Commit
·
5986767
1
Parent(s):
d90661e
Update README.md
Browse files
README.md
CHANGED
|
@@ -41,7 +41,7 @@ This model is still in its infancy and it's meant to be constantly updated and t
|
|
| 41 |
- [vae.sygil_muse_v0.1.pt](https://huggingface.co/Sygil/Sygil-Muse/blob/main/vae.sygil_muse_v0.1.pt): Trained from scratch for 3.0M steps with **dim: 128** and **vq_codebook_size: 256**.
|
| 42 |
- [maskgit.3461001.p](https://huggingface.co/Sygil/Sygil-Muse/blob/main/maskgit.3461001.pt): Maskgit trained from the VAE for 3.46M steps
|
| 43 |
- #### Beta:
|
| 44 |
-
- [vae.
|
| 45 |
|
| 46 |
Note: Checkpoints under the Beta section are updated daily or at least 3-4 times a week. While the beta checkpoints can be used as they are only the latest version is kept on the repo and the older checkpoints are removed when a new one
|
| 47 |
is uploaded to keep the repo clean.
|
|
@@ -66,7 +66,7 @@ The model was trained on the following dataset:
|
|
| 66 |
- **Resolution/Image Size**: First trained at a resolution of 64x64, then increased to 256x256 and then to 512x512. Check the notes down below for more details on this.
|
| 67 |
- **Dimension:** 128
|
| 68 |
- **vq_codebook_size:** 8192
|
| 69 |
-
- **Total Training Steps:**
|
| 70 |
|
| 71 |
Note: On Muse we can change the image_size or resolution at any time without having to train the model from scratch again, this allows us to first train the model at low resolution using the same `dim` and `vq_codebook_size` to train faster and then we can increase the `image_size` and use a higher resolution once the model has trained enough.
|
| 72 |
|
|
|
|
| 41 |
- [vae.sygil_muse_v0.1.pt](https://huggingface.co/Sygil/Sygil-Muse/blob/main/vae.sygil_muse_v0.1.pt): Trained from scratch for 3.0M steps with **dim: 128** and **vq_codebook_size: 256**.
|
| 42 |
- [maskgit.3461001.p](https://huggingface.co/Sygil/Sygil-Muse/blob/main/maskgit.3461001.pt): Maskgit trained from the VAE for 3.46M steps
|
| 43 |
- #### Beta:
|
| 44 |
+
- [vae.664500.pt](https://huggingface.co/Sygil/Sygil-Muse/blob/main/vae.664500.pt): Trained from scratch for 664K steps and higher **vq_codebook_size** than before.
|
| 45 |
|
| 46 |
Note: Checkpoints under the Beta section are updated daily or at least 3-4 times a week. While the beta checkpoints can be used as they are only the latest version is kept on the repo and the older checkpoints are removed when a new one
|
| 47 |
is uploaded to keep the repo clean.
|
|
|
|
| 66 |
- **Resolution/Image Size**: First trained at a resolution of 64x64, then increased to 256x256 and then to 512x512. Check the notes down below for more details on this.
|
| 67 |
- **Dimension:** 128
|
| 68 |
- **vq_codebook_size:** 8192
|
| 69 |
+
- **Total Training Steps:** 664,500
|
| 70 |
|
| 71 |
Note: On Muse we can change the image_size or resolution at any time without having to train the model from scratch again, this allows us to first train the model at low resolution using the same `dim` and `vq_codebook_size` to train faster and then we can increase the `image_size` and use a higher resolution once the model has trained enough.
|
| 72 |
|