Masthash

#txt2img

bruno caldas vianna
1 month ago

#aiart #txt2img #srñtablediffusion
Dear stable diffusion,

The things I'm looking for do not have a name poem by Hilda Hilst on a street post / as coisas que eu procuro não tem nome poema de Hilda Hilst num poste

Why are text to image AI models (#StableDiffusion or #MidJourney) so bad at creating hands or faces? Any research/explaination on this area? #MachineLearning #ML #txt2img

#stableDiffusion #AI #txt2img
I have just finished this #experiment, in which 310 pictures have been generated with the same seed, only difference is the amount of samples, which increased progressively from 1 to 310.

These generations have then been upscaled using the realest-general-x4v3 upscaler model and #ComfyUI as software.

This the result:
https://youtu.be/hU4MyESWnm0

#AIart #denoising #Realesr #Dreamshaper

tiago
7 months ago

Daisies in a glass jar.

Two versions of the same shading algorithm.

#generative #mastoart #txt2img

Daisies in a glass jar.
Daisies in a glass jar.
tiago
7 months ago

Sunflowers in a jar. (One more.)

Testing with color. New shading algorithm. Better consistency with the line drawing algorithm, much more control on the shading regions and properties (based on txt2img model)

#generative #mastoart #txt2img

Sunflowers in a jar.
tiago
7 months ago

Sunflowers in a jar.

Testing with color. New shading algorithm. Better consistency with the line drawing algorithm, much more control on the shading regions and properties (based on txt2img model)

#generative #mastoart #txt2img

Sunflowers in a jar.
tiago
8 months ago

Moriana.

This piece was produced with a line drawing original algorithm from the output of a txt2img model.

#genart #generativeart #mastoart #penplotter #ItaloCalvino #txt2img

Moriana.
tiago
8 months ago

Clarice.

This piece was produced with a line drawing original algorithm from the output of a txt2img model.

#genart #generativeart #mastoart #penplotter #ItaloCalvino #txt2img

Clarice.
Lord Caramac the Clueless, KSC
9 months ago

@Bianca Diese Modelle können auch alle nicht zählen, sondern merken sich nur statistische Informationen über die ungefähre Größenordnung von Dingen. Deshalb haben Menschen da oft sechs oder vier Finger an einer Hand, manchmal auch sieben oder drei.

Stable Diffusion ist sich auch überhaupt nicht sicher, wieviele Mitglieder die Beatles haben, alles zwischen drei und acht habe ich schon gesehen, und manchmal bestehen die Beatles aus zwei John Lennons, drei Paul McCartneys und drei Durchschnittsbeatles, die nicht wie irgendein bestimmter Beatle aussehen, allen irgendwie ähneln und nicht identisch sind...

#aiart #stablediffusion #midjourney #dalle #txt2img

Lord Caramac the Clueless, KSC
9 months ago

@Bianca Eben nicht. Das Ding ändert keine Bilder ab, die man nicht explizit als Seed reinfüttert, sondern nimmt im Normalfall einfach blankes Zufallsrauschen als Ausgangspunkt und ändert es ab, bis daraus ein Bild wird. Diese diffusionsbasierten AIs lernen tatsächlich den Stil der Bilder, mit denen man sie füttert, und merken sich die Bilder selbst nicht. Wenn man einem solchen System sagt, es soll ein bestimmtes Bild reproduzieren, mit dem es gefüttert worden ist, liefert es ein Ergebnis, das meist mehr oder weniger nah am Original ist, aber keine Kopie, sondern eine Neuinterpretation.

Die Bilder, mit denen ein Bildgenerator trainiert wird, sind am Ende eben nicht Teil des neuronalen Modells, sondern nur aus diesen Bildern abgeleitete statistische Informationen über Objekte und Strukturen in diesen Bildern. Das wäre auch ziemlicher Irrsinn, denn dann wäre die fertige AI nicht wirklich kleiner vom Speicherbedarf her als die Gesamtheit all dieser Bilder, aber üblicherweise hat man fertige Modelle, die um etliche Größenordnungen kleiner sind als die Bilder aus dem Training. Wenn nicht, hat man irgendetwas falsch gemacht.

