维基百科

File:Algorithmically-generated AI-generated artwork of a cyberpunk cityscape.png

原始文件 （8,192 × 4,096像素，文件大小：36.8 MB，MIME类型：image/png）

摘要

描述

Algorithmically-generated AI artwork featuring a cyberpunk cityscape, created using the Stable Diffusion V1-4 AI diffusion model.

Procedure/Methodology

All artworks 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 768x512 image was generated with txt2img using the following prompts:

Prompt: digital painting of a cyberpunk cityscape, neon signs, futuristic, art style of range murata artgerm norman rockwell wlop katsuhiro otomo shintaro kago monet

Negative prompt: none

Settings: Steps: 50, Sampler: Euler a, CFG scale: 7, Size: 768x512

Afterwards, the image was extended by 128 pixels on the top, bottom, left and right sides using fourteen successive passes of the "Outpainting mk2" script within img2img, adding additional detail to the image one after the other, until the image's dimensions reached 2048x1024 as its natively generated size (prior to the commencement of any upscaling). For each individual pass, this was done using a setting of 100 sampling steps with Euler a, denoising strength of 0.8, CFG scale of 7, mask blur of 8, fall-off exponent value of 1.8, colour variation set to 0.03. This subsequently increased the field of view of the image compared to the originally generated image, from one tiny portion of the street in the centre of the image, to a significantly wider view showing the buildings on both sides, in addition to the pedestrian foreground and cityscape in the distance.

Then, two passes of the SD upscale script using "SwinIR_4x" were run within img2img. The first pass used a tile overlap of 128, denoising strength of 0.1, 150 sampling steps with Euler a, and a CFG scale of 7. The second pass used a tile overlap of 256, denoising strength of 0.1, 150 sampling steps with Euler a, and a CFG scale of 7. This creates our final 8192x4096 image.
日期
来源 自己的作品
作者 Benlisquare
授权
(二次使用本文件)
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.

许可协议

Public domain
这个作品属于公有领域，因为其由计算机算法或人工智能生成，不包含足够的人类作者信息来支持版权主张。
英国以及香港为计算机生成的作品提供自创作后50年的有限版权期限。 [1][2]
AI derivative works 法律免责声明
大多数图像生成人工智能模型都是使用受版权保护的作品进行训练的。在某些情况下，此类模型可以生成包含受版权保护的训练图像的主要版权元素的图像，从而使这些输出物成为衍生作品。因此，上传到维基共享资源的人工智能生成的艺术作品可能会侵犯原始作品作者的权利。有关更多详细信息，请参阅共享资源:人工智能生成媒体文件。

azərbaycanca ∙ Deutsch ∙ English ∙ español ∙ français ∙ galego ∙ हिन्दी ∙ 日本語 ∙ português do Brasil ∙ русский ∙ slovenščina ∙ Türkçe ∙ Tiếng Việt ∙ 中文 ∙ 中文（简体） ∙ 中文（繁體） ∙ +/−

说明

添加一行文字以描述该文件所表现的内容

此文件中描述的项目

描繪內容

核對和

1b1ce85f8eb9877ec9e82e3eddfdd9c868e98f0d

确定方法：​SHA-1

資料大小

38,584,745 字节

高度

4,096 像素

寬度

8,192 像素

文件历史

点击某个日期/时间查看对应时刻的文件。

日期/时间缩⁠略⁠图大小用户备注
当前2022年10月4日 (二) 15:542022年10月4日 (二) 15:54版本的缩略图8,192 × 4,096（36.8 MB）Benlisquarere-do final steps using 0.1 denoising strength SwinIR_4x (instead of 0.01), as I'm not too satisfied with how the building detail turned out with the lower denoising setting
2022年10月4日 (二) 15:042022年10月4日 (二) 15:04版本的缩略图8,192 × 4,096（37.03 MB）Benlisquare{{Information |Description=Algorithmically-generated AI artwork featuring a cyberpunk cityscape, created using the [https://github.com/CompVis/stable-diffusion Stable Diffusion V1-4] AI diffusion model. ;Procedure/Methodology All artworks 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] created by [https://github.com/AUTOMATIC1111 AUTOMATIC1111]. A single 768x512 imag...

以下2个页面使用本文件：

全域文件用途

以下其他wiki使用此文件：

检索自“https://zh.wikipedia.org/wiki/File:Algorithmically-generated_AI-generated_artwork_of_a_cyberpunk_cityscape.png”