Update README.md

README.md

@@ -6,7 +6,7 @@ tags:
 - stable-diffusion
 - text-to-image
 - diffusers
-thumbnail: "https://huggingface.co/nitrosocke/Future-Diffusion/resolve/main/images/future-diffusion-thumbnail-2.jpg"
+thumbnail: "https://huggingface.co/nitrosocke/Future-Diffusion/resolve/main/images/redshift-diffusion-768-thumbnail.jpg"
 inference: false
 ---
 
@@ -24,19 +24,20 @@ Trained on Stability.ai's  [Stable Diffusion 2.0](https://huggingface.co/stabili
 **Disclaimer: The SD 2.0 model is just a few days old at this point and we still need to figure out how it works exactly. Please view this as an early prototype and experiment with the model.**
 
 **Characters rendered with the model:**
-![Characters Samples](https://huggingface.co/nitrosocke/Future-Diffusion/resolve/main/images/redshift-diffusion-768-samples01s.png)
+![Characters Samples](https://huggingface.co/nitrosocke/Future-Diffusion/resolve/main/images/redshift-diffusion-768-samples01s.jpg)
 **Cars and Animals rendered with the model:**
-![Misc. Samples](https://huggingface.co/nitrosocke/Future-Diffusion/resolve/main/images/redshift-diffusion-768-samples02s.png)
+![Misc. Samples](https://huggingface.co/nitrosocke/Future-Diffusion/resolve/main/images/redshift-diffusion-768-samples02s.jpg)
 **Landscapes rendered with the model:**
-![Landscape 1](https://huggingface.co/nitrosocke/Future-Diffusion/resolve/main/images/redshift-diffusion-768-samples03s.png)
+![Landscape 1](https://huggingface.co/nitrosocke/Future-Diffusion/resolve/main/images/redshift-diffusion-768-samples03s.jpg)
+![Landscape 2](https://huggingface.co/nitrosocke/Future-Diffusion/resolve/main/images/redshift-diffusion-768-samples04s.jpg)
 
 #### Prompt and settings for the Characters:
-**redshift style [subject] Negative Prompt:**   
+**redshift style portrait black female cyberpunk hacker tattoos colorful short hair wearing a crop top redshift style Negative Prompt: mutated body double head bad anatomy long face long neck long body text watermark signature**   
  _Steps: 20, Sampler: Euler a, CFG scale: 7, Size: 768x1024_
 
 #### Prompt and settings for the Landscapes:
-**redshift style Negative Prompt:**   
- _Steps: 20, Sampler: Euler a, CFG scale: 7, Size: 1152x768_
+**redshift style beautiful fjord at sunrise Negative Prompt: fog blurry soft**   
+ _Steps: 20, Sampler: Euler a, CFG scale: 7, Size: 1536x768_
 
 This model was trained using the diffusers based dreambooth training by ShivamShrirao using prior-preservation loss and the _train-text-encoder_ flag in 7.500 steps.