patrickvonplaten
commited on
Commit
•
0b2e68a
1
Parent(s):
2b64332
Update README.md
Browse files
README.md
CHANGED
@@ -181,8 +181,8 @@ We currently provide four checkpoints, which were trained as follows.
|
|
181 |
- [`stable-diffusion-v1-2`](https://huggingface.co/CompVis/stable-diffusion-v1-2): Resumed from `stable-diffusion-v1-1`.
|
182 |
515,000 steps at resolution `512x512` on "laion-improved-aesthetics" (a subset of laion2B-en,
|
183 |
filtered to images with an original size `>= 512x512`, estimated aesthetics score `> 5.0`, and an estimated watermark probability `< 0.5`. The watermark estimate is from the LAION-5B metadata, the aesthetics score is estimated using an [improved aesthetics estimator](https://github.com/christophschuhmann/improved-aesthetic-predictor)).
|
184 |
-
- [`stable-diffusion-v1-3`](https://huggingface.co/CompVis/stable-diffusion-v1-3): Resumed from `stable-diffusion-v1-2`. 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)
|
185 |
-
- [
|
186 |
|
187 |
- **Hardware:** 32 x 8 x A100 GPUs
|
188 |
- **Optimizer:** AdamW
|
|
|
181 |
- [`stable-diffusion-v1-2`](https://huggingface.co/CompVis/stable-diffusion-v1-2): Resumed from `stable-diffusion-v1-1`.
|
182 |
515,000 steps at resolution `512x512` on "laion-improved-aesthetics" (a subset of laion2B-en,
|
183 |
filtered to images with an original size `>= 512x512`, estimated aesthetics score `> 5.0`, and an estimated watermark probability `< 0.5`. The watermark estimate is from the LAION-5B metadata, the aesthetics score is estimated using an [improved aesthetics estimator](https://github.com/christophschuhmann/improved-aesthetic-predictor)).
|
184 |
+
- [`stable-diffusion-v1-3`](https://huggingface.co/CompVis/stable-diffusion-v1-3): Resumed from `stable-diffusion-v1-2`. 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).
|
185 |
+
- [`stable-diffusion-v1-4`](https://huggingface.co/CompVis/stable-diffusion-v1-4) Resumed from `stable-diffusion-v1-2`.225,000 steps at resolution `512x512` on "laion-aesthetics v2 5+" and 10 % dropping of the text-conditioning to improve [classifier-free guidance sampling](https://arxiv.org/abs/2207.12598).
|
186 |
|
187 |
- **Hardware:** 32 x 8 x A100 GPUs
|
188 |
- **Optimizer:** AdamW
|