Text-to-Image Summary – Part 3

This is Part 3. See Part 1 and Part 2 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: CLIP Guided Diffusion v4
Author: Katherine Crowson
Original script: https://colab.research.google.com/drive/1V66mUeJbXrTuQITvJunvnWVn96FEbSI3
Time for 512×512 on a 3090: 3 minutes 05 seconds
Maximum resolution on a 24 GB 3090: Locked to 512×512
Description: Another CLIP Guided Diffusion script. Locked to 512×512 resolution. Like the other CLIP Diffusion scripts, some of the results can be very detailed and interesting, but a lot of time it is hit and miss to get a result that reliably matches the input phrase. When it gets a “hit” it can create very detailed impressive results, but the amount of “misses” stops it from getting a great rating. Still worth a try if you have the patience to run a large batch of images waiting for the best results. The following samples came hand picked from a large batch run of random prompt phrases.

'a forest clearing' CLIP Guided Diffusion v4 Text-to-Image
a forest clearing

'a storybook illustration of a nightmare' CLIP Guided Diffusion v4 Text-to-Image
a storybook illustration of a nightmare

'an impressionist painting of a cemetery' CLIP Guided Diffusion v4 Text-to-Image
an impressionist painting of a cemetery

'Harry Potter in the style of Rembrandt' CLIP Guided Diffusion v4 Text-to-Image
Harry Potter in the style of Rembrandt

'a detailed painting of a witch' CLIP Guided Diffusion v4 Text-to-Image
a detailed painting of a witch

'a babbling brook' CLIP Guided Diffusion v4 Text-to-Image
a babbling brook

'a desert oasis' CLIP Guided Diffusion v4 Text-to-Image
a desert oasis

'a hyperrealistic painting of an android' CLIP Guided Diffusion v4 Text-to-Image
a hyperrealistic painting of an android

'eyeballs' CLIP Guided Diffusion v4 Text-to-Image
eyeballs

'a cross stitch of Buzz Lightyear' CLIP Guided Diffusion v4 Text-to-Image
a cross stitch of Buzz Lightyear


Name: CLIP Guided Decision Transformer
Author: Katherine Crowson
Original script: https://colab.research.google.com/drive/1V66mUeJbXrTuQITvJunvnWVn96FEbSI3
Time for 512×512 on a 3090: 1 minutes 13 seconds
Maximum resolution on a 24 GB 3090: Locked to 384×384
Description: Another one from Katherine Crowson. Some of the results can be very detailed and interesting, but a lot of time it is hit and miss to get a result that reliably matches the input phrase. When it gets a “hit” it can create very detailed impressive results, but the amount of “misses” stops it from getting a great rating. The following samples came hand picked from a large batch run of random prompt phrases.
Another good point for CLIP Decsision Transformer is that it will generate a batch of images from each run. So rather than a single image for the prompt text you can specify (for example) 8 images to be generated from the prompt. This allows a much larger set of images to be quickly generated to find those great outputs in.
For these images I have enhanced the resolution 4x using Real-ESRGAN (the thumnails are the original output images and the clicked images are resized x4).

a detailed painting of a palace by Thomas Kinkade
a detailed painting of a palace by Thomas Kinkade

a drawing of Chewbacca
a drawing of Chewbacca

a forest path
a forest path

a renaissance painting of a mountain range
a renaissance painting of a mountain range

a rough seascape
a rough seascape

a rough seascape
a rough seascape

a spooky forest
a spooky forest

an oil on canvas painting of a western town
an oil on canvas painting of a western town

Frankenstein
Frankenstein

The Grand Canyon
The Grand Canyon


Name: CLIPIT
Author: dribnet
Original script: https://github.com/dribnet/clipit
Time for 512×512 on a 3090: 2 minutes 38 seconds
Maximum resolution on a 24 GB 3090: 768×768 or 1120×480
Description: Another GAN+CLIP script. Gives nice results that tend to match the prompt text more closely. This one is heavy on VAM usage.

'a happy family by Piet Mondiran' CLIPIT
a happy family by Piet Mondiran

'a landscape' CLIPIT
a landscape

'a peacock' CLIPIT
a peacock

'a tropical beach by Thomas Kinkade' CLIPIT
a tropical beach by Thomas Kinkade

'a woodcut of Dracula' CLIPIT
a woodcut of Dracula

'an ambient occlusion render of a zombie' CLIPIT
an ambient occlusion render of a zombie

'eyeballs in the style of Claude Monet' CLIPIT
eyeballs in the style of Claude Monet


Name: Art Machine
Author: Hillel Wayne
Original script: https://colab.research.google.com/drive/1n_xrgKDlGQcCF6O-eL3NOd_x4NSqAUjK
Time for 512×512 on a 3090: 4 minutes 04 seconds
Maximum resolution on a 24 GB 3090: 768×768 or 1120×480
Description: Another VQGAN+CLIP scipt.

