Text-to-Image Summary – Part 7

This is Part 7. There is also Part 1, Part 2, Part 3, Part 4, Part 5, Part 6 and Part 8.

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


Name: Multi-Perceptor VQGAN+CLIP v4
Author: Remi Durant
Original script: https://colab.research.google.com/drive/1peZ98vBihDD9A1v7JdH5VvHDUuW5tcRK
Time for 512×512 on a 3090: 2 minutes 36 seconds
Maximum resolution on a 24 GB 3090: 1120×480
Maximum resolution on an 8GB 2080: Unable to run on 8GB VRAM
Description: Version 4 of Remi’s Multi-Perceptor VQGAN+CLIP script.

'a bronze sculpture of a garden' Multi-Perceptor VQGAN+CLIP v4
a bronze sculpture of a garden

'a church by Tadeusz Kantor' Multi-Perceptor VQGAN+CLIP v4
a church by Tadeusz Kantor

'a color pencil sketch of a monkey hyperdetailed' Multi-Perceptor VQGAN+CLIP v4
a color pencil sketch of a monkey hyperdetailed

'a comic book panel of a lush rainforest' Multi-Perceptor VQGAN+CLIP v4
a comic book panel of a lush rainforest

'a matte painting of a witch by William Geissler' Multi-Perceptor VQGAN+CLIP v4
a matte painting of a witch by William Geissler

'a peninsula by Ei-Q CGSociety' Multi-Perceptor VQGAN+CLIP v4
a peninsula by Ei-Q CGSociety

'a surrealist sculpture of hell' Multi-Perceptor VQGAN+CLIP v4
a surrealist sculpture of hell

'an eyeball made of flowers' Multi-Perceptor VQGAN+CLIP v4
an eyeball made of flowers

'cyberpunk art of a canyon' Multi-Perceptor VQGAN+CLIP v4
cyberpunk art of a canyon

'lineart of dense woodland' Multi-Perceptor VQGAN+CLIP v4
lineart of dense woodland


Name: V-Majesty Diffusion v1.2
Authors: Original script by Dango233 and multimodalart
Original script: https://colab.research.google.com/github/multimodalart/MajestyDiffusion/blob/main/v.ipynb
Time for 512×512 on a 3090: 3 minutes 08 seconds
Maximum resolution on a 24 GB 3090: 1664×704.
Maximum resolution on an 8GB 2080: Unable to run on 8GB VRAM
Description: A new diffusion based script.

'a black and white photo of war' V-Majesty Diffusion
a black and white photo of war

'a brownstone by Oliver Sin super detailed' V-Majesty Diffusion
a brownstone by Oliver Sin super detailed

'a cute creature' V-Majesty Diffusion
a cute creature

'a doctor' V-Majesty Diffusion
a doctor

'a drawing of a babbling brook photorealistic' V-Majesty Diffusion
a drawing of a babbling brook photorealistic

'a hill' V-Majesty Diffusion
a hill

'a ninja by Michael Ford psychedelic' V-Majesty Diffusion
a ninja by Michael Ford psychedelic

'a photo of a beautiful young girl in a summer garden at dusk' V-Majesty Diffusion
a photo of a beautiful young girl in a summer garden at dusk

'a storybook illustration of a cozy den' V-Majesty Diffusion
a storybook illustration of a cozy den

'New York City' V-Majesty Diffusion
New York City


Name: Latent Majesty Diffusion v1.3
Authors: Original script by Dango233 and multimodalart
Original script: https://colab.research.google.com/github/multimodalart/MajestyDiffusion/blob/main/latent.ipynb
Time for 512×512 on a 3090: 2 minutes 24 seconds
Maximum resolution on a 24 GB 3090: 512×512 (when using GFPGAN upscaling)
Maximum resolution on an 8GB 2080: Unable to run on 8GB VRAM
Description: Starts with a smaller resolution image (usually 256×256 pixels), upscales it with GFPGAN, and then does a few more diffusion passes. GFPGAN can really help get better coherency in faces.

