ZeroCool94 commited on
Commit
58ea16c
1 Parent(s): 38f3abf

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -1
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:** 800,0000
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