File:X-Y plot of algorithmically-generated AI art by different science-fiction subgenres.png
原始文件 （6,912 × 3,211像素，文件大小：31 MB，MIME类型：image/png）
摘要
| 描述 |
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.
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:
During the generation of this batch, the X/Y plot was generated using the "X/Y plot" txt2img script, along with the following settings:
|
| 日期 | |
| 来源 | 自己的作品 |
| 作者 | Benlisquare |
| 授权 (二次使用本文件) |
As the creator of the output images, I release this image under the licence displayed within the template below.
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.
|
 | 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
- 您可以自由地：
- 共享 – 复制、发行并传播本作品
- 修改 – 改编作品
- 惟须遵守下列条件：
- 署名 – 您必须对作品进行署名，提供授权条款的链接，并说明是否对原始内容进行了更改。您可以用任何合理的方式来署名，但不得以任何方式表明许可人认可您或您的使用。
- 相同方式共享 – 如果您再混合、转换或者基于本作品进行创作，您必须以与原先许可协议相同或相兼容的许可协议分发您贡献的作品。
|
已授权您依据自由软件基金会发行的无固定段落及封面封底文字（Invariant Sections, Front-Cover Texts, and Back-Cover Texts）的GNU自由文件许可协议1.2版或任意后续版本的条款，复制、传播和／或修改本文件。该协议的副本请见“GNU Free Documentation License”。 |
Usage notes
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.
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11月2日 (三) 12:36 | | 6,912 × 3,211（31 MB） | Benlisquare | use upscaled latent space to ensure that finer details are generated. still using SD ft-mse-original VAE |
| 2022年11月1日 (二) 09:18 |  | 6,912 × 3,211（29.62 MB） | Benlisquare | use SD ft-mse-original VAE to adjust minor details | |
| 2022年10月31日 (一) 14:29 |  | 6,912 × 3,211（29.39 MB） | Benlisquare | inpaint those horrifying looking hands | |
| 2022年10月30日 (日) 11:43 |  | 6,912 × 3,211（29.4 MB） | Benlisquare | {{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... |
文件用途
以下页面使用本文件：
全域文件用途
以下其他wiki使用此文件：
- en.wikipedia.org上的用途
