add link to kane's repo
Browse files
README.md
CHANGED
|
@@ -18,6 +18,8 @@ Example new classes are "cloud strife", "tifa lockhart", "aerith gainsborough",
|
|
| 18 |
|
| 19 |
Training was performed using Kane Wallmann's fork of the original Xavier Xiao which uses the filenames of training images as the caption on an individual basis, rather than a blanket "class" word.
|
| 20 |
|
|
|
|
|
|
|
| 21 |
Regularization sets such as "man" and "woman" were used for the male and female characters, and additional regularization sets were created for cities, buildings, and groups of people.
|
| 22 |
|
| 23 |
Training set includes screenshots of groups of characters, and compared to prior attempts these additional group images improve the ability to create group images at inference time. An example training image would be "cloud strife and barret wallace standing in a garden with a waterfall in the background". The propensity for inference to generate mixed or muddied characters is lowered, and exchanges of clothing and hair color is reduced.
|
|
|
|
| 18 |
|
| 19 |
Training was performed using Kane Wallmann's fork of the original Xavier Xiao which uses the filenames of training images as the caption on an individual basis, rather than a blanket "class" word.
|
| 20 |
|
| 21 |
+
https://github.com/kanewallmann/Dreambooth-Stable-Diffusion
|
| 22 |
+
|
| 23 |
Regularization sets such as "man" and "woman" were used for the male and female characters, and additional regularization sets were created for cities, buildings, and groups of people.
|
| 24 |
|
| 25 |
Training set includes screenshots of groups of characters, and compared to prior attempts these additional group images improve the ability to create group images at inference time. An example training image would be "cloud strife and barret wallace standing in a garden with a waterfall in the background". The propensity for inference to generate mixed or muddied characters is lowered, and exchanges of clothing and hair color is reduced.
|