ProGamerGov commited on
Commit
0c8ad71
1 Parent(s): d4f9725

Improve ReadMe description

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -4,7 +4,7 @@ license: creativeml-openrail-m
4
 
5
  **Min-Illust-Background-Diffusion**
6
 
7
- This fine-tuned Stable Diffusion v1.5 model was trained for 2250 iterations with a batch size of 4, on a selection of artistic works by Sin jong hun. Training was performed using [ShivamShrirao/diffusers](https://github.com/ShivamShrirao/diffusers) with full precision, prior-preservation loss, the train-text-encoder feature, and the new [1.5 MSE VAE from Stability AI](https://huggingface.co/stabilityai/sd-vae-ft-mse). A total of 4120 regularization / class images were used from [here](https://huggingface.co/datasets/ProGamerGov/StableDiffusion-v1-5-Regularization-Images). Regularization images were generated using the prompt "artwork style", 50 DDIM steps, and a CFG of 7.
8
 
9
  Use the tokens **sjh style** in your prompts for the effect. Note that the effect also appears to occur at a much weaker strength on prompts that steer the output towards specific artistic styles.
10
 
 
4
 
5
  **Min-Illust-Background-Diffusion**
6
 
7
+ This fine-tuned Stable Diffusion v1.5 model was trained for 2250 iterations with a batch size of 4, on a selection of artistic works by Sin Jong Hun. Training was performed using [ShivamShrirao/diffusers](https://github.com/ShivamShrirao/diffusers) with full precision, prior-preservation loss, the train-text-encoder feature, and the new [1.5 MSE VAE from Stability AI](https://huggingface.co/stabilityai/sd-vae-ft-mse). A total of 4120 regularization / class images were used from [here](https://huggingface.co/datasets/ProGamerGov/StableDiffusion-v1-5-Regularization-Images). Regularization images were generated using the prompt "artwork style", 50 DDIM steps, and a CFG of 7.
8
 
9
  Use the tokens **sjh style** in your prompts for the effect. Note that the effect also appears to occur at a much weaker strength on prompts that steer the output towards specific artistic styles.
10