File:Algorithmically-generated animation of young woman adorned with flowers.webm

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

Original file ‎(WebM audio/video file, VP9, length 10 s, 1,024 × 1,024 pixels, 81.84 Mbps overall, file size: 97.57 MB)

Captions

Captions

Add a one-line explanation of what this file represents

Summary[edit]

Description

Algorithmically-generated 10-second animation featuring a young woman adorned with flowers, running at 30 frames per second, consisting of frames created using the Stable Diffusion V1-4 AI diffusion model.

Procedure/Methodology

All still frames created using a single NVIDIA RTX 3090. Front-end used for the entire generation process is Stable Diffusion web UI created by AUTOMATIC1111.

A single 512x512 image was generated with txt2img using the following prompts:

Prompt: instagram model in art style of Albert Lynch and Carne Griffiths and Franz Xaver Winterhalter and Lilia Alvarado and Sophie Anderson, highly detailed, sharp focus illustration, artstation hq, (detailed face), (((full body))), (((standing)))

Negative prompt: (bad anatomy) (portrait)

Settings: Steps: 30, Sampler: DDIM, CFG scale: 15, Size: 512x512

One pass of the SD upscale script using "SwinIR_4x" was run within img2img, using a tile overlap of 64, denoising strength of 0.3, 150 sampling steps with Euler a, and a CFG scale of 8. This creates a 1024x1024 image for use as a baseline to generate the 300 still frames necessary to play a 10 second video at 30fps.

Using the custom script Stable Diffusion Animation Script v0.6, a 1024x1024 resolution VP9 WEBM video was generated using the following settings:

Settings: Steps: 100, Sampler: Euler a, CFG scale: 12, Animation length: 10, Framerate: 30, Denoise strength: 0.4, Zoom factor: 1.0, X-pixel shift: 0, Y-pixel shift: 0

The keyframe inputs are as follows:

0 | 0.4 | 1.0 | 0 | 0 | flowers | | -1

2 | 0.4 | 1.0 | 0 | 0 | face closer to camera, flowers | (((dark))), (((fog))), (((mist))), (((blur))) | -1

4 | 0.4 | 1.0 | 0 | 0 | face closer to camera | (((dark))), (((fog))), (((mist))), (((blur))) | -1

6 | 0.4 | 1.0 | 0 | 0 | ((face closer to camera)), (((eye contact with viewer))) | (((dark))), (((fog))), (((mist))), (((blur))) | -1

8 | 0.4 | 1.0 | 0 | 0 | ((face closer to camera)), (((eye contact with viewer))), (((disdain))), (((angry glare))) | (((dark))), (((fog))), (((mist))), (((blur))) | -1

10 | 0.4 | 1.0 | 0 | 0 | (((face closer to camera))), (((eye contact with viewer))), (((disdain))), (((angry glare))) | (((dark))), (((fog))), (((mist))), (((blur))) | -1

For context, the script generates the configured number of still frames (in this case 300 frames), based on the above keyframe information (in order: time, denoise, zoom, x-shift, y-shift, positive prompts, negative prompts, seed), and then runs the following in ffmpeg:

ffmpeg -y -framerate 30 -i 20221003183716_%%05d.png -crf 30 -preset slow 20221003183716.webm
Date
Source Own work
Author Benlisquare
Permission
(Reusing this file)
Output video

As the creator of the output video, I release this video 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.

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.

File history

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

Date/TimeThumbnailDimensionsUserComment
current10:32, 3 October 202210 s, 1,024 × 1,024 (97.57 MB)Benlisquare (talk | contribs){{Information |Description=Algorithmically-generated 10-second animation featuring a young woman adorned with flowers, running at 30 frames per second, consisting of frames created using the [https://github.com/CompVis/stable-diffusion Stable Diffusion V1-4] AI diffusion model. ;Procedure/Methodology All still frames created using a single NVIDIA RTX 3090. Front-end used for the entire generation process is [https://github.com/AUTOMATIC1111/stable-diffusion-webui Stable Diffusion web UI] cre...

You cannot overwrite this file.

There are no pages that use this file.

Transcode status

Update transcode status
Format Bitrate Download Status Encode time
VP9 720P 2.58 Mbps Completed 18:09, 31 May 2023 32 s
Streaming 720p (VP9) 2.58 Mbps Completed 08:59, 25 January 2024 1.0 s
VP9 480P 1.29 Mbps Completed 18:09, 31 May 2023 25 s
Streaming 480p (VP9) 1.29 Mbps Completed 18:56, 17 December 2023 2.0 s
VP9 360P 690 kbps Completed 18:09, 31 May 2023 24 s
Streaming 360p (VP9) 691 kbps Completed 02:07, 2 January 2024 1.0 s
VP9 240P 343 kbps Completed 18:08, 31 May 2023 17 s
Streaming 240p (VP9) 343 kbps Completed 20:27, 9 December 2023 1.0 s
WebM 360P 1.02 Mbps Completed 18:08, 31 May 2023 11 s
Streaming 144p (MJPEG) 1.13 Mbps Completed 01:57, 30 October 2023 6.0 s

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:Algorithmically-generated_animation_of_young_woman_adorned_with_flowers.webm&oldid=789640231"