Update README.md

README.md

@@ -9,7 +9,7 @@ license: creativeml-openrail-m
 ![sample1](https://huggingface.co/joachimsallstrom/Glitch-Embedding/resolve/main/sample1.jpg)
 Glitch generates both painted and photorealistic styles, where subjects and objects become more or less part of the VHS like glitch. 
 
-It works great with tv and film references
+It works great with tv and film references,
 ![sample2](https://huggingface.co/joachimsallstrom/Glitch-Embedding/resolve/main/sample2.jpg)
 
 and in an artsy, stylised sense to set a mood.
@@ -27,6 +27,16 @@ To get great results a very basic negative prompting is suggested:
 
 This negative prompt is used throughout images shown in this presentation, which is a shorter, edited version of Stability AI’s recommendation for SD 2.x.
 
+### Example prompts and settings
+
+<i>Left image:</i><br>
+**a profile photo of a woman and a city, photo by dblx**<br>
+_Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 1965858791, Size: 1088x768, Model hash: 4bdfc29c_
+
+<i>Right image:</i><br>
+**woman photo closeup soap bubbles, photo by dblx**<br>
+Negative prompt: **deformed, ugly**<br>
+_Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 3612934306, Size: 1152x768, Model hash: 4bdfc29c_
 
 VISA GIF-VIDEO.