ryankiros/neural-storyteller
A recurrent neural network that generates novel-style stories describing input images by combining skip-thought vectors, visual-semantic embeddings, and style shifting.
Not currently ranked — collecting fresh signals.
star history
The system takes an image as input and generates a coherent short story by combining image-sentence embeddings with a conditional neural language model. It leverages skip-thought vectors for semantic text understanding and applies a style-shifting operation inspired by neural style transfer to convert standard image captions into the style of novel narratives. The model was trained on Microsoft COCO captions without additional story-image paired data.
Frequently asked
- What is ryankiros/neural-storyteller?
- A recurrent neural network that generates novel-style stories describing input images by combining skip-thought vectors, visual-semantic embeddings, and style shifting.
- Is neural-storyteller open source?
- Yes — ryankiros/neural-storyteller is an open-source project tracked on heatdrop.
- What language is neural-storyteller written in?
- ryankiros/neural-storyteller is primarily written in Python.
- How popular is neural-storyteller?
- ryankiros/neural-storyteller has 3k stars on GitHub.
- Where can I find neural-storyteller?
- ryankiros/neural-storyteller is on GitHub at https://github.com/ryankiros/neural-storyteller.