Text-to-Image
stable-diffusion
ProGamerGov commited on
Commit
4352068
1 Parent(s): de3585c

Add inspiration to ReadMe

Browse files
Files changed (1) hide show
  1. README.md +4 -1
README.md CHANGED
@@ -9,7 +9,7 @@ datasets:
9
 
10
  **Object-Taped-To-Wall-Diffusion**
11
 
12
- This fine-tuned Stable Diffusion v1.5 model was trained for 2000 iterations with a batch size of 4, on a selection of photos of things taped to wall. 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 2100 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" with 50 DPM++ 2S a Karras steps and a CFG of 7, using the MSE VAE. A negative prompt of "text" was also used for this dataset.
13
 
14
  Use the tokens **ttw 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.
15
 
@@ -28,3 +28,6 @@ Example images were generated with the v1 2000 iteration model using DPM++ 2S a
28
  ```
29
  ttw style, <object> taped to wall
30
  ```
 
 
 
9
 
10
  **Object-Taped-To-Wall-Diffusion**
11
 
12
+ This fine-tuned Stable Diffusion v1.5 model was trained for 2000 iterations with a batch size of 4, on a selection of photos of things taped to a wall. 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 2100 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" with 50 DPM++ 2S a Karras steps and a CFG of 7, using the MSE VAE. A negative prompt of "text" was also used for this dataset.
13
 
14
  Use the tokens **ttw 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.
15
 
28
  ```
29
  ttw style, <object> taped to wall
30
  ```
31
+
32
+
33
+ This model was inspired by the 2019 art piece [*Comedian* by Italian artist Maurizio Cattelan](https://en.wikipedia.org/wiki/Comedian_(artwork\)), where a banana was duct taped to a wall.