'a hyperrealistic painting of a cute creature' Latent Majesty Diffusion
a hyperrealistic painting of a cute creature

'a hyperrealistic painting of an evil clown' Latent Majesty Diffusion
a hyperrealistic painting of an evil clown

'a picture of a tree' Latent Majesty Diffusion
a picture of a tree

'a surrealist painting of kittens' Latent Majesty Diffusion
a surrealist painting of kittens

'an engraving of an angry woman made of voxels' Latent Majesty Diffusion
an engraving of an angry woman made of voxels

'an oil painting of an attractive woman by Eileen Aldridge' Latent Majesty Diffusion
an oil painting of an attractive woman by Eileen Aldridge

'an ultrafine detailed painting of Bruce Willis 4K HD realism' Latent Majesty Diffusion
an ultrafine detailed painting of Bruce Willis 4K HD realism

'Robert DeNiro ZBrush' Latent Majesty Diffusion
Robert DeNiro ZBrush

'Tweety Pie' Latent Majesty Diffusion
Tweety Pie

'Yoda' Latent Majesty Diffusion
Yoda


Name: Huemin JAX Diffusion v2.7
Author: Huemin
Original script: https://colab.research.google.com/github/huemin-art/jax-guided-diffusion/blob/v2.7/Huemin_Jax_Diffusion_2_7.ipynb
Time for 512×512 on a 3090: 3 minutes 55 seconds
Maximum resolution on a 24 GB 3090: 2496×1088
Maximum resolution on an 8GB 2080: Unable to run on 8GB VRAM
Description: Starts with a smaller resolution image (usually 256×256 pixels), upscales it with GFPGAN, and then does a few more diffusion passes. GFPGAN can really help get better coherency in faces.

'a babbling brook' Huemin JAX Diffusion
a babbling brook

'a mountain path Flickr' Huemin JAX Diffusion
a mountain path Flickr

'a river CGSociety' Huemin JAX Diffusion
a river CGSociety

'a spooky forest by John F. Peto' Huemin JAX Diffusion
a spooky forest by John F. Peto

'a storybook illustration of a mansion by Donald Roller Wilson' Huemin JAX Diffusion
a storybook illustration of a mansion by Donald Roller Wilson

'a surrealist sculpture of an alien forest' Huemin JAX Diffusion
a surrealist sculpture of an alien forest

'a watercolor painting of fear made of bones ZBrush' Huemin JAX Diffusion
a watercolor painting of fear made of bones ZBrush

'a wetland by Alexander Robertson super detailed' Huemin JAX Diffusion
a wetland by Alexander Robertson super detailed

'New York City' Huemin JAX Diffusion
New York City

'vector art of a bouquet of flowers ZBrush' Huemin JAX Diffusion
vector art of a bouquet of flowers ZBrush


Name: Disco Diffusion v5.2
Authors: Original script by @somnai, @gandamu and @zippy731
Original script: https://colab.research.google.com/github/zippy731/disco-diffusion-turbo/blob/skunk/Disco_Diffusion.ipynb
Time for 512×512 on a 3090: 2 minutes 2 seconds
Maximum resolution on a 24 GB 3090: 2496×1088
Maximum resolution on an 8GB 2080: 768×768
Description: Latest version of Disco Diffusion.

'a bay by Louis Valtat Tri-X 400 TX' Disco Diffusion v5.2
a bay by Louis Valtat Tri-X 400 TX

'a hyperrealistic painting of a mansion' Disco Diffusion v5.2
a hyperrealistic painting of a mansion

'a hyperrealistic painting of a nightmare' Disco Diffusion v5.2
a hyperrealistic painting of a nightmare

'a pond' Disco Diffusion v5.2
a pond

'a tributary by Jacob Marrel' Disco Diffusion v5.2
a tributary by Jacob Marrel

'an alien landscape' Disco Diffusion v5.2
an alien landscape

'an island by Andrew Robertson IMAX' Disco Diffusion v5.2
an island by Andrew Robertson IMAX

'Frankenstein made of liquid metal CryEngine' Disco Diffusion v5.2
Frankenstein made of liquid metal CryEngine

'medusa by Gai Qi' Disco Diffusion v5.2
medusa by Gai Qi

'the Amazon Rainforest' Disco Diffusion v5.2
the Amazon Rainforest


Name: DALL-E Mini
Author: Original script by Boris Dayma
Original script: https://colab.research.google.com/github/borisdayma/dalle-mini/blob/main/tools/inference/inference_pipeline.ipynb
Time for 512×512 on a 3090: Locked to 256×256 – 1 minute 13 seconds
Maximum resolution on a 24 GB 3090: 256×256
Maximum resolution on an 8GB 2080: 256×256
Description: Capable of rendering multiple images in one pass. Very nice results. Limited to 256×256 at this time. These examples show a 4×4 grid of 16 images for each prompt.

