Update README.md

README.md

@@ -42,13 +42,40 @@ It achieves the following results on the evaluation set:
 
 ## example
 
-![prompt](https://i.imgur.com/DKHoLtB.png)
 
 Results in (_DALL-E, but you get the idea_):
 
-![sentient cheese astronaut](https://i.ibb.co/zrCf4BK/DALL-E-2022-11-09-12-17-40-sentient-cheese-robot-astronaut-highly-detailed-concept-art-eric-zener-el.png)
+![example](https://i.ibb.co/WkmTnZD/image.png)
 
-this `distilgpt2` version is probably small/fast enough to be used locally on CPU!
+
+
+- this `distilgpt2` version is probably small/fast enough to be used locally on CPU!
+
+## basic usage
+
+install transformers as needed:
+
+```bash
+pip install -U transformers
+```
+
+load and query through a `pipeline` object:
+
+```python
+from transformers import pipeline
+
+model_tag = "pszemraj/distilgpt2-magicprompt-SD"
+generator = pipeline(
+    "text-generation",
+    model=model_tag,
+)
+
+prompt = "The Answer to Why"
+result = generator(
+    prompt,
+)  # generate
+print(result[0]["generated_text"])
+```
 
 ## Training and evaluation data