Commit
•
c46d782
1
Parent(s):
c337526
Update README.md
Browse files
README.md
CHANGED
@@ -68,7 +68,7 @@ This model is fine tuned from Stable Diffusion v1-3 where the text encoder has b
|
|
68 |
- **Batch:** 6 x 4 = 24
|
69 |
- **Learning rate:** warmup to 0.0001 for 1,000 steps and then kept constant
|
70 |
|
71 |
-
Training was done using a [modified version of the original Stable Diffusion training code]((https://github.com/justinpinkney/stable-diffusion)
|
72 |
|
73 |
|
74 |
# Uses
|
@@ -140,17 +140,4 @@ Specifically, the checker compares the class probability of harmful concepts in
|
|
140 |
The concepts are passed into the model with the generated image and compared to a hand-engineered weight for each NSFW concept.
|
141 |
|
142 |
|
143 |
-
## Citation
|
144 |
-
|
145 |
-
```bibtex
|
146 |
-
@InProceedings{Rombach_2022_CVPR,
|
147 |
-
author = {Rombach, Robin and Blattmann, Andreas and Lorenz, Dominik and Esser, Patrick and Ommer, Bj\"orn},
|
148 |
-
title = {High-Resolution Image Synthesis With Latent Diffusion Models},
|
149 |
-
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
|
150 |
-
month = {June},
|
151 |
-
year = {2022},
|
152 |
-
pages = {10684-10695}
|
153 |
-
}
|
154 |
-
```
|
155 |
-
|
156 |
*This model card was written by: Justin Pinkney and is based on the [Stable Diffusion model card](https://huggingface.co/CompVis/stable-diffusion-v1-4).*
|
|
|
68 |
- **Batch:** 6 x 4 = 24
|
69 |
- **Learning rate:** warmup to 0.0001 for 1,000 steps and then kept constant
|
70 |
|
71 |
+
Training was done using a [modified version of the original Stable Diffusion training code]((https://github.com/justinpinkney/stable-diffusion), the original version of the weights is [here](https://huggingface.co/lambdalabs/stable-diffusion-image-conditioned).
|
72 |
|
73 |
|
74 |
# Uses
|
|
|
140 |
The concepts are passed into the model with the generated image and compared to a hand-engineered weight for each NSFW concept.
|
141 |
|
142 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
143 |
*This model card was written by: Justin Pinkney and is based on the [Stable Diffusion model card](https://huggingface.co/CompVis/stable-diffusion-v1-4).*
|