a fine art painting of a fire breathing dragona fine art painting of a fire breathing dragon

a hyperrealistic painting of an ugly monstera hyperrealistic painting of an ugly monster

a planeta planet

a rivera river

a rosea rose

a surrealist painting of a kinga surrealist painting of a king

an airbrush painting of satanan airbrush painting of satan

an engraving of a frogan engraving of a frog

an ultrafine detailed painting of fearan ultrafine detailed painting of fear

Darth Vader trending on pixivDarth Vader trending on pixiv


Name: Latent Majesty Diffusion v1.6
Authors: Original script by Dango233 and multimodalart
Original script: https://colab.research.google.com/github/multimodalart/MajestyDiffusion/blob/main/latent.ipynb
Time for 512×512 on a 3090: 2 minutes 07 seconds
Maximum resolution on a 24 GB 3090: 512×512 (when using GFPGAN upscaling)
Maximum resolution on an 8GB 2080: Unable to run on 8GB VRAM
Description: The latest amazing update to Latent Diffusion. Awesome colors, textures, lighting, details, coherency. Highly recommended.

'a colorful parrot' Latent Majesty Diffusion v1.6
a colorful parrot

'a detailed matte painting of puppies' Latent Majesty Diffusion v1.6
a detailed matte painting of puppies

'a gallery' Latent Majesty Diffusion v1.6
a gallery

'a mountain cabin by Tom Palin 4K HD realism' Latent Majesty Diffusion v1.6
a mountain cabin by Tom Palin 4K HD realism

'a renaissance painting of a spooky forest' Latent Majesty Diffusion v1.6
a renaissance painting of a spooky forest

'a school of tropical fish by Jane Carpanini' Latent Majesty Diffusion v1.6
a school of tropical fish by Jane Carpanini

'an ugly creature' Latent Majesty Diffusion v1.6
an ugly creature

'the Amazon Rainforest photorealistic' Latent Majesty Diffusion v1.6
the Amazon Rainforest photorealistic

'The Grinch' Latent Majesty Diffusion v1.6
The Grinch

'Yoda trending on Flickr' Latent Majesty Diffusion v1.6
Yoda trending on Flickr


Name: Disco Diffusion v5.4
Authors: Original script by @somnai, @gandamu, @zippy731 and @devdef
Original script: https://colab.research.google.com/github/alembics/disco-diffusion/blob/main/Disco_Diffusion.ipynb
Time for 512×512 on a 3090: 2 minutes 20 seconds
Maximum resolution on a 24 GB 3090: 2496×1088
Maximum resolution on an 8GB 2080: 768×768
Description: Latest version of Disco Diffusion.

'a 3D render of the Grand Canyon by Dóra Keresztes' Disco Diffusion v5.4
a 3D render of the Grand Canyon by Dóra Keresztes

'a hyperrealistic painting of a zombie made of cheese and feathers CryEngine and rendered in Cinema4D' Disco Diffusion v5.4
a hyperrealistic painting of a zombie made of cheese and feathers CryEngine and rendered in Cinema4D

'a macro photograph of an ugly creature' Disco Diffusion v5.4
a macro photograph of an ugly creature

'a matte painting of a monument' Disco Diffusion v5.4
a matte painting of a monument

'a picture of a vast city' Disco Diffusion v5.4
a picture of a vast city

'a skyscraper' Disco Diffusion v5.4
a skyscraper

'a thunder storm' Disco Diffusion v5.4
a thunder storm

'Jason Vorhees by Chen Chi' Disco Diffusion v5.4
Jason Vorhees by Chen Chi

'reflective spheres hyperrealistic' Disco Diffusion v5.4
reflective spheres hyperrealistic

'the country by Robert Thomas and Chen Jiru rendered in unreal engine and 4K photo' Disco Diffusion v5.4
the country by Robert Thomas and Chen Jiru rendered in unreal engine and 4K photo


Name: Pixel Art Diffusion v3
Authors: Original script by @somnai, @gandamu, @zippy731 and @KaliYuga_ai
Original script: https://colab.research.google.com/github/KaliYuga-ai/Pixel-Art-Diffusion/blob/main/Pixel_Art_Diffusion_v3_0_(With_Disco_Symmetry).ipynb
Time for 512×512 on a 3090: 3 minutes 14 seconds
Maximum resolution on a 24 GB 3090: 1920×1088
Maximum resolution on an 8GB 2080: Unable to run on 8GB VRAM
Description: Uses a fine tuned model to generate pixel art like imagery.

