Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
This is a finetuned version of the LTX Video 0.9 VAE, which attempts to improve the checkerboard artifacts which are common in the original model. Most of the finetuning was done on the decoder only, to prevent the latent space from changing. After that, some limited training of the encoder only, with the decoder frozen, was done to further reduce artifacts while only minimally changing the latent space.
|
| 2 |
|
| 3 |
The finetuning was partially successful, as it did reduce the strength of the artifacts, but it did not eliminate them entirely. Unfortunately they may be very diffucult to eliminate completely, due to the use of strided convolutions in the encoder and pixel shuffle upscaling in the decoder. ([See this article for explanation](https://distill.pub/2016/deconv-checkerboard/))
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: openrail
|
| 3 |
+
base_model:
|
| 4 |
+
- Lightricks/LTX-Video
|
| 5 |
+
---
|
| 6 |
This is a finetuned version of the LTX Video 0.9 VAE, which attempts to improve the checkerboard artifacts which are common in the original model. Most of the finetuning was done on the decoder only, to prevent the latent space from changing. After that, some limited training of the encoder only, with the decoder frozen, was done to further reduce artifacts while only minimally changing the latent space.
|
| 7 |
|
| 8 |
The finetuning was partially successful, as it did reduce the strength of the artifacts, but it did not eliminate them entirely. Unfortunately they may be very diffucult to eliminate completely, due to the use of strided convolutions in the encoder and pixel shuffle upscaling in the decoder. ([See this article for explanation](https://distill.pub/2016/deconv-checkerboard/))
|