Update README.md

2023-08-09 03:42:43 +02:00
parent 7f22d9a21e
commit 451cb196b7
1 changed files with 16 additions and 5 deletions
@@ -22,14 +22,25 @@ Without the interposer, the two latent spaces are incompatible:
 ## Training
 The training script should spit out a working model, nn layout is probably not optimal but I'm pretty short on VRAM to trial and error a better layout. PRs welcome.

+### Interposer v1.1
+This is the second release using the "spaceship" architecture. It was trained on the Flickr2K dataset and was continued from the v1.0 checkpoint.
+Overall, it seems to perform a lot better, especially for real life photos. I also investigated the odd v1->xl artifacts but in the end it seems [inherent to the VAE decoder stage.](https://github.com/comfyanonymous/ComfyUI/issues/1116)
+
+![loss](https://github.com/city96/SD-Latent-Interposer/assets/125218114/e890420f-cebd-4f88-b243-62560b8384e5)
+
+### Interposer v1.0 
 Not sure why the training loss is so different, it might be due to the """highly curated""" dataset of 1000 random images from my Downloads folder that I used to train it.

 I probably should've just grabbed LAION.

-I also trained a v1-to-v2 mode, which
+I also trained a v1-to-v2 mode, before realizing v1 and v2 shared the same latent space. Oh well.

-### v1.0 Training loss/progress
+<details>
+  <summary>Loss graphs for v1.0 models</summary>
+  
+  ![loss](https://github.com/city96/SD-Latent-Interposer/assets/125218114/f92c399b-a823-4521-b09b-8bdc3795f1ea)
+  
+  ![xl-to-v1_interposer](https://github.com/city96/SD-Latent-Interposer/assets/125218114/0d963bc5-570f-4ebe-95db-16e261f05e48)
+  
+</details>

-![loss](https://github.com/city96/SD-Latent-Interposer/assets/125218114/f92c399b-a823-4521-b09b-8bdc3795f1ea)
-
-![xl-to-v1_interposer](https://github.com/city96/SD-Latent-Interposer/assets/125218114/0d963bc5-570f-4ebe-95db-16e261f05e48)