Commit
•
5ff7909
1
Parent(s):
93160e7
Update README.md
Browse files
README.md
CHANGED
|
@@ -28,6 +28,8 @@ The **Stable-Diffusion-v1-3** checkpoint was initialized with the weights of the
|
|
| 28 |
checkpoint and subsequently fine-tuned on 195,000 steps at resolution `512x512` on "laion-improved-aesthetics" and 10 % dropping of the text-conditioning to improve [classifier-free guidance sampling](https://arxiv.org/abs/2207.12598).
|
| 29 |
For more information, please refer to [Training](#training).
|
| 30 |
|
|
|
|
|
|
|
| 31 |
## Model Details
|
| 32 |
- **Developed by:** Robin Rombach, Patrick Esser
|
| 33 |
- **Model type:** Diffusion-based text-to-image generation model
|
|
|
|
| 28 |
checkpoint and subsequently fine-tuned on 195,000 steps at resolution `512x512` on "laion-improved-aesthetics" and 10 % dropping of the text-conditioning to improve [classifier-free guidance sampling](https://arxiv.org/abs/2207.12598).
|
| 29 |
For more information, please refer to [Training](#training).
|
| 30 |
|
| 31 |
+
This weights here are intended to be used with the D🧨iffusers library. If you are looking for the weights to be loaded into the CompVis Stable Diffusion codebase, [come here](https://huggingface.co/CompVis/stable-diffusion-v-1-3-original)
|
| 32 |
+
|
| 33 |
## Model Details
|
| 34 |
- **Developed by:** Robin Rombach, Patrick Esser
|
| 35 |
- **Model type:** Diffusion-based text-to-image generation model
|