Upload README.md
Browse files
README.md
CHANGED
|
@@ -10,7 +10,7 @@ inference: false
|
|
| 10 |
|
| 11 |
This model has been trained to simulate what it may be like if the current (December 2022) artstation protest images against AI were actually used as training data inside a conventional anime stable diffusion model.
|
| 12 |
|
| 13 |
-
This was a quick and dirty DreamBooth model trained without regularization for 3023 steps. the key word is **ai protest**, simply use it in your prompt. **you may wish to increase the weight and/or duplicate it, as the influence is quite weak
|
| 14 |
|
| 15 |
The base model is an early preview of WD1.4 (colloquially "WD 1.3.5") [wd-1-4-float32-booru-110k](https://huggingface.co/hakurei/waifu-diffusion-v1-4/blob/9fa4a42a9c4a0948472fa909e6c1a39be0dda699/models/wd-1-4-float32-booru-110k.ckpt) This means you should probably be using danbooru-style image tags.
|
| 16 |
|
|
|
|
| 10 |
|
| 11 |
This model has been trained to simulate what it may be like if the current (December 2022) artstation protest images against AI were actually used as training data inside a conventional anime stable diffusion model.
|
| 12 |
|
| 13 |
+
This was a quick and dirty DreamBooth model trained without regularization for 3023 steps. the key word is **ai protest**, simply use it in your prompt. **you may wish to increase the weight and/or duplicate it, as the influence is quite weak.**
|
| 14 |
|
| 15 |
The base model is an early preview of WD1.4 (colloquially "WD 1.3.5") [wd-1-4-float32-booru-110k](https://huggingface.co/hakurei/waifu-diffusion-v1-4/blob/9fa4a42a9c4a0948472fa909e6c1a39be0dda699/models/wd-1-4-float32-booru-110k.ckpt) This means you should probably be using danbooru-style image tags.
|
| 16 |
|