File:X-Y plot of algorithmically-generated AI art by different science-fiction subgenres.png

From Wikimedia Commons, the free media repository
Jump to navigation Jump to search

Original file (6,912 × 3,211 pixels, file size: 31 MB, MIME type: image/png)

Captions

Captions

Add a one-line explanation of what this file represents

Summary

[edit]
Description

An X/Y plot of algorithmically-generated AI portrait artworks depicting the aesthetics of different science-fiction subgenres, created using a custom merged Stable Diffusion AI diffusion model checkpoint featuring wd-v1-3-full.ckpt merged with F111 and Stable Diffusion V1-5 at 0.5 sigmoid, and then merged with R34_e4 at 0.25 weighted sum. This plot serves to illustrate how the replacement of a single keyword within a text prompt can alter the aesthetic style of an AI-generated artwork.

Procedure/Methodology

These images were generated using an NVIDIA RTX 4090; since Ada Lovelace chipsets (using compute capability 8.9, which requires CUDA 11.8) are not fully supported by the pyTorch dependency libraries currently used by Stable Diffusion, I've used a custom build of xformers, along with pyTorch cu116 and cuDNN v8.6, as a temporary workaround. Front-end used for the entire generation process is Stable Diffusion web UI created by AUTOMATIC1111.

A batch of 768x1024 images were generated with txt2img using the following prompts:

Prompt: extremely detailed, 1girl, (solo:1.3), (white skin:1.0), (beautiful eyes, long eyelashes, hair between eyes, slicked back hair, hair spread out, very long hair, (messy hair:1.0), bangs, :3, parted lips), skindentation, spread hair, soft skin, glossy skin, fisheye, soft focus, (cyberpunk outfit:1.2), (cyberpunk clothes:1.2), (cyberpunk setting in background:1.2)

Negative prompt: lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, deformed, broken body, mutated, extra hands, extra feet, extra arms, extra legs, multiple views, ribbon, pregnant, steam, fat, chubby, obese, bats, bat wings

Settings: Steps: 40, Sampler: Euler a, CFG scale: 9, Size: 768x1024, Highres. fix, Denoising strength: 0.7

During the generation of this batch, the X/Y plot was generated using the "X/Y plot" txt2img script, along with the following settings:

  • X-axis: Prompt S/R: cyberpunk, steampunk, dieselpunk, biopunk, cassettepunk, atompunk, cyberpop, gothic, fantasy
  • Y-axis: Seed: -1, -1, -1
This script searches for the first value (in this case "cyberpunk") within the prompt, and replaces the string with the subsequent comma-separated values.
Date
Source Own work
Author Benlisquare
Permission
(Reusing this file)
Output images

As the creator of the output images, I release this image under the licence displayed within the template below.

Stable Diffusion AI model

The Stable Diffusion AI model is released under the CreativeML OpenRAIL-M License, which "does not impose any restrictions on reuse, distribution, commercialization, adaptation" as long as the model is not being intentionally used to cause harm to individuals, for instance, to deliberately mislead or deceive, and the authors of the AI models claim no rights over any image outputs generated, as stipulated by the license.

Addendum on datasets used to teach AI neural networks
Artworks generated by Stable Diffusion are algorithmically created based on the AI diffusion model's neural network as a result of learning from various datasets; the algorithm does not use preexisting images from the dataset to create the new image. Ergo, generated artworks cannot be considered derivative works of components from within the original dataset, nor can any coincidental resemblance to any particular artist's drawing style fall foul of de minimis. While an artist can claim copyright over individual works, they cannot claim copyright over mere resemblance over an artistic drawing or painting style. In simpler terms, Vincent van Gogh can claim copyright to The Starry Night, however he cannot claim copyright to a picture of a T-34 tank painted with similar brushstroke styles as Gogh's The Starry Night created by someone else.
File history includes unedited version(s)

The upload history for this file includes one or more unedited versions of the file uploaded shortly before the final version was uploaded. The unedited versions are not intended to be used independently, and should not be split out as separate files unless this is needed for a specific known use.

