morsoli
aimangastudio
Type a story idea, get laid-out manga pages with AI
- Google GenAI

StoryDiffusion holds one character steady across a long run of generated images. Give it 3 or more text prompts, and it draws them as a single comic. The project is the official code behind a NeurIPS 2024 paper. The catch: the video model's code and weights were never released.
Best for: Researchers and tinkerers testing character consistency in comics and image-to-video.
From the StoryDiffusion README on GitHub. Tap an image to see it full size.
Rewritten from the README. Check the repo for the latest steps.
conda create --name storydiffusion python=3.10conda activate storydiffusionpip install -U pip then the command belowpip install -r requirements.txtComic_Generation.ipynb and run the cells.python gradio_app_sdxl_specific_id_low_vram.pyOther storyboard projects people compare with StoryDiffusion.
morsoli
Type a story idea, get laid-out manga pages with AI
omnichar
Keeps one character file you reuse across AI image and video models
neopen
Agent skill that turns a script into shot-by-shot video prompts
NomaDamas
3D blocking and camera moves, exported as keyframe packs for AI video
Do you maintain StoryDiffusion? Add this badge to your README so English speakers can find our write-up.
[](https://openmicrodrama.com/projects/hvision-nku-storydiffusion)The badge links to this page. Want your description changed? Email support@openmicrodrama.com.
Reviewed Oct 1, 2026. Official code for a NeurIPS 2024 paper. Last push 2024-09-26, far outside our 90-day window; kept as the classic reference for keeping one character across comic panels. We write these descriptions ourselves. The repo's own docs are the final word.