'a bedroom hyperrealistic and hyperdetailed #pixelart' Pixel Art Diffusion v3
a bedroom hyperrealistic and hyperdetailed #pixelart

'a cephalopod IMAX and lens flare #pixelart' Pixel Art Diffusion v3
a cephalopod IMAX and lens flare #pixelart

'a cinematic painting of a cottage #pixelart' Pixel Art Diffusion v3
a cinematic painting of a cottage #pixelart

'a cross stitch of a townhouse made of voxels and timber #pixelart' Pixel Art Diffusion v3
a cross stitch of a townhouse made of voxels and timber #pixelart

'a pastel of a cute girl #pixelart' Pixel Art Diffusion v3
a pastel of a cute girl #pixelart

'a surrealist sculpture of Charmander #pixelart' Pixel Art Diffusion v3
a surrealist sculpture of Charmander #pixelart

'an alien city by Anders Zorn and Laura Muntz Lyall photorealistic and CGSociety #pixelart' Pixel Art Diffusion v3
an alien city by Anders Zorn and Laura Muntz Lyall photorealistic and CGSociety #pixelart


concept art of a wetland ZBrush and CryEngine #pixelart

'Frankenstein made of string and vines trending on pixiv and hyperrealistic #pixelart' Pixel Art Diffusion v3
Frankenstein made of string and vines trending on pixiv and hyperrealistic #pixelart

'pixel art of a cloudy sunset #pixelart' Pixel Art Diffusion v3
pixel art of a cloudy sunset #pixelart


Name: Disco Diffusion v5.6
Authors: Original script by @somnai and @gandamu
Original script: https://colab.research.google.com/github/alembics/disco-diffusion/blob/main/Disco_Diffusion.ipynb
Time for 512×512 on a 3090: 3 minutes 34 seconds
Maximum resolution on a 24 GB 3090: 2496×1088
Maximum resolution on an 8GB 2080: 768×768
Description: Latest version of Disco Diffusion.

'a collage painting of a lush rainforest by Doc Hammer and Alexander Ivanov hyperrealistic and CryEngine' Disco Diffusion v5.4
a collage painting of a lush rainforest by Doc Hammer and Alexander Ivanov hyperrealistic and CryEngine

'a cubist painting of a lion and a sunset CryEngine and trending on pixiv' Disco Diffusion v5.4
a cubist painting of a lion and a sunset CryEngine and trending on pixiv

'a fine art painting of a zombie' Disco Diffusion v5.4
a fine art painting of a zombie

'a gulf by I Ketut Soki and Alfons von Czibulka' Disco Diffusion v5.4
a gulf by I Ketut Soki and Alfons von Czibulka

'a monastery trending on Flickr and #film' Disco Diffusion v5.4
a monastery trending on Flickr and #film

'a morning landscape' Disco Diffusion v5.4
a morning landscape

'a prairie CGSociety and CryEngine' Disco Diffusion v5.4
a prairie CGSociety and CryEngine

'a werewolf' Disco Diffusion v5.4
a werewolf

'ballpoint pen art of a monument' Disco Diffusion v5.4
ballpoint pen art of a monument


cyberpunk art of heaven filmic and CryEngine


Name: CLIP Guided k-diffusion
Author: Original script by Katherine Crowson
Original script: https://colab.research.google.com/drive/1w0HQqxOKCk37orHATPxV8qb0wb4v-qa0
Time for 512×512 on a 3090: 6 minutes 56 seconds
Maximum resolution on a 24 GB 3090: Fixed to 512×512 resolution.
Maximum resolution on an 8GB 2080: Unable to run on 8GB VRAM
Description: A new script by Katherine. Seems to generate more abstract results and these example images needed a long run of random prompts to select from.

