post pictures your computer has generated ( algorithmic art )
- Thread starter Version
- Start date
mixed_biscuits
_________________________
mixed_biscuits
_________________________
mixed_biscuits
_________________________
The only surprising thing about that pizza is that the margherita has pepperoni on it
Last edited:
mixed_biscuits
_________________________
woops
is not like other people
trip hop lp cover
mixed_biscuits
_________________________
Some really weird results from this meta request, while also censoring half its own creations:
Last edited:
Mr. Tea
Let's Talk About Ceps
Balenciaga's winter collection just drop?
Version
O9A INSIGHT ROLE
recent developments since the release of Stable Diffusion
people have discovered the Stable Diffusion img2img script: "make variations of input image"
here's a blog post showing how someone used img2img to transform their untrained ham-fisted ms paint image into sci-fi dystopia
there is also diffuse the rest
draw a crappy ms paint style picture, supply a prompt and it'll generate improved versions
the image below shows my badly drawn penguin on the left and on the right we have the AI version...
prompt: distended penguin musician
and
Stable Diffusion Animation
given a start prompt and an end prompt the program will try and interpolate between the two - it's early days, the resulting animations seem a bit clumsy
plus GIMP, Photoshop, and Blender plugins under development
people have discovered the Stable Diffusion img2img script: "make variations of input image"
here's a blog post showing how someone used img2img to transform their untrained ham-fisted ms paint image into sci-fi dystopia
there is also diffuse the rest
draw a crappy ms paint style picture, supply a prompt and it'll generate improved versions
the image below shows my badly drawn penguin on the left and on the right we have the AI version...
prompt: distended penguin musician
and
Stable Diffusion Animation
given a start prompt and an end prompt the program will try and interpolate between the two - it's early days, the resulting animations seem a bit clumsy
plus GIMP, Photoshop, and Blender plugins under development
Version
O9A INSIGHT ROLE
Midjourney seems to produce the best Cthulhu clowns
cthulhu clown, photograph by hans bellmer, in the style of H R Giger, hellish, artstation, calotype, multiple exposure, photoillustration, biomorphic, ambrotype, hand tinted
insane cthulhu clown posse, photograph by hans bellmer, in the style of H R Giger, hellish, artstation, assemblage, calotype, multiple exposure, photoillustration, biomorphic, ambrotype
nendoroid of sad cthulhu clown, figurine in the style of H R Giger, figurine in the style of hans bellmer, hellish, horror
cthulhu clown, photograph by hans bellmer, in the style of H R Giger, hellish, artstation, calotype, multiple exposure, photoillustration, biomorphic, ambrotype, hand tinted
insane cthulhu clown posse, photograph by hans bellmer, in the style of H R Giger, hellish, artstation, assemblage, calotype, multiple exposure, photoillustration, biomorphic, ambrotype
nendoroid of sad cthulhu clown, figurine in the style of H R Giger, figurine in the style of hans bellmer, hellish, horror
Version
O9A INSIGHT ROLE
some resources for Stable Diffusion prompt "engineering"
Lexica - Search over 5M+ Stable Diffusion images and prompts
useful for prompt theft
Exploring 12 Million of the 2.3 Billion Images Used to Train Stable Diffusion’s Image Generator
article detailing a project to examine what images Stable Diffusion was trained on - they've created an image browser where you can see the image and accompanying text that is in the dataset
Lexica - Search over 5M+ Stable Diffusion images and prompts
useful for prompt theft
Exploring 12 Million of the 2.3 Billion Images Used to Train Stable Diffusion’s Image Generator
article detailing a project to examine what images Stable Diffusion was trained on - they've created an image browser where you can see the image and accompanying text that is in the dataset
Version
O9A INSIGHT ROLE
AI wins state fair art contest, annoys humans
he used Midjourney to generate the image which won the category - judges were reportedly unaware that the piece was generated by AI
he used Midjourney to generate the image which won the category - judges were reportedly unaware that the piece was generated by AI
Version
O9A INSIGHT ROLE
another prompt engineering resource: an implemation of CLIP retrieval
or in another words, search for what you're looking to generate, and see what image-text pairings the AI was trained on ( this quizzes the LAION dataset which was used when training stable diffusion )
or in another words, search for what you're looking to generate, and see what image-text pairings the AI was trained on ( this quizzes the LAION dataset which was used when training stable diffusion )
Mr. Tea
Let's Talk About Ceps
What d'yall reckon to this?
www.nytimes.com
An A.I.-Generated Picture Won an Art Prize. Artists Aren’t Happy. (Published 2022)
“I won, and I didn’t break any rules,” the artwork’s creator says.
Version
O9A INSIGHT ROLE
What d'yall reckon to this?
An A.I.-Generated Picture Won an Art Prize. Artists Aren’t Happy. (Published 2022)
“I won, and I didn’t break any rules,” the artwork’s creator says.
vibe shift
Clinamenic
Binary & Tweed
I'm all for it.
futurism.com
Someone's Making an Entire Movie Using Video Generated by AI
A guy with no background in film or artificial intelligence is working on making an entire movie, in an ambitious attempt to open filmmaking to the masses.
futurism.com