Was diese Dinger machen, sind keine Collagen aus vorgefertigten Elementen, sondern eine Rekonstruktion von Strukturen aus dem Nichts gemäß von maschinell erlernten statistischen Wahrscheinlichkeiten.

#aiart #stablediffusion #midjourney #dalle #txt2img

tiago
9 months ago

Portrait of a young woman aux trois crayons from a txt2img output, other study. #wip #generative #generativeart #mastoart #txt2img

Portrait of a young woman aux trois crayons.
tiago
9 months ago

Portrait of a young woman aux trois crayons from a txt2img output, Maximilian Pirner inspired ;) more work needed. #wip #generative #generativeart #mastoart #txt2img

Portrait of a young woman aux trois crayons.
Lord Caramac the Clueless, KSC
9 months ago

@kriegundfreitag Ich weiß gar nicht, was alle haben - ich pixle schon digitale Bilder seit 1988, und seit es neuronale Netze gibt, die interessante Bilder produzieren (also seit #deepdream mit den #puppyslugs und komischen LSD-Hallus), benutze ich auch die. #txt2img ist ein interessantes Werkzeug, das sich auch gut mit anderen digitalen Techniken kombinieren läßt. Manchmal male und zeichne ich auch mit Acryl oder Bleistift, aber am Ende digitalisiere ich das meist und bearbeite es mit #GIMP und #Krita weiter. Ich habe mal spaßeshalber ein paar surrealistische Buntstiftzeichungen von mir hochgeladen und daraus neue in meinem Stil generieren lassen, das sieht nicht schlecht aus.

tiago
9 months ago

The vanishing shadow robot.

This piece was produced with a
original line drawing algorithm, generative guided, from the output of a txt2img model.

#lineism #generative #generativeart #mastoart #txt2img

The vanishing shadow robot.
tiago
9 months ago

The vanishing shadow robot.

This piece was produced with a
original line drawing algorithm, generative guided, from the output of a txt2img model.

#lineism #generative #generativeart #mastoart #txt2img

Robot.
tiago
9 months ago

The end (III)

This piece was produced with a original line drawing algorithm, generative guided, from the output of a txt2img model.

#lineism #generative #generativeart #mastoart #txt2img

tiago
9 months ago

The end (II).

This piece was produced with a original line drawing algorithm, generative guided, from the output of a txt2img model.

#lineism #generative #generativeart #mastoart #txt2img

tiago
9 months ago

The end.

This piece was produced with a original line drawing algorithm, generative guided, from the output of a txt2img model.

#lineism #generative #generativeart #mastoart #txt2img

Woman looking at the end.
tiago
9 months ago

A variation on a theme drawn a few days back. Returning home, seems like it. Houses with lots of doors is always confusing.

#lineism #generative #generativeart #mastoart #txt2img

tiago
9 months ago

A variation on a theme drawn a few days back. Returning home, seems like it. Houses with lots a doors is always confusing.

#lineism #generative #generativeart #mastoart #txt2img

tiago
9 months ago

Bell flowers.

This piece was produced with a original line drawing algorithm, generative guided, from the output of a txt2img model.

#lineism #generative #generativeart #mastoart #txt2img

This piece was produced with a original line drawing algorithm, generative guided, from the output of a txt2img model.

#lineism #generative #generativeart #mastoart #txt2img
tiago
9 months ago

Hermit.

This piece was produced with a original line drawing algorithm, generative guided, from the output of a txt2img model.

#lineism #generative #generativeart #mastoart #txt2img

Hermit.
tiago
9 months ago

Old house.

This piece was produced with a original line drawing algorithm, generative guided, from the output of a txt2img model.