'a jigsaw puzzle of paranoia by Petr Brandl and Sasha Putrya' CLIP Guided k-diffusion v5.4
a jigsaw puzzle of paranoia by Petr Brandl and Sasha Putrya

'a landscape vivid colors' CLIP Guided k-diffusion v5.4
a landscape vivid colors

'a pastel of Cookie Monster by Ren Bonian and Ángel Botello for sale on Facebook Marketplace and CryEngine' CLIP Guided k-diffusion v5.4
a pastel of Cookie Monster by Ren Bonian and Ángel Botello for sale on Facebook Marketplace and CryEngine

'a reef' CLIP Guided k-diffusion v5.4
a reef

'a renaissance painting of Al Pacino' CLIP Guided k-diffusion v5.4
a renaissance painting of Al Pacino

'a statue of a submarine made of metal and crystals by James Sessions American painter and Elfriede Lohse-Wächtler' CLIP Guided k-diffusion v5.4
a statue of a submarine made of metal and crystals by James Sessions American painter and Elfriede Lohse-Wächtler

'an airbrush painting of a nightmare creature vivid colors and rendered in Cinema4D' CLIP Guided k-diffusion v5.4
an airbrush painting of a nightmare creature vivid colors and rendered in Cinema4D

'an oil painting of a cephalopod made of paper and mist' CLIP Guided k-diffusion v5.4
an oil painting of a cephalopod made of paper and mist

'an ugly person and an area 4K HD realism and trending on pixiv' CLIP Guided k-diffusion v5.4
an ugly person and an area 4K HD realism and trending on pixiv

'conceptual art of an ugly monster' CLIP Guided k-diffusion v5.4
conceptual art of an ugly monster


Name: CLIP Prior + VQGAN (MSE method)
Author: Original script by Katherine Crowson
Original script: https://colab.research.google.com/drive/1yOpCY9eXvzELHppvh-o0DevhxVYOGr5i
Time for 512×512 on a 3090: 3 minutes 31 seconds
Maximum resolution on a 24 GB 3090: 832×512
Maximum resolution on an 8GB 2080: Unable to run on 8GB VRAM
Description: A new script by Katherine. Can give some interesting details but coherence may suffer at larger resolutions.

'a collage painting of a tiger vivid colors and photorealistic' CLIP Prior + VQGAN (MSE method)
a collage painting of a tiger vivid colors and photorealistic

'a cove 4K photo and CryEngine' CLIP Prior + VQGAN (MSE method)
a cove 4K photo and CryEngine

'a cute creature' CLIP Prior + VQGAN (MSE method)
a cute creature

'a glacier' CLIP Prior + VQGAN (MSE method)
a glacier

'a space nebula' CLIP Prior + VQGAN (MSE method)
a space nebula

'a townhouse' CLIP Prior + VQGAN (MSE method)
a townhouse

'a valley' CLIP Prior + VQGAN (MSE method)
a valley

'an oil painting of a peacock by Wu Hong and Eve Ryder' CLIP Prior + VQGAN (MSE method)
an oil painting of a peacock by Wu Hong and Eve Ryder

'Cthulhu' CLIP Prior + VQGAN (MSE method)
Cthulhu

'digital art of a wetland made of cheese and timber by Jacob Duck and Jacob Gerritsz Cuyp' CLIP Prior + VQGAN (MSE method)
digital art of a wetland made of cheese and timber by Jacob Duck and Jacob Gerritsz Cuyp


Name: Latent Diffusion LAION_400M v2
Author: Original script by pesser
Original script: https://github.com/pesser/stable-diffusion
Time for 16 256×256 images on a 3090: 49 seconds
Maximum resolution on a 24 GB 3090: 512×512
Maximum resolution on an 8GB 2080: Unable to run on 8GB VRAM
Description: Renders multiple images quickly. Coherency is best at 256×256 so these example images are 2×2 tiled results. Each took 35 seconds on a 3090.

