Update README.md
Browse files
README.md
CHANGED
|
@@ -1,5 +1,6 @@
|
|
| 1 |
---
|
| 2 |
library_name: diffusers
|
|
|
|
| 3 |
---
|
| 4 |
# Furception v1.0, by Project RedRocket.
|
| 5 |
|
|
@@ -14,12 +15,6 @@ Furception 1.0:
|
|
| 14 |
|
| 15 |
Note that the output is overall smoother and has significantly less artifacting around edges in high-detail regions.
|
| 16 |
|
| 17 |
-
#### Licensing:
|
| 18 |
-
|
| 19 |
-
You are free to use this model for personal, non-commercial use.
|
| 20 |
-
|
| 21 |
-
You are also free to distribute this model alongside other (non-commercial) models, as long as you give credit. Please include the version number as well in case future models are released.
|
| 22 |
-
|
| 23 |
#### Training details:
|
| 24 |
Overall training is fundamentally similar to LDM. We used the same relative base weights for MAE, MSE, and LPIPS as used in LDM and in sd-vae-ft-mse in the case of LPIPS. The discriminator's weight in the loss objective is dynamically set so that the gradient norm for the discriminator is half that of the reconstruction loss, just like LDM. We used a similar discriminator to what LDM uses, except reparameterized to Wasserstein loss with a gradient penalty and with its group norm layers replaced with layer norms.
|
| 25 |
|
|
|
|
| 1 |
---
|
| 2 |
library_name: diffusers
|
| 3 |
+
license: cc-by-nc-sa-4.0
|
| 4 |
---
|
| 5 |
# Furception v1.0, by Project RedRocket.
|
| 6 |
|
|
|
|
| 15 |
|
| 16 |
Note that the output is overall smoother and has significantly less artifacting around edges in high-detail regions.
|
| 17 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
#### Training details:
|
| 19 |
Overall training is fundamentally similar to LDM. We used the same relative base weights for MAE, MSE, and LPIPS as used in LDM and in sd-vae-ft-mse in the case of LPIPS. The discriminator's weight in the loss objective is dynamically set so that the gradient norm for the discriminator is half that of the reconstruction loss, just like LDM. We used a similar discriminator to what LDM uses, except reparameterized to Wasserstein loss with a gradient penalty and with its group norm layers replaced with layer norms.
|
| 20 |
|