#Theme: A photograph displaying contrast that mirrors an aspect of reality that is splintered in a subtle way into an alternate reality.
#My Prompt in Dalle3: Create a photograph of a blossoming tree in a meadow surrounded by a forest that looks dark and gloomy. Make the photograph 16:9. The blossoming tree is secretly composed of pixels that are barely holding onto reality, splinter, broken, tortured, altered colors, surreal.
#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
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
• OP’s favorite | +1 point
• Most original | +1 point
• Last two entries (to compensate for less time to vote) | +1 point
• Prompt and workflow included | +1 point
The winner gets to pick next theme! Best inspirations for everyone and have fun!
#Past entries post: https://lemmy.world/post/13802673
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.
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.
You won! You get to pick the next round!
Hi there, i do not want to steal the win from the mighty cheesehand! If i go directly to the post on https://sh.itjust.works, cheese hand has 10 upvotes.
I think something is still wrong with lemmyworld. The cheese hand is the most upvoted with 10. Check out the host instance page https://sh.itjust.works/c/imageai
I just confirmed on the lemmyworld Matrix chat that there was a problem with some inbound events getting lost that was only resolved a couple days ago. So any lemmyworld users can't see stuff that happened during a certain time frame.
Agreed, still I can't see it. So strange.
I don't see that at all, another comment talks about not everybody being able to see everything. I changed on two apps and a laptop and I have no cheese hands...
Did you go to the link I gave instead of through the lemmyworld instance?
I did and it just brought up this thread and I don't see it there. Not sure if it's because I'm logged into the Lemmy.world instance?
Might be. You can try opening it in a private/incognito tab.
“Cheese hand” they say! 😭
First the mozzarella joke and now this. All the intended mystique and other worldly vibes, gone.
All I can see now is Cheese Hand :(
Granted, it is hard to unsee once you start thinking of cheese :)
Anyway, there has been a problem syncing with Lemmyworld. Apparently a bunch of updates are just lost. I already unpinned/pinned the posts again. So they should be properly pinned for everyone. But do let me know if something is still wrong.
Hi there! Looks like you linked to a Lemmy community using a URL instead of its name, which doesn't work well for people on different instances. Try fixing it like this: !imageai@sh.itjust.works
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.
That's really helpful! I will dig into those settings for sure now.