Model giving extremely short prompts transformers.js

I’m using transformers.js in a browser setting, trying text to text generation

my code is this

import { pipeline } from "";

      let storyTeller = await pipeline(

      async function story() {
        let result = await storyTeller("give a story on XXX", { // example
          min_new_tokens: 1000,
          temperature: 0.6,
          repetition_penalty: 5,
          no_repeat_ngram_size: 1,

        document.getElementById("output").innerHTML = result;

However this often gives me one word or a sentence at best, even if I set min_new_token to 2000 or more. Why is that?