Application Changelog

Latest updates and features for StoryLLM.

Windows Setup & Launch Script Updates

v1.0.2

Released on April 12, 2025

We have updated the setup and launch scripts specifically for Windows users to provide a smoother installation and running experience.

  • setup_windows.bat: Improved detection of Conda installations and added more robust error checking during dependency installation.
  • launch_storyllm.bat: Corrected an issue where the storyllm_env environment might not activate automatically in some specific PowerShell or Command Prompt configurations.

Recommendation: If you installed StoryLLM on Windows before April 12, 2025, we recommend downloading the latest project files from your user dashboard (User Dashboard -> Active License -> Download Button). This will ensure you have the improved scripts.

Users on Linux are not affected by this specific script update.

Minor Bug Fixes and Stability Improvements

v1.0.1

Released on April 10, 2025

This quick update addresses a few minor issues reported since our launch:

  • Fixed: Resolved an issue where the segment editor occasionally failed to load preview images for very long story videos.
  • Improved: Enhanced stability during the final video export process, reducing potential errors.
  • UI: Minor adjustments to button placements in the generator tabs for better consistency.

Thank you for your feedback! We continue to work on improving StoryLLM.

Initial Release of StoryLLM!

v1.0.0

Released on April 09, 2025

We are thrilled to announce the initial public release of StoryLLM! 🎉

This version brings you the power of local AI content creation, allowing you to generate unlimited videos and images right on your own computer.

Key features in this release include:

  • Story Generator: Turn your scripts into dynamic videos with AI-generated visuals and voiceovers.
  • Slide Generator: Create engaging slideshows with consistent timing and visuals.
  • Image Generator: Produce standalone AI images from text prompts.
  • Local AI Core: Utilizes Stable Diffusion for images and Kokoro TTS for free local voice generation.
  • Privacy Focused: Your content stays on your machine when using local models.
  • Optional integrations with cloud APIs (OpenAI, Gemini, ElevenLabs).
  • Advanced YouTube uploader with multi-language metadata support.

We are excited for you to explore the possibilities! Download the project files from your dashboard and start creating.