'a charcoal drawing of a kitchen' Art Machine
a charcoal drawing of a kitchen

'a mosaic of a mountain path | CryEngine' Art Machine
a mosaic of a mountain path | CryEngine

'a silk screen of a tropical beach in the style of Kandinsky' Art Machine
a silk screen of a tropical beach in the style of Kandinsky

'a woodcut of a nightmare creature' Art Machine
a woodcut of a nightmare creature

'an illustration of of a mountainscape' Art Machine
an illustration of of a mountainscape

'an ultrafine detailed painting of a green tree frog as created by Craig Mullins' Art Machine
an ultrafine detailed painting of a green tree frog as created by Craig Mullins

'Dracula' Art Machine
Dracula

'Planets' Art Machine
Planets


Name: VQGAN+CLIP v5
Author: Max Woolf
Original script: https://colab.research.google.com/drive/1wkF67ThUz37T2_oPIuSwuO4e_-0vjaLs
Time for 512×512 on a 3090: 2 minutes 13 seconds
Maximum resolution on a 24 GB 3090: 768×768 or 1120×480
Description: Another VQGAN+CLIP scipt. More abstract results from this one.

'a desert oasis in the style of Salvador Dali' VQGAN+CLIP v5
a desert oasis in the style of Salvador Dali

'a hyperrealistic painting of a dragon' VQGAN+CLIP v5
a hyperrealistic painting of a dragon

'Big Bird' VQGAN+CLIP v5
Big Bird

'Cthulhu' VQGAN+CLIP v5
Cthulhu

'Robert DeNiro' VQGAN+CLIP v5
Robert DeNiro

'Yoda' VQGAN+CLIP v5
Yoda “hmmm, abstract I am”


Name: Zoetrope 5.5
Author: Bearsharktopusdev
Original script: https://colab.research.google.com/drive/1LpEbICv1mmta7Qqic1IcRTsRsq7UKRHM
Time for 512×512 on a 3090: 3 minutes 27 seconds
Maximum resolution on a 24 GB 3090: 768×768 or 1120×720
Description: Updated version of Zoetrope 5. Supports more VQGAN models, CLIP models and optimizers compared to Zoetrope 5.

'a cephalopod' Zoetrope 5.5 Text-to-Image
a cephalopod

'a flemish baroque of a demon' Zoetrope 5.5 Text-to-Image
a flemish baroque of a demon

'a photo of a submarine in the style of Vincent van Gogh' Zoetrope 5.5 Text-to-Image
a photo of a submarine in the style of Vincent van Gogh

'a snail' Zoetrope 5.5 Text-to-Image
a snail

'Cthulhu' Zoetrope 5.5 Text-to-Image
Cthulhu

'flesh' Zoetrope 5.5 Text-to-Image
flesh


Name: Zeta Quantize
Author: afiaka87
Original script: https://colab.research.google.com/gist/afiaka87/a97cca3b54c02209b94ff805224f9eb5/zeta_quantize.ipynb
Time for 512×512 on a 3090: 4 minutes 18 seconds
Maximum resolution on a 24 GB 3090: 768×768 or 1120×720
Description: Another VQGAN+CLIP scipt.

'a cute creature made of silver' Zeta Quantize
a cute creature made of silver

'a detailed painting of a cephalopod' Zeta Quantize
a detailed painting of a cephalopod

'a detailed painting of a ghost' Zeta Quantize
a detailed painting of a ghost

'a forest fire made of copper' Zeta Quantize
a forest fire made of copper

'a peacock' Zeta Quantize
a peacock

'a sketch of a Pokemon character in the style of Odilon Redon' Zeta Quantize
a sketch of a Pokemon character in the style of Odilon Redon

'a watercolor painting of dense woodland' Zeta Quantize
a watercolor painting of dense woodland


Name: Experimental VQGAN
Author: Various
Original script: https://colab.research.google.com/drive/1jx3klUxlGbYUwvtqzC9SYl4XZKHL3R81
Time for 512×512 on a 3090: 1 minutes 12 seconds
Maximum resolution on a 24 GB 3090: 768×768 or 1120×720
Description: Very nice smooth results from this one.

'a desert oasis in the style of Craig Mullins' Experimental VQGAN
a desert oasis in the style of Craig Mullins

'a dragon' Experimental VQGAN
a dragon

'a manga drawing of a happy alien' Experimental VQGAN
a manga drawing of a happy alien

'a nightmare' Experimental VQGAN
a nightmare

'a surrealist painting of love' Experimental VQGAN
a surrealist painting of love

'a watercolor painting of a lighthouse' Experimental VQGAN
a watercolor painting of a lighthouse

'an airbrush painting of a well kept garden by Piet Mondiran' Experimental VQGAN
an airbrush painting of a well kept garden by Piet Mondiran

'Cookie Monster' Experimental VQGAN
Cookie Monster


Name: SlideShowVisions
Author: Active Galaxy
Original script: https://colab.research.google.com/drive/1IihC4ZJvCh_tOgBVd900BzHX-ulPEFsa
Time for 512×512 on a 3090: 2 minutes 25 seconds
Maximum resolution on a 24 GB 3090: 768×768 or 1120×720
Description: Tends to give more abstract paper cutout looks.

