跳至內容

File:Algorithmically-generated black and white portrait art of a young Japanese woman in the snow.png

頁面內容不支援其他語言。
這個檔案來自維基共享資源
維基百科，自由的百科全書

原始檔案 ‎（2,048 × 4,096 像素，檔案大小：11.19 MB，MIME 類型：image/png）

摘要

描述

Algorithmically-generated AI portrait artwork in monochrome style, featuring a young Japanese woman at the front of a castle on a snowy day, 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 512x768 image was generated with txt2img using the following prompts:

Prompt: black and white, highly detailed line art, (close up shot of:0.6) (full body1.3) of a teenage Japanese geisha girl (pretty face:1.4) (realistic eyes:1.2) (detailed pupils) (ornate coiffed hair), in front of battlements, on a moonlit night, snowfall, [:falling snowflakes:0.7], by (Yoji Shinkawa:1.2), (Kentaro Miura), (WLOP), (Artgerm), (intricate human hands), [bodycon] intricate

Negative prompt: disney, two heads, ((mutated hands and fingers and face and nose)) (walleyed), blurred face, ((poorly drawn face)) (long neck) ((ugly)) frown, ((neutral expressions)), curly hair, [[child]]

Settings: Steps: 50, Sampler: Euler a, CFG scale: 6, Size: 512x768

Afterwards, the image was extended by 256 pixels total on the bottom using two 128 pixel passes of the "Outpainting mk2" script within img2img. 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 increases the image's dimensions to 512x1024, while also revealing the young woman's hands and lower dress, which were previously absent from the original AI-generated image made within txt2img which only featured the woman from the navel upwards.

Then, two passes of the SD upscale script using "SwinIR_4x" were run within img2img. The first pass used a tile overlap of 64, 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 128, denoising strength of 0.1, 150 sampling steps with Euler a, and a CFG scale of 7. This creates our final 2048x4096 image.
日期
來源 自己的作品
作者 Benlisquare
授權許可
(重用此檔案)
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.

授權條款

我，本作品的著作權持有者，決定用以下授權條款發佈本作品：
w:zh:創用CC
姓名標示 相同方式分享
此檔案採用創用CC 姓名標示-相同方式分享 4.0 國際授權條款。
您可以自由：
  • 分享 – 複製、發佈和傳播本作品
  • 重新修改 – 創作演繹作品
惟需遵照下列條件：
  • 姓名標示 – 您必須指名出正確的製作者，和提供授權條款的連結，以及表示是否有對內容上做出變更。您可以用任何合理的方式來行動，但不得以任何方式表明授權條款是對您許可或是由您所使用。
  • 相同方式分享 – 如果您利用本素材進行再混合、轉換或創作，您必須基於如同原先的相同或兼容的條款，來分布您的貢獻成品。
GNU head 已授權您依據自由軟體基金會發行的無固定段落、封面文字和封底文字GNU自由文件授權條款1.2版或任意後續版本，對本檔進行複製、傳播和／或修改。該協議的副本列在GNU自由文件授權條款中。
您可以選擇您需要的授權條款。

說明

添加單行說明來描述出檔案所代表的內容

在此檔案描寫的項目

描繪內容

檔案來源 Chinese (Taiwan) (已轉換拼寫)

上傳者的原創作品

校驗和

85e491d4b02985c4ea993dd1f12b01b1a18319ea

斷定方法：​SHA-1 中文 (已轉換拼寫)

資料大小

11,730,108 位元組

高度

4,096 像素

寬度

2,048 像素

隸屬於

人工智能生成圖像 中文 (已轉換拼寫)

類型

人工智慧藝術 中文 (已轉換拼寫)

檔案歷史

點選日期/時間以檢視該時間的檔案版本。

日期/時間縮⁠圖尺寸使用者備⁠註
目前2022年10月7日 (五) 22:47於 2022年10月7日 (五) 22:47 版本的縮圖2,048 × 4,096（11.19 MB）Benlisquare{{Information |Description=Algorithmically-generated AI portrait artwork in monochrome style, featuring a young Japanese woman at the front of a castle on a snowy day, 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 [...

下列頁面有用到此檔案：

取自「https://zh.wikipedia.org/wiki/File:Algorithmically-generated_black_and_white_portrait_art_of_a_young_Japanese_woman_in_the_snow.png」