AI Image Generation

Kharzette

Watcher of Overs

5,337

4,067

• Jan 11, 2023

• #81

I've been restoring my old BSP libraries to life again. This is a map compiler for old quake style map editors. I primarily use quake army knife.

Anyway, one of the best ways to jazz up a map is with a nice skybox. These are 6 sided cubemaps that any face marked as "sky" projects into. They used to almost always be made in Bryce. An ancient tool some of you may remember.

Now I'm attempting to use stable diffusion. My first attempts using "panoramic forest skybox" with mostly default settings got this sort of thing:

Not very useful so I switched to mountains:

Got alot better results. Occasionally it would split vertically thusly:

Then I tried a superwide format that I could easily wrap onto 4 cubemap faces 256x4:

These got really vague and spooky and arty. I think the cause was I activated some automatic tiling checkbox.
It also seemed to want to put vertical bars as if looking out a window.

 

Kharzette

Watcher of Overs

5,337

4,067

• Jan 11, 2023

• #82

Eventually I switched from Euler A to DDIM and it makes some really nice scenery:

The real trick is going to be the top and bottom faces of the cubemaps. Bottom is rarely seen but it is nice to have.

 

• 2

Reactions: 1 users

Kharzette

Watcher of Overs

5,337

4,067

• Jan 11, 2023

• #83

Here's some "forest, looking straight up at the sky". I had to go 512x512 as 256 doesn't seem to be big enough for it to work with:

 

• 1

Reactions: 1 user

Kharzette

Watcher of Overs

5,337

4,067

• Jan 11, 2023

• #84

This vid has it figured out. There's a pluging + using monoscopic 360 vr seems to be the key.



This gets me results like:

So have to figure out how to convert that into a cubemap

found this:

Panorama to Cubemap

Convert a 360° panorama to a cubemap.

jaxry.github.io

 

• 1

Reactions: 1 user

Bandwagon

Kolohe

<Silver Donator>

24,244

65,186

• 
• 
• 
• 
• 

• Jan 11, 2023

• #85

Kharzette said:

This vid has it figured out. There's a pluging + using monoscopic 360 vr seems to be the key.



This gets me results like:

View attachment 452594
So have to figure out how to convert that into a cubemap

found this:

Panorama to Cubemap

Convert a 360° panorama to a cubemap.

jaxry.github.io

Click to expand...

I use autopano giga and panotours pro at work to turn panos into cubemaps. They went out of business. You could probably find a pirated version

 

Kharzette

Watcher of Overs

5,337

4,067

• Jan 11, 2023

• #86

That github thing is not too bad! I don't have it in game yet but these are the faces for a mountain set:

Makes you want to mine some iron ore!

 

• 1

Reactions: 1 user

Pasteton

Blackwing Lair Raider

2,733

1,918

• Jan 12, 2023

• #87

anyone keeping tabs on ai porn? Lots of advancements lately had really impressive results putting celebrity faces on some 5ways etc. you can obviously tell it’s fake but it’s waaay better than it used to be

 

Kharzette

Watcher of Overs

5,337

4,067

• Jan 14, 2023

• #88

Here's what the above mountain box looks like in my map build tool in a semibroken map:

 

C

Captain Suave

Caesar si viveret, ad remum dareris.

5,250

8,950

• Jan 14, 2023

• #89

"Deepfakes" headline is clickbait. Actual tool does super-nifty stylistic transformation on source image/video based on secondary input.

At the exponential rate these things are rolling out I have NO idea what the future of media is going to look like in 10-15 years.

 

• 3

Reactions: 2 users

Kharzette

Watcher of Overs

5,337

4,067

• Feb 5, 2023

• #90

Here are some experiments with various models with the prompt "videogame mmo fantasy cover art"







This one I did properly with ffmpeg. The previous I was lazy and just used an irfanview slideshow captured with obs

- YouTube

Enjoy the videos and music that you love, upload original content and share it all with friends, family and the world on YouTube.

youtu.be

 

Last edited: Feb 5, 2023

• 1

Reactions: 1 user

Ravishing

Uninspiring Title

<Bronze Donator>

8,456

3,577

• Feb 6, 2023

• #91

Captain Suave said:

"Deepfakes" headline is clickbait. Actual tool does super-nifty stylistic transformation on source image/video based on secondary input.