'a happy child' SlideShowVisions
a happy child

'a house vivid colors' SlideShowVisions
a house vivid colors

'a sea monster' SlideShowVisions
a sea monster

'a thunder storm' SlideShowVisions
a thunder storm

'a tree' SlideShowVisions
a tree

'a woodcut of war' SlideShowVisions
a woodcut of war

'an engraving of zombies' SlideShowVisions
an engraving of zombies

'Han Solo' SlideShowVisions
Han Solo


Name: Quick CLIP Guided Diffusion
Author: Daniel Russell
Original script: https://colab.research.google.com/drive/1FuOobQOmDJuG7rGsMWfQa883A9r4HxEO
Time for 512×512 on a 3090: 43 seconds
Maximum resolution on a 24 GB 3090: 512×512
Description: Modified version of CLIP Guided Diffusion that gets results quicker. Option for 256×256 or 512×512 sized images. Still very hit and miss when getting images that resemble the input prompt. The following samples came from a large overnight batch run of random prompts.

'a cathedral' Quick CLIP Guided Diffusion
a cathedral

'a digital painting of a space nebula' Quick CLIP Guided Diffusion
a digital painting of a space nebula

'a lounge room' Quick CLIP Guided Diffusion
a lounge room

'a monkey | lens flare' Quick CLIP Guided Diffusion
a monkey | lens flare

'a nightmare creature' Quick CLIP Guided Diffusion
a nightmare creature

'a rough seascape' Quick CLIP Guided Diffusion
a rough seascape

'a landscape' Quick CLIP Guided Diffusion
a landscape

'an android' Quick CLIP Guided Diffusion
an android

'an attractive woman' Quick CLIP Guided Diffusion
an attractive woman

'an oil on canvas painting of a cloudy sunset' Quick CLIP Guided Diffusion
an oil on canvas painting of a cloudy sunset


Name: CLIP Guided Diffusion v5
Author: Katherine Crowson
Original script: https://colab.research.google.com/drive/1QBsaDAZv8np29FPbvjffbE1eytoJcsgA
Time for 512×512 on a 3090: 3 minutes 48 seconds
Maximum resolution on a 24 GB 3090: Locked to 512×512
Description: Another CLIP Guided Diffusion script. Locked to 512×512 resolution. Needs less VRAM than the previous versions. The following samples came hand picked from a large batch run of random prompt phrases.

'a cityscape' CLIP Guided Diffusion v5 Text-to-Image
a cityscape

'a gorilla' CLIP Guided Diffusion v5 Text-to-Image
a gorilla

'Cthulhu by Craig Mullins' CLIP Guided Diffusion v5 Text-to-Image
Cthulhu by Craig Mullins

'computer rendering of Emporer Palpatine made of cheese by Evan Charlton' CLIP Guided Diffusion v5 Text-to-Image
computer rendering of Emporer Palpatine made of cheese by Evan Charlton

'digital art of a mountainscape as created by Persis Goodale Thurston Taylor' CLIP Guided Diffusion v5 Text-to-Image
digital art of a mountainscape as created by Persis Goodale Thurston Taylor

'a digital rendering of Chewbacca' CLIP Guided Diffusion v5 Text-to-Image
a digital rendering of Chewbacca

'an ugly person' CLIP Guided Diffusion v5 Text-to-Image
an ugly person

See this tweet for an example of using CLIP Guided Diffusion to stylize a portrait.


Name: MSE Regulized Modified
Author: jbusted
Original script: https://colab.research.google.com/drive/1gFn9u3oPOgsNzJWEFmdK-N9h_y65b8fj
Time for 512×512 on a 3090: 3 minutes 02 seconds
Maximum resolution on a 24 GB 3090: 768×768 or 1120×720
Description: Modified and updated version of the previous “MSE Regulized VQGAN+CLIP” script. Less likely to suffer the previous script’s issue of subjects floating in a purple void.

