Spaces:
Sleeping
Sleeping
A newer version of the Gradio SDK is available: 6.12.0
metadata
title: Story_Poem
emoji: π
colorFrom: blue
colorTo: pink
sdk: gradio
sdk_version: 5.25.2
app_file: app.py
pinned: false
π AI Story & Poem Generator
A creative multimodal app that turns images into imaginative stories or poems, with optional themes and characters. The output is generated using AI and also converted to English audio using text-to-speech.
π Features
- πΌοΈ Accepts any image as a creative prompt
- π§ Uses a vision-language model to caption the image (BLIP)
- βοΈ Generates a story or poem using Falcon LLM
- π§ Converts the text output to English audio with
gTTS - π Downloadable
.txtand.mp3files
π How to Use
- Upload an image β choose any photo or illustration.
- Enter a theme β like βdreamsβ, βfriendshipβ, βmysteryβ.
- (Optional) Add characters β e.g., "a curious cat", "two sisters".
- Select either βPoemβ or βStoryβ.
- Hit Generate and enjoy:
- π A creative text based on the image + theme
- π English audio narration
- π Downloads for both
π§ Models Used
| Task | Model |
|---|---|
| Image Captioning | Salesforce/blip-image-captioning-base |
| Text Generation | tiiuae/falcon-rw-1b |
| Text-to-Speech | gTTS (Google |