#lineism #generative #generativeart #mastoart #txt2img

Old house.
Old house.
tiago
9 months ago

Old house.

This piece was produced with a original line drawing algorithm, generative guided, from the output of a txt2img model.

#lineism #generative #generativeart #mastoart #txt2img

Old house.
tiago
9 months ago

Woman seated.

This piece was produced with a original line drawing algorithm, generative guided, from the output of a txt2img model.

#lineism #generative #generativeart #mastoart #txt2img

Woman seated.
tiago
9 months ago

marginalia: experiences with generative pen plot drawings and algorithms
#nftart #nft #tezos #generative #lineism #txt2img #objkt

tiago
9 months ago

Woman seated.

This piece was produced with a original line drawing algorithm, generative guided, from the output of a txt2img model.

#lineism #generative #generativeart #mastoart #txt2img

Woman seated.
tiago
9 months ago

Portrait of a young woman.

This piece was produced with a original line drawing algorithm from the output of a txt2img model, a kind of guided generative process.

#txt2img #generativeart #mastoart

Portrait of a young woman.
tiago
9 months ago

Wild flowers. #lineism #generative #generativeart #mastoart

This piece was produced with a line drawing original algorithm from the output of a #txt2img model. The SVG file is ordered for pen plotting and generated for ISO A paper series.

Wild flowers.
tiago
9 months ago

Woman portrait (from the marginalia collection) #nft #tezos #generative #txt2img #lineism #generativeart

The artwork was produced with a line drawing original algorithm seeded with the output from a txt2img model. The SVG file is ordered for pen plotting and generated for ISO A paper series.
https://objkt.com/asset/KT1Fy4t991qRUiSzcRsqdiYmqSAuLZxvJiVt/53

Woman portrait.
tiago
9 months ago

Young woman portrait (from the marginalia collection) #nft #tezos #generative #txt2img #lineism #generativeart
https://objkt.com/asset/KT1Fy4t991qRUiSzcRsqdiYmqSAuLZxvJiVt/47

The artwork was produced with a line drawing original algorithm seeded with the output from a txt2img model. The SVG file is ordered for pen plotting and generated for ISO A paper series.

Young woman portrait
tiago
9 months ago

marginalia: experiences with generative pen plot drawings and algorithms
#NFTArt #nft #tezos #generative #lineism #txt2img

https://objkt.com/profile/tz2TDtxBkfAy6nyNWnTE7xasWWQppkyKZjDE/collections

Lord Caramac the Clueless, KSC
9 months ago

#deepdreamgenerator #txt2img turned it into mediæval Zaphod Beeblebrox #aiart #stablediffusion

A snake with a ridiculous haircut.

#stablediffusion #aiart #inpainting #txt2img

Stylus 🦉
10 months ago

"sketch of a anatomically accurate human hand" trying to add qualifiers to Stable Diffusion (invoke ai branch) prompts just makes the problem how how BAD it is at hands .. even worse. #txt2img

tiago
11 months ago
Picture of a AI generated city street.
tiago
11 months ago

Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scale #txt2img #arXiv #AI
https://arxiv.org/abs/2211.03759

"...we find that the amplified stereotypes are difficult to predict and not easily mitigated by users or model owners. The extent to which these image-generation models perpetuate and amplify stereotypes and their mass deployment is cause for serious concern."

Fell (Akkoma)
11 months ago
I asked an AI to generate "dwarf fortress"

IT KNOWS 😱

#stablediffusion #ai #aiart #dwarffortress #texttoimage #txt2img
Fell (Akkoma)
11 months ago
My wife and I were playing around with #StableDiffusion making #AI generated paintings. We loved the result to "cat drinking coffee with a hat" so much that we decided to frame it. 🖼️
#aiart #cat #coffee #txt2img #texttoimage
Photo of a framed painting of a cat sitting at a table. There is a cup of coffee on the table and the cat is wearing a bright red hat. Another cup of coffee appears to be floating in mid air.