Text-to-Image Summary – Part 4

This is Part 4. See Part 1, Part 2 and Part 3 for the previous posts.

This post continues listing the Text-to-Image scripts included with Visions of Chaos and some example outputs from each script.


Name: PixelDraw
Author: dribnet
Original script: https://colab.research.google.com/github/dribnet/clipit/blob/master/demos/PixelDrawer.ipynb
Time for 512×512 on a 3090: 1 minutes 59 seconds
Maximum resolution on a 24 GB 3090: Huge. 4096×4096 and beyond.
Description: Generates “pixel art” images. I had a lot of requests to add support for this one.

'a cartoon of a peacock' PixelDraw Text-to-Image
a cartoon of a peacock

'a cloudy sunset' PixelDraw Text-to-Image
a cloudy sunset

'a gorilla' PixelDraw Text-to-Image
a gorilla

'a morning landcsape' PixelDraw Text-to-Image
a morning landscape

'a watercolor painting of a castle' PixelDraw Text-to-Image
a watercolor painting of a castle

'an art deco painting of Al Pacino' PixelDraw Text-to-Image
an art deco painting of Al Pacino

'Hell' PixelDraw Text-to-Image
Hell

'Shrek' PixelDraw Text-to-Image
Shrek


Name: DirectVisions
Author: Jens Goldberg
Original script: https://colab.research.google.com/drive/127lKSsQjx-UDDUSvIkLL6mREfZ0KQu5D
Time for 512×512 on a 3090: 2 minutes 39 seconds
Maximum resolution on a 24 GB 3090: Huge. 4096×4096 and beyond.
Description: Interesting detailed images. Can create huge resolution results.

'a color pencil sketch of a western town' DirectVisions Text-to-Image
a color pencil sketch of a western town

'a detailed painting of a cephalopod' DirectVisions Text-to-Image
a detailed painting of a cephalopod

'a digital rendering of an ugly face' DirectVisions Text-to-Image
a digital rendering of an ugly face

'a pencil sketch of Buzz Lightyear' DirectVisions Text-to-Image
a pencil sketch of Buzz Lightyear

'a rough seascape by Pinchus Kremegne' DirectVisions Text-to-Image
a rough seascape by Pinchus Kremegne

'a stock photo of a president' DirectVisions Text-to-Image
a stock photo of a president

'a sunset' DirectVisions Text-to-Image
a sunset

'an alien city' DirectVisions Text-to-Image
an alien city

'an alien forest by Helen Berman' DirectVisions Text-to-Image
an alien forest by Helen Berman

'an evening landscape' DirectVisions Text-to-Image
an evening landscape


Name: Pixel Direct
Author: Unknown
Original script: https://colab.research.google.com/drive/1F9ZOZnpV3uBPRDSESaAXYwzNZJQRJT75
Time for 512×512 on a 3090: 1 minutes 03 seconds
Maximum resolution on a 24 GB 3090: Huge. 4096×4096 and beyond.
Description: Another “Pixel Art” script. More abstract results than the PixelDraw script above.

'a bronze sculpture of a nightmare creature' Pixel Direct Text-to-Image
a bronze sculpture of a nightmare creature

'a cartoon of Al Pacino' Pixel Direct Text-to-Image
a cartoon of Al Pacino

'a nightclub' Pixel Direct Text-to-Image
a nightclub

'a silk screen of a bouquet of flowers' Pixel Direct Text-to-Image
a silk screen of a bouquet of flowers

'an etching of a worried woman' Pixel Direct Text-to-Image
an etching of a worried woman

'an illustration of of a thunder storm' Pixel Direct Text-to-Image
an illustration of of a thunder storm


Name: FourierVisions
Author: Unknown
Original script: https://colab.research.google.com/drive/1nGNBjhbYnDHSumGPjpFHjDOsaZFAqGgF
Time for 512×512 on a 3090: 1 minutes 40 seconds
Maximum resolution on a 24 GB 3090: Huge. 4096×4096 and beyond.
Description: Detailed images. The default script generates washed out pastel images, but with some gamma and brightness tweaks they can be improved (still not ideal, but better). Allows very large resolution images.

'a cathedral' FourierVisions Text-to-Image
a cathedral

'a charcoal drawing of zombies' FourierVisions Text-to-Image
a charcoal drawing of zombies

'a detailed painting of a sunset by Thomas Cantrell Dugdale' FourierVisions Text-to-Image
a detailed painting of a sunset by Thomas Cantrell Dugdale

'a ghost made of mist' FourierVisions Text-to-Image
a ghost made of mist

'a kitchen' FourierVisions Text-to-Image
a kitchen

'a movie monster' FourierVisions Text-to-Image
a movie monster

'a pencil sketch of a sad clown' FourierVisions Text-to-Image
a pencil sketch of a sad clown

'a werewolf' FourierVisions Text-to-Image
a werewolf

'an evil clown by Viktor Oliva' FourierVisions Text-to-Image
an evil clown by Viktor Oliva

'an ink drawing of an ugly monster' FourierVisions Text-to-Image
an ink drawing of an ugly monster


Name: PyramidVisions
Author: Unknown
Original script: https://colab.research.google.com/drive/1dpAS_wK34y7c6s-CatAFmBtbkjGT_erM
Time for 512×512 on a 3090: 3 minutes 08 seconds
Maximum resolution on a 24 GB 3090: Huge. 4096×4096 and beyond.
Description: Very detailed images. Not the fastest script, but gives some very nice results. Lower VRAM requirements so good for lesser spec GPUs. Definitely one of the better scripts worth exploring.

'a desert oasis' PyramidVisions Text-to-Image
a desert oasis

'a lush rainforest' PyramidVisions Text-to-Image
a lush rainforest

'a marble sculpture of an angry person' PyramidVisions Text-to-Image
a marble sculpture of an angry person

'a minimalist painting of the Amazon Rainforest' PyramidVisions Text-to-Image
a minimalist painting of the Amazon Rainforest

'a nightmare creature' PyramidVisions Text-to-Image
a nightmare creature

'a pastel of a computer made of paper' PyramidVisions Text-to-Image
a pastel of a computer made of paper

'an abstract sculpture of a sad clown' PyramidVisions Text-to-Image
an abstract sculpture of a sad clown

'an acrylic painting of an alien forest | vivid colors' PyramidVisions Text-to-Image
an acrylic painting of an alien forest | vivid colors

'Medusa' PyramidVisions Text-to-Image
Medusa

'vector art of an ugly woman' PyramidVisions Text-to-Image
vector art of an ugly woman



Any Others I Missed?

Do you know of any other colabs and/or github Text-to-Image systems I have missed? Let me know and I will see if I can convert them to work with Visions of Chaos for a future release. If you know of any public Discords with other colabs being shared let me know too.

Jason.

4 responses to “Text-to-Image Summary – Part 4

    • Looks interesting but I cannot automate a download of the model from dropbox and it seems to need linux only components. I get other strange errors I cannot find a fix for at the moment.
      If they release a more simple to use version with an easily downloadable model I may be able to add a front end to it in Visions of Chaos, but for now, no go.

      • From what I know Pytti is behind a Patreon member’s only paywall at the moment. If I cannot share it with others then I am not going to spend time trying to get it working. If the author ever decides to freely share the script I will look at implementing a front end for it in Visions of Chaos, but in the meantime I am concentrating on the many other freely available and sharable scripts out there.

        Feed Forward VQGAN is on my to look at list. I briefly tried it before but got stuck with dependencies problems and circular references.

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s