At the exponential rate these things are rolling out I have NO idea what the future of media is going to look like in 10-15 years.

Click to expand...

There is a flood of AI Art is using a method like this.

Source: Figure to Real 3

Source: Figure to Real

 

• 1

Reactions: 1 user

pharmakos

soʞɐɯɹɐɥd

<Bronze Donator>

16,305

-2,234

• Feb 6, 2023

• #92

Mostly stuff from my series I attribute to The Ghost of Salvador Dali, but lots of other artists represented as well, and mashups of artists (this top one is from the prompt "painting collaboration between Salvador Dali and Alex Grey, for example. And a little ways into that first gallery are a series of Dali / Yoshitaka Amano mashups, a Van Gogh mashup, a couple of my favorite recent mashup -- Salvador Dali and Lisa Frank lol)



















There were supposed to be 10 full galleries like this, but uploading to Imgur from mobile can lead to a lot of errors and I sort of gave up lol. I need to collect them all onto my laptop and filter out duplicates anyway. Will complete my collection soon.

 

Last edited: Feb 6, 2023

• 1

Reactions: 1 user

pharmakos

soʞɐɯɹɐɥd

<Bronze Donator>

16,305

-2,234

• Feb 8, 2023

• #93

Getty Images is Suing Stable Diffusion for a Staggering $1.8 Trillion

The numbers involved are mindblowing.

petapixel.com

"Getty Images is Suing Stable Diffusion for a Staggering $1.8 Trillion"

 

• 5

Reactions: 4 users

Bandwagon

Kolohe

<Silver Donator>

24,244

65,186

• 
• 
• 
• 
• 

• Feb 8, 2023

• #94

pharmakos said:

Getty Images is Suing Stable Diffusion for a Staggering $1.8 Trillion

The numbers involved are mindblowing.

petapixel.com

"Getty Images is Suing Stable Diffusion for a Staggering $1.8 Trillion"

Click to expand...

lol....

“While some of the output generated through the use of StableDiffusion is aesthetically pleasing, other output is of much lower quality and at times ranges from the bizarre to the grotesque. Stability AI’s incorporation of Getty Images’ marks into low quality, unappealing, or offensive images dilutes those marks in further violation of federal and state trademark laws.”

Click to expand...

 

• 4

Reactions: 3 users

pharmakos

soʞɐɯɹɐɥd

<Bronze Donator>

16,305

-2,234

• Feb 8, 2023

• #95

We are living in the Uncanny Valley these days

 

• 1

Reactions: 1 user

pharmakos

soʞɐɯɹɐɥd

<Bronze Donator>

16,305

-2,234

• Feb 14, 2023

• #96

"The Philosophical Ramifications of Quantum Reckoning (or, the Chaos that the Observer has Wrought)" by the Ghost of Salvador Dali, as conveyed through Stable Diffusion 2.1

 

• 1

Reactions: 1 user

pharmakos

soʞɐɯɹɐɥd

<Bronze Donator>

16,305

-2,234

• Feb 14, 2023

• #97

"The Reality of our Extraterrestrial Rulers, as Revealed to Enoch Trismegistus" by the Ghost of Salvador Dali

 

• 1

Reactions: 1 user

Kharzette

Watcher of Overs

5,337

4,067

• Feb 17, 2023

• #98

Good site for grabbing models Civitai | Stable Diffusion models, embeddings, hypernetworks and more

 

• 1

Reactions: 1 user

Kharzette

Watcher of Overs

5,337

4,067

• Feb 21, 2023

• #99

ControlNET and Stable Diffusion: A Game Changer for AI Image Generation

New technology brings unprecedented levels of control to Stable Diffusion

bootcamp.uxdesign.cc

Might try the pose detection stuff. Curious if I can extract it in a usable form, like bvh or bip or something

Hmm the pose model is 5 gigs. Probably too much for my poor old 980 4gig card.

 

Last edited: Feb 21, 2023

Kharzette

Watcher of Overs

5,337

4,067

• Feb 21, 2023

• #100

We helped Rob learn inpainting. The mouth worked well but he had a really hard time with the hand.

 

• 1

Reactions: 1 user