @merde@sh.itjust.works | Angry Sailor Moon | 7 | | 0 | 0 | 0 | | @Itrytoblenderrender@lemmy.world | False Vacuum | 6 | Workflow | 1| 0 |1| | @WhatsHerBucket@lemmy.world | Matrix Moon | 5 | Last Two entries, Workflow | 2 | 0 | 2 | | @M0oP0o@mander.xyz | Semi-aged Sailor Moon | 5 | Workflow | 1| 0 | 1 | | @cloudless@lemmy.cafe | Double exposure city | 5 | Last two entries, OP Favorite, Workflow | 3 | 0 | 3 | | @allo@sh.itjust.works | Witch | 5 | Workflow | 1 | 0 | 1 | | @Halcyon@discuss.tchncs.de | Interconnected | 4 | Workflow | 1 | 0 | 1 |
@BallShapedMan@lemmy.world, can you see if these scores are correct with the upvotes I've provided?
glass windows reflection, splintered reality fracture, realistic realism photograph, graffiti on abandoned broken building city wall in London downtown, (farm land), portal crack, half pixel, rainbow fractal split cut in half, oil on canvas paint, angelic, surreal abstract (((digital crisp definition fragmented fragment crack))), beautiful jungle plants, (fractal pixel art style, corrupted rift), high definition, 4k ultra quality, innovative, experimental, intricate detail, sublime, vivid colors, warm light
The colors are fantastic!!
voilà, I've joined the evil forces of moo & poo!
chosen over
no "alternate reality" in this one :/
Nooooooo! Now there's two of them! :)
I remembered an article about False Vacuum (Wikipedia) when i thought about this challenge. We see the remains of an alternate reality, condensed to this little "Stone" by the pressure of our reality.
Made with comfyui, using outpainting. The workflow should be embedded in this picture (Catbox).
Details
Prompt:
Model
The generation Process of the Base Image needs only 6 Steps at a CFG of 3 Thanks to the turbo Model.
The Outpainting needs 60 Steps and a CFG of 8.
workflow should be embedded into the picture
Unfortunately, I think lemmy strips the metadata as a safety precaution so people don't accidentally share their GPS coordinates when posting photos from their phones. A third party file sharing host is often used for sharing images with workflows intact, such as Google Drive, Catbox, etc.
Thank you for this valuable info. I did not realize this and should have tested this. I will put the original image in the post.
Edit: I´ve added the original image via Catbox in the top Post.
Gorgeous!
Help me understand how you know how many steps are required if you wouldn't mind. I use A1111 but have always left the steps at the default setting.
Short Answer: It depends on the model, the sampler you choose and the scheduler.
In my experience: the more steps you use , the more detail you get but with diminishing returns the higher you go with your step count. Also the more steps, the more generation time (and room heating) you have.
We also have now the "Turbo" Models which generate good images at a relatively low step count. For the turbo Models, you are a bit restricted regarding scheduler and sampler., but you get a detailed description for the model on the civitai Page. For example the civitai Page (CIVIT AI) of the model used for this Picture.
For the "normal" (SDXL in this case) Models: Tiral and error. I normally use a xy Plot to check things like CFG Scale or Steps out.
Here an example XY Plot for the Model SDXLFaetastic_v24. Testing different CFG Values and Steps with a constant sampler and scheduler. I´ve used the same Prompt as for the base image for the contest picture (Screenshot of the Plot, the original Image has 120MB:
Sample XY Plot
Full Picture (Catbox 120MB)
In the original Plot you see differences at different step counts.
🤯, I thought for sure my knowledge of these tools was getting to be complete. I have so much more to learn! I'm excited. Thank you!
I´ve added the 120 MB xy Plot via Catbox into the comment above. Thanks to @theUnlikely@sopuli.xyz for the info that catbox exists.
just a cute little entry. Let's see what happens! :)
spoiler
prompt: mythic superwitch that eternally curses the entire area if downvoted for the third week in a row, (fracturing reality), (((absolutely beautiful))), ((ripping apart reality to get her way)), (crushing insignificant humans), (((haunting))), (((chilling))), (((foreboding))), Illustration, ((escalating vengeance)), (spreading decay)
a double exposure photo of shops in Times Square, New York. The main image is modern day, but the faint double exposure is from around 1900
Great concept idea!
Wow, this was tricky to find since it’s not stickied!
Here is the outcome of a lot of tweaks that started with the prompt in Dalle: “create an ultra detailed image of New York City with a glitch in the matrix”.
I'm guessing there is a problem with federation to lemmy.world. Another user from that instance is having the same problem. Check the home instance of this community at https://sh.itjust.works/c/imageai. It also shows as pinned on the sopuli.xyz instance.
The matrix like effect with the moon and the city is chefs kiss!
Not subtle, but I like it.
Prompt in the bingilator (first try but did 9 overall): A half harvest moon sailor moon. one half is a old black and white picture, the other a cartoon.
Looks great, I'm still confused on the Sailor Moon love. I missed the wave due to my age but my brothers had friends who loved her.
i have no idea what sailorMoon is 😁
Even Naruto was a mystery for me till 2 years ago when i sat down and read the manga (upto a point!) in order just to understand the kids, why they run with their arms backwards 🤷 + all the other references on popular media
i guess i'll do the same soon with sailorMoon too
I should do the same. But my kids never got into this person, I did all the others except Sponge Bob. The media I strictly prohibited when I was around, that laugh... Torture has to be less painful than that!
🎶Gotta get in tune with Sailor Moon.
'Cause that cartoon has got the boom anime babes.
That make me think the wrong thing 🎶
We're interconnected - good chemistry
Prompt @ Dall-E:
A photorealistic portrait of a woman and a man standing front to front at the edge of a forest, looking at each other, their skin is partly composed of subtle tiny molecules. It is visible that through the molecules they are interwoven with nature and the forest and everything. The image is displaying the connection between the human reality and the world of chemistry.
oh 💩! this won't be easy 🙂
you worked for a month to get sd to do that.
The theme is the means and not the end.