Update README.md
Browse files
README.md
CHANGED
|
@@ -21,6 +21,8 @@ This is the same version 1 model that has been test-released in AI Novelist/Trin
|
|
| 21 |
|
| 22 |
The dataset is filtered to exclude NSFW or unsafe contents. After our extensive experimentation and testing with 10M+ user generated images, we decided that this model is safe enough and less prone to spit out a questionable content than the stock SD v1.4 model or other anime/manga models. However, if the user tortures this model enough until it talks, it may be still possible to force this model to generate obnoxious materials. We do not consider this model to be 100% risk-free.
|
| 23 |
|
|
|
|
|
|
|
| 24 |
#### Examples
|
| 25 |
|
| 26 |
Below images are directly generated by the native TrinArt service with a custom upscaler and processes, so your mileage may vary.
|
|
|
|
| 21 |
|
| 22 |
The dataset is filtered to exclude NSFW or unsafe contents. After our extensive experimentation and testing with 10M+ user generated images, we decided that this model is safe enough and less prone to spit out a questionable content than the stock SD v1.4 model or other anime/manga models. However, if the user tortures this model enough until it talks, it may be still possible to force this model to generate obnoxious materials. We do not consider this model to be 100% risk-free.
|
| 23 |
|
| 24 |
+
*This statement does not restrict third-party from training a derivative of this model that includes NSFW.
|
| 25 |
+
|
| 26 |
#### Examples
|
| 27 |
|
| 28 |
Below images are directly generated by the native TrinArt service with a custom upscaler and processes, so your mileage may vary.
|