'a bronze sculpture of a planet' MSE Regulized Modified Text-to-Image
a bronze sculpture of a planet

'a cave by Asher Brown Durand' MSE Regulized Modified Text-to-Image
a cave by Asher Brown Durand

'a charcoal drawing of Emporer Palpatine' MSE Regulized Modified Text-to-Image
a charcoal drawing of Emporer Palpatine

'a cozy den' MSE Regulized Modified Text-to-Image
a cozy den

'a detailed drawing of a heart made of string by William MacTaggart' MSE Regulized Modified Text-to-Image
a detailed drawing of a heart made of string by William MacTaggart

'a digital rendering of Arnold Schwarzenegger made of metal by Muriel Brandt' MSE Regulized Modified Text-to-Image
a digital rendering of Arnold Schwarzenegger made of metal by Muriel Brandt

'a lounge room' MSE Regulized Modified Text-to-Image
a lounge room

'a palace by Jules Joseph Lefebvre' MSE Regulized Modified Text-to-Image
a palace by Jules Joseph Lefebvre

'an oil on canvas painting of a lush rainforest' MSE Regulized Modified Text-to-Image
an oil on canvas painting of a lush rainforest

'an oil on canvas painting of Cookie Monster' MSE Regulized Modified Text-to-Image
an oil on canvas painting of Cookie Monster


Name: Pixray
Author: dribnet
Original script: https://colab.research.google.com/github/dribnet/clipit/blob/master/demos/Start_Here.ipynb
Time for 512×512 on a 3090: 1 minutes 44 seconds
Maximum resolution on a 24 GB 3090: 768×768 or 1120×720
Description: Updated version of the previous “CLIPIT” script.

'a bronze sculpture of a nightmare creature' Pixray Text-to-Image
a bronze sculpture of a nightmare creature

'a fire breathing dragon by Jan Baptist Weenix' Pixray Text-to-Image
a fire breathing dragon by Jan Baptist Weenix

'a morning landscape' Pixray Text-to-Image
a morning landscape

'a surrealist sculpture of an elephant' Pixray Text-to-Image
a surrealist sculpture of an elephant

'a watercolor painting of an astronaut' Pixray Text-to-Image
a watercolor painting of an astronaut

'an oil painting of a worried woman | Rendered in Cinema4D' Pixray Text-to-Image
an oil painting of a worried woman | Rendered in Cinema4D

'an ugly creature' Pixray Text-to-Image
an ugly creature

'Dracula' Pixray Text-to-Image
Dracula

'Frankenstein' Pixray Text-to-Image
Frankenstein

'vector art of a forest clearing' Pixray Text-to-Image
vector art of a forest clearing


Name: CLIP Guided Diffusion v6
Author: Dango233
Original script: https://colab.research.google.com/drive/14xBm1aSxQLbq26-jmDJi8I1HJ4ti5ybt
Time for 512×512 on a 3090: 3 minutes 10 seconds
Maximum resolution on a 24 GB 3090: Locked to 512×512
Description: Latest CLIP Guided Diffusion script. The best one yet. Capable of some very nice results.

'a hyperrealistic painting of a human' CLIP Guided Diffusion v6 Text-to-Image
a hyperrealistic painting of a human

'a sketch of planets' CLIP Guided Diffusion v6 Text-to-Image
a sketch of planets

'a storybook illustration of a cloudy sunset' CLIP Guided Diffusion v6 Text-to-Image
a storybook illustration of a cloudy sunset

'a wizard | vivid colors' CLIP Guided Diffusion v6 Text-to-Image
a wizard | vivid colors

'an art deco sculpture of a planet' CLIP Guided Diffusion v6 Text-to-Image
an art deco sculpture of a planet

'an attractive man by John Linnell' CLIP Guided Diffusion v6 Text-to-Image
an attractive man by John Linnell

'an oil on canvas painting of satan' CLIP Guided Diffusion v6 Text-to-Image
an oil on canvas painting of satan

'an oil painting of a clown' CLIP Guided Diffusion v6 Text-to-Image
an oil painting of a clown

'digital art of an ugly person by Avigdor Arikha' CLIP Guided Diffusion v6 Text-to-Image
digital art of an ugly person by Avigdor Arikha

'princess in sanctuary trending on artstation photorealistic portrait of a young princess' CLIP Guided Diffusion v6 Text-to-Image
princess in sanctuary trending on artstation photorealistic portrait of a young princess


Name: CLIPDraw
Author: Kevin Frans
Original script: https://colab.research.google.com/github/kvfrans/clipdraw/blob/main/clipdraw.ipynb
Time for 512×512 on a 3090: 7 minutes 10 seconds
Maximum resolution on a 24 GB 3090: Huge. 4096×4096 and beyond.
Description: Generates images by a series of lines. Very abstract results.

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

'a digital painting of a rose' CLIPDraw Text-to-Image
a digital painting of a rose

'a sad clown' CLIPDraw Text-to-Image
a sad clown

'an abstract painting of Yoda' CLIPDraw Text-to-Image
an abstract painting of Yoda

'an etching of a library' CLIPDraw Text-to-Image
an etching of a library

'The Sydney Harbour Bridge' CLIPDraw Text-to-Image
The Sydney Harbour Bridge


Continued in Part 4.

Jason.

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