story-to-image-generator

Story-to-Image Generator Configuration

Configuration and utilities for generating images from stories using Stable Diffusion.

Overview

This repository contains the configuration files and utilities needed to generate images from stories created by the phrase-to-story-generator model.

Contents

• config.json: Generation parameters and style templates
• example_usage.py: Complete implementation example
• README.md: This documentation

Usage

from diffusers import StableDiffusionPipeline
import torch
import json

# Load configuration
with open("config.json", "r") as f:
    config = json.load(f)

# Load Stable Diffusion pipeline
pipe = StableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5")

# Generate image from story
story = "In a magical forest where ancient trees whispered secrets..."
# See example_usage.py for complete implementation

Features

• Story Analysis: Automatic extraction of visual elements from text
• Style Templates: Multiple art style options (fantasy, sci-fi, adventure, nature)
• Configurable Parameters: Customizable generation settings
• Easy Integration: Works seamlessly with story generation models

Configuration

The config.json file includes:

• Generation Parameters: Steps, guidance scale, image dimensions
• Prompt Templates: Pre-designed prompts for different genres
• Visual Keywords: Keyword mappings for scene detection
• Style Categories: Automatic genre classification

Art Styles

• Fantasy: Magical, mystical, enchanted themes
• Sci-Fi: Futuristic, technological, space themes
• Adventure: Epic, heroic, dramatic themes
• Nature: Peaceful, realistic, natural themes

Integration

This configuration works best with:

• yashu16/phrase-to-story-generator
• Stable Diffusion v1.5
• Custom story analysis pipeline

Updates

• Latest: 2025-09-03 11:40:15 - Enhanced configuration
• Version: 2.0
• Features: Improved genre detection and prompt templates

---

Created by yashu16 | GitHub | Hugging Face