'a babbling brook' Latent Diffusion LAION_400M v2
a babbling brook

'a colorful parrot' Latent Diffusion LAION_400M v2
a colorful parrot

'a fine art painting of a castle' Latent Diffusion LAION_400M v2
a fine art painting of a castle

'a matte painting of a rose' Latent Diffusion LAION_400M v2
a matte painting of a rose

'a pencil sketch of a cave 4K photo and hyperrealistic' Latent Diffusion LAION_400M v2
a pencil sketch of a cave 4K photo and hyperrealistic

'a photorealistic painting of Cthulhu for sale on Facebook Marketplace and Flickr' Latent Diffusion LAION_400M v2
a photorealistic painting of Cthulhu for sale on Facebook Marketplace and Flickr

'a surrealist painting of a cloudy sunset' Latent Diffusion LAION_400M v2
a surrealist painting of a cloudy sunset

'a surrealist painting of a monkey' Latent Diffusion LAION_400M v2
a surrealist painting of a monkey

'an illustration of of a tiger by Stanley Twardowicz and Antoni Pitxot' Latent Diffusion LAION_400M v2
an illustration of of a tiger by Stanley Twardowicz and Antoni Pitxot

'an impressionist painting of a cottage' Latent Diffusion LAION_400M v2
an impressionist painting of a cottage


Name: Stable Diffusion
Author: Original script by pesser
Original script: https://github.com/CompVis/stable-diffusion
Time for 512×512 on a 3090: 34 seconds
Maximum resolution on a 24 GB 3090: 1280×640
Maximum resolution on an 8GB 2080: 640×576
Description: Incredible. Latest and greatest. Beats all previous Text-to-Image systems. If you only use one, use this one.

'a black and white photo of puppies' Stable Diffusion
a black and white photo of puppies

'a cathedral rendered in unreal engine and super detailed' Stable Diffusion
a cathedral rendered in unreal engine and super detailed

'a city made of mist trending on ArtStation and trending on Flickr' Stable Diffusion
a city made of mist trending on ArtStation and trending on Flickr

'a detailed matte painting of a lush rainforest made of crystals and feathers' Stable Diffusion
a detailed matte painting of a lush rainforest made of crystals and feathers

'a king' Stable Diffusion
a king

'a polaroid photo of a clown vivid colors and 8K 3D' Stable Diffusion
a polaroid photo of a clown vivid colors and 8K 3D

'an airbrush painting of the Terminator CryEngine and for sale on Facebook Marketplace' Stable Diffusion
an airbrush painting of the Terminator CryEngine and for sale on Facebook Marketplace

'an ambient occlusion render of a wetland by William Forsyth and Victorine Foot trending on pixiv and CryEngine' Stable Diffusion
an ambient occlusion render of a wetland by William Forsyth and Victorine Foot trending on pixiv and CryEngine

'poster art of a farm by Frederic Leighton and Yang Borun rendered in unreal engine and 8K 3D' Stable Diffusion
poster art of a farm by Frederic Leighton and Yang Borun rendered in unreal engine and 8K 3D

'the Australian outback' Stable Diffusion
the Australian outback


Name: Deforum Stable Diffusion v0.3
Author: Original script by Robin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser, Björn Ommer
Original script: https://colab.research.google.com/github/deforum/stable-diffusion/blob/main/Deforum_Stable_Diffusion.ipynb
Time for 512×512 on a 3090: 34 seconds
Maximum resolution on a 24 GB 3090: 1280×640
Maximum resolution on an 8GB 2080: 640×576
Description: Incredible. Latest and greatest. Beats all previous Text-to-Image systems. If you only use one, use this one. Deforum builds upon Stable Diffusion with animation support.

'a babbling brook' Deforum Stable Diffusion
a babbling brook

'a forest path' Deforum Stable Diffusion
a forest path

'a photo of a lake' Deforum Stable Diffusion
a photo of a lake

'a ranch by Nikolai Alekseyevich Kasatkin and Harriet Zeitlin' Deforum Stable Diffusion
a ranch by Nikolai Alekseyevich Kasatkin and Harriet Zeitlin

'a watercolor painting of a rectory hyperdetailed and trending on ArtStation' Deforum Stable Diffusion
a watercolor painting of a rectory hyperdetailed and trending on ArtStation

'Al Pacino by Lam Qua and George Frederick Harris' Deforum Stable Diffusion
Al Pacino by Lam Qua and George Frederick Harris

'an angry person by Kazys Varnelis and Dóra Keresztes' Deforum Stable Diffusion
an angry person by Kazys Varnelis and Dóra Keresztes

'an astronaut' Deforum Stable Diffusion
an astronaut

'puppies' Deforum Stable Diffusion
puppies

'war' Deforum Stable Diffusion
war


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.