Commit
·
6820509
1
Parent(s):
6ace42a
Update README.md
Browse files
README.md
CHANGED
|
@@ -81,9 +81,19 @@ image.save("fantasy_forest_illustration.png")
|
|
| 81 |
- If you have low GPU RAM available, make sure to add a `pipe.enable_attention_slicing()` after sending it to `cuda` for less VRAM usage (to the cost of speed).
|
| 82 |
|
| 83 |
## Available Checkpoints:
|
| 84 |
-
-
|
| 85 |
-
|
| 86 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 87 |
## Training
|
| 88 |
|
| 89 |
**Training Data**:
|
|
|
|
| 81 |
- If you have low GPU RAM available, make sure to add a `pipe.enable_attention_slicing()` after sending it to `cuda` for less VRAM usage (to the cost of speed).
|
| 82 |
|
| 83 |
## Available Checkpoints:
|
| 84 |
+
- #### Stable:
|
| 85 |
+
- [Sygil Diffusion v0.1](https://huggingface.co/Sygil/Sygil-Diffusion/blob/main/sygil-diffusion-v0.1.ckpt): Trained on Stable Diffusion 1.5 for 800,000 steps.
|
| 86 |
+
- [Sygil Diffusion v0.2](https://huggingface.co/Sygil/Sygil-Diffusion/blob/main/sygil-diffusion-v0.2.ckpt): Resumed from Sygil Diffusion v0.1 and trained for a total of 1.77 million steps.
|
| 87 |
+
|
| 88 |
+
- #### Beta:
|
| 89 |
+
- [sygil-diffusion-v0.3_1860778_lora.ckpt](https://huggingface.co/Sygil/Sygil-Diffusion/blob/main/sygil-diffusion-v0.3_1860778_lora.ckpt): Resumed from Sygil Diffusion v0.2 and trained for a total of 1.86 million steps so far.
|
| 90 |
+
|
| 91 |
+
Note: Checkpoints under the Beta section are updated daily or at least 3-4 times a week. This is usually the equivalent of 1-2 training session,
|
| 92 |
+
this is done until they are stable enough to be moved into a proper release, usually every 1 or 2 weeks.
|
| 93 |
+
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
|
| 94 |
+
is uploaded to keep the repo clean. The HuggingFace inference API as well as the diffusers library will always use the latest beta checkpoint in the diffusers format.
|
| 95 |
+
For special cases we might make additional repositories to keep a copy of the diffusers model like when a model uses a different Stable Diffusion model as base (eg. Stable Diffusion 1.5 vs 2.1).
|
| 96 |
+
|
| 97 |
## Training
|
| 98 |
|
| 99 |
**Training Data**:
|