Posts made by foreverlurk

@Olo said in How detailed are your size fantasies:

@littlest-lily Yup, I do the “quick sensation” daydream too. Usually just looking at my open hand, then curling my fingers and imagining how she feels against my palm. Just a few seconds away from reality.

Sorry for necroing this thread but I have to say, you have no idea how relieved I am to learn someone else do this too. I’ve been doing the exact same thing forever, so thanks for proving I’m not insane, LOL.

@Olo Very nice concept and execution!

If I’m being honest, I’ve imagined this happening to my teacher a few times while daydreaming in class, growing up

@tinycoin Thanks, glad you like them!

@SmolChlo it’s funny because that’s exactly a scenario I had in mind for another pic, but it fits this one perfectly too. Her confidence stems from being under the protection of her giant who makes sure that the other patrons (and the rest of his crew) won’t touch a hair on her head. Also, being a regular at that place, she knows for a fact they don’t have rats or cats roaming about.

Sorry for the spam but I thought these also turned out pretty good.

Some more playing around with perspective and making the AI understand the concept of size difference… not that easy sometimes, but rewarding when it does.

@SmolChlo said in Foreverlurk's AI artwork:

@foreverlurk I can’t get enough of the Epic one! His incoming hand is so massive compared to little MK

Thanks, it’s one of my favorite too!
In the movie MK is shrunk down to only an inch tall, so yeah that size difference needs to be huuuuugge.

In other news, Microsoft cranked the filtering to 11 last night on Bing Image Creator, I’m getting a lot of blocked prompts/images that were fine just yesterday (even some 100% non-sexual stuff gets blocked). I hope it’s just a bug, or overcompensation that will be fine tuned in the future, but right now just using “woman” in your prompt can be flagged.

Also… I’ve received my first hate mail for using AI art, which was to be expected, of course. I don’t really mind, but I fear some people using tactics like mass-reporting my stuff or false flagging them. I have backups of everything of course, but yeah.

Some more samples of what is possible by combining DALL-E 3, SDXL, and GIMP.

Are You Real?

Need a Hand?

Epic (2013) Alternate Ending

Still Bigger Than A Mouse

Sizeable Worry

Trust Me

Punishment

@Olo Where can I see epicillusionist’s work? His DA account seems deactivated?

https://www.deviantart.com/epicillusionist

I hope it’s not another victim of the purges.

@nephilim said in Foreverlurk's AI artwork:

@foreverlurk uh… when I download this, to where do I download? What app opens it??

Oh, well you’ll need a Stable Diffusion client, then installation depends on each one. If this isn’t clear, I recommend checking some tutorials on YT as I’m not the best person to explain how to use them, sorry.

For SD I like A1111, but that’s just one of many :
https://github.com/AUTOMATIC1111/stable-diffusion-webui

@nephilim said in Foreverlurk's AI artwork:

@foreverlurk So, if I understand correctly, StableDiffusion lets you use your own models?

Correct, you can use and train your own. There are different technique to either add to an existing model, modify concepts inside an existing model, or training a brand new one from scratch. All with their pros and cons.

There even a few publicly available models for size content:

https://civitai.com/models/151689?modelVersionId=175451
https://civitai.com/models/92200?modelVersionId=98299

@nephilim hahahaha don’t have a stroke on me!

This is pure DALL-E, which is built by OpenAI:
https://openai.com/dall-e-3

That version will be available to paying customers of ChatGPT+. Part of its strength comes from ChatGPT4 being used to parse the weights. Part of its weakness is the censorship and filtering. Another “weakness”: unlike Stable Diffusion, you require literal datacenters to run it, and you can’t train custom models.

You can use a free version right now if you have a Microsoft Account:
https://www.bing.com/create

@nephilim it really depends, but I’ve noticed that in regards to the filters I mentionned, less is more. The key is to give the mimimum information to the AI and leave the rest up to chance. More text in your prompt can add “noise”.

My basic prompt is something like :

• “realistic [illustration|render|painting|drawing|etc.] of shrunken woman, two inches tall, tiny, shrunk, [sitting|standing|sitting|etc.] on [palm of hand|table|etc.], photorealistic”

The actual inches isn’t really important, it’s more to give another weight to the idea the subject is not its normal scale. You can then add more info about the scene, like this:

• realistic illustration of shrunken woman being examined by alchemist, six inches tall, tiny, shrunk, standing on table, in medieval alchemy lab, fantasy, digital art, photorealistic

Mind you, that took about 20 tries to get something like this. You’ll get plenty of crappy results, too.

Another thing I’m trying to do is comics… I haven’t found the perfect prompt yet but I’m getting cohesion between panels, which is a great start.

• Three-panel comic, realistic illustration showing a female wizard, in a high fantasy setting. The first panel shows the woman normal sized, she casts a shrinking spell. The second panel shows her gradually getting smaller. The third panel shows her shrinking again, even smaller.*

Be aware that Microsoft is very aggressive on censorship, like I said any negative emotions or situations cannot be prompted.

@littlest-lily said in Foreverlurk's AI artwork:

I’ll be honest, I’m someone who isn’t a fan of the rise of AI art, for various personal reasons. But it warmed my heart that you were being so considerate and transparent when posting these, so thank you so much for that They do look really good!

Thanks!

And I understand completely, that’s why I put front and center that this was made using AI. There are a lot of valid reasons to oppose this tech, or AI in general.