Licensing

[edit]
I, the copyright holder of this work, hereby publish it under the following licenses:
w:en:Creative Commons
attribution share alike
This file is licensed under the Creative Commons Attribution-Share Alike 4.0 International license.
You are free:
  • to share – to copy, distribute and transmit the work
  • to remix – to adapt the work
Under the following conditions:
  • attribution – You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
  • share alike – If you remix, transform, or build upon the material, you must distribute your contributions under the same or compatible license as the original.
GNU head Permission is granted to copy, distribute and/or modify this document under the terms of the GNU Free Documentation License, Version 1.2 or any later version published by the Free Software Foundation; with no Invariant Sections, no Front-Cover Texts, and no Back-Cover Texts. A copy of the license is included in the section entitled GNU Free Documentation License.
You may select the license of your choice.

Usage notes

[edit]

To display a single grid cell individually, use the {{CSS image crop}} template. For example:

Quarter size

{{CSS image crop |Image=X-Y plot of algorithmically-generated AI art by different science-fiction subgenres.png | bSize = 3456 | cWidth = 384 | cHeight = 512 | oTop = 581 | oLeft = 2304 | Location = none | Description = | Alt = }}

Sixteenth size

{{CSS image crop |Image=X-Y plot of algorithmically-generated AI art by different science-fiction subgenres.png | bSize = 1728 | cWidth = 192 | cHeight = 256 | oTop = 292 | oLeft = 576 | Location = none | Description = | Alt = }}

If using native resolution (warning, very wasteful use of bandwidth), start from an initial top offset value of 139, and then progress each row using multiples of 1024; meanwhile, columns are progressed using increments of 768 starting from zero. Depending on the set size of the image, the vertical offset values should remain divisible by 64/128/256/512/etc plus the initial offset for the header, while the horizontal offset values would be divisible by 48/96/192/384/etc, assuming appropriate size, width and height values have been chosen. Divide the initial top offset of 139 by the same ratio that you wish to rescale the image to, rounding up if it is not a whole number.

File history

Click on a date/time to view the file as it appeared at that time.

Date/TimeThumbnailDimensionsUserComment
current12:36, 2 November 2022Thumbnail for version as of 12:36, 2 November 20226,912 × 3,211 (31 MB)Benlisquare (talk | contribs)use upscaled latent space to ensure that finer details are generated. still using SD ft-mse-original VAE
09:18, 1 November 2022Thumbnail for version as of 09:18, 1 November 20226,912 × 3,211 (29.62 MB)Benlisquare (talk | contribs)use SD ft-mse-original VAE to adjust minor details
14:29, 31 October 2022Thumbnail for version as of 14:29, 31 October 20226,912 × 3,211 (29.39 MB)Benlisquare (talk | contribs)inpaint those horrifying looking hands
11:43, 30 October 2022Thumbnail for version as of 11:43, 30 October 20226,912 × 3,211 (29.4 MB)Benlisquare (talk | contribs){{Information |Description=An X/Y plot of algorithmically-generated AI portrait artworks depicting the aesthetics of different science-fiction subgenres, created using a custom merged Stable Diffusion AI diffusion model checkpoint featuring [https://huggingface.co/hakurei/waifu-diffusion wd-v1-3-full.ckpt] merged with [https://ai.zeipher.com/ F111] and [https://huggingface.co/runwayml/stable-diffusion-v1-5 Stable Diffusion V1-5] at 0.5 sigmoid, and then merged with R3...

You cannot overwrite this file.

File usage on other wikis

The following other wikis use this file:

Metadata

This file contains additional information such as Exif metadata which may have been added by the digital camera, scanner, or software program used to create or digitize it. If the file has been modified from its original state, some details such as the timestamp may not fully reflect those of the original file. The timestamp is only as accurate as the clock in the camera, and it may be completely wrong.

Retrieved from "https://commons.wikimedia.org/w/index.php?title=File:X-Y_plot_of_algorithmically-generated_AI_art_by_different_science-fiction_subgenres.png&oldid=928798628"