README.md

---
license: openrail
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.

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)
```