added example code

README.md

@@ -5,6 +5,35 @@ pipeline_tag: text-generation
 
 A model based upon the prompts of all the images in my InvokeAI's output directory. Mostly only positive prompts, though you may catch some words in [] brackets.
 
-I'll post some example code for how to use this model in the future.
+Note: the prompts are very chaotic; a good way to stress test a model, perhaps?
 
-Note: the prompts are very chaotic; a good way to stress test a model, perhaps?
+
+To use this model, you can import it as a pipeline like so:
+```py
+from transformers import pipeline
+
+generator = pipeline(model="cactusfriend/nightmare-invokeai-prompts",
+                    tokenizer="cactusfriend/nightmare-invokeai-prompts",
+                    task="text-generation")
+```
+
+Here's an example function that'll generate by default 20 prompts, at a temperature of 1.8 which seems good for this model.
+```py
+def makePrompts(prompt: str, *, p: float=0.9,
+                k: int = 40, num: int = 20,
+                temp: float = 1.8, mnt: int = 150):
+    outputs = generator(prompt, max_new_tokens=mnt,
+                        temperature=temp, do_sample=True,
+                        top_p=p, top_k=k, num_return_sequences=num)
+    items = set([i['generated_text'] for i in outputs])
+    print("-" * 60)
+    print("\n".join(items))
+    print("-" * 60)
+```
+
+Then, you can call it like so:
+```py
+makePrompts("a photograph of")
+# or, to change some defaults:
+makePrompts("spaghetti all over", temp=1.4, p=0.92, k=45)
+```