# ryankiros/neural-storyteller

A recurrent neural network for generating little stories about images

Repository: https://github.com/ryankiros/neural-storyteller
Canonical: https://ross.abutalabs.com/products/neural-storyteller
Language: Python
License Family: other
Last push: 2017-10-18T21:15:39+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3962, "days_push": 3241, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2958, forks 524 (observed 2026-08-28T04:07:32.252361+00:00)

## What it is
A recurrent neural network research project that generates short stories about images by combining skip-thought vectors, visual-semantic embeddings, and style shifting. It includes code for generating stories from your own images and instructions for training new models.

## Use cases
- generate a story from a photo
- caption images in a narrative style
- transfer the style of novel prose to image captions
- experiment with skip-thought vector models
- train a conditional language model on books

## When to choose
- you want to reproduce or study 2015-era neural story generation research
- you need a reference implementation of style shifting and skip-thought decoding

## When to avoid
- you need a maintained or production-ready image captioning system
- you want modern transformer-based image-to-text models
- you need a permissively licensed project (no license is provided)

## Facets
- artifact type: library
- maturity: abandoned
- function: machine-learning, deep-learning, nlp, image-processing, llm-inference
- domain: deep-learning, computer-vision, artificial-intelligence
- platform: python
- tags: image-captioning, story-generation, skip-thoughts, style-transfer, rnn, research-code, natural-language-processing, linux

## Member repositories
- ryankiros/neural-storyteller (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:32.252361+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:32:11.942761+00:00, confidence not recorded.
  - readme: https://github.com/ryankiros/neural-storyteller (fetched 2026-08-28T04:07:32.252361+00:00, sha 93193d6c9a59)
- Data as of 2026-08-30T08:39:29.467469+00:00.