ZeroCool94
commited on
Commit
•
58ea16c
1
Parent(s):
38f3abf
Update README.md
Browse files
README.md
CHANGED
@@ -65,6 +65,8 @@ image.save("astronaut_rides_horse.png")
|
|
65 |
- Despite not being a dependency, we highly recommend you to install [xformers](https://github.com/facebookresearch/xformers) for memory efficient attention (better performance)
|
66 |
- 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).
|
67 |
|
|
|
|
|
68 |
|
69 |
## Training
|
70 |
|
@@ -79,7 +81,7 @@ The model was trained on the following dataset:
|
|
79 |
- **Gradient Accumulations**: 1
|
80 |
- **Batch:** 1
|
81 |
- **Learning rate:** warmup to 1e-7 for 10,000 steps and then kept constant
|
82 |
-
- **Total Training Steps:** 800,
|
83 |
|
84 |
Developed by: [Sygil-Dev](https://github.com/Sygil-Dev/)
|
85 |
|
|
|
65 |
- Despite not being a dependency, we highly recommend you to install [xformers](https://github.com/facebookresearch/xformers) for memory efficient attention (better performance)
|
66 |
- 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).
|
67 |
|
68 |
+
## Available Checkpoints:
|
69 |
+
- [Sygil Diffusion v0.1](https://huggingface.co/Sygil/Sygil-Diffusion/blob/main/sygil-diffusion-v0.1.ckpt): Trained for 800,000 steps
|
70 |
|
71 |
## Training
|
72 |
|
|
|
81 |
- **Gradient Accumulations**: 1
|
82 |
- **Batch:** 1
|
83 |
- **Learning rate:** warmup to 1e-7 for 10,000 steps and then kept constant
|
84 |
+
- **Total Training Steps:** 800,000
|
85 |
|
86 |
Developed by: [Sygil-Dev](https://github.com/Sygil-Dev/)
|
87 |
|