#7373rd of 75 in Image and videoFor image, video and design, image and design, video and animation
stable-diffusion-videos
Python library that morphs between Stable Diffusion prompts to make videos
- Stars
- 4.7k
- License
- Apache-2.0
- Last commit
- Dec 2025
- Last release
- Dec 2025
- Language
- Python
4,655 on 22 Apr 20264,708 on 11 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Provides a StableDiffusionWalkPipeline that interpolates between prompt and seed pairs in latent space and renders the frames into a video. It can take an audio file so the interpolation rate follows the music, and includes an Interface class that launches a web UI. Installed with pip, with a Colab notebook and example scripts.
Who it is for: Developers making prompt-morph and music videos with Stable Diffusion in Python
Strengths
- Audio-driven interpolation lets videos move to the beat of a supplied track
- Short API: one walk() call takes prompts, seeds, fps and step counts
- Installs with pip; Colab notebook available for trying it without local setup
- Built-in Interface class launches a UI from an existing pipeline
Weaknesses
- README examples use Stable Diffusion v1-4 only; newer model families are not documented
- Real-ESRGAN upsampling is commented out because of package issues
- Apple M1 requires float32 on MPS, since float16 is unavailable
- Documentation is limited to the README and an examples folder
What it needs
- GPU optional
- Needs PyTorch
- Models: Stable Diffusion v1-4 (CompVis)
What changed
From the release notes. No flag means the note does not say so, not that the upgrade is safe.
Also in Image and video
See all 75| Rank | Project | Score |
|---|---|---|
| 1 | frigateLocal NVR with realtime object detection for IP cameras | 93 out of 100 |
| 2 | MoneyPrinterTurboGenerates short videos from a topic, with script, footage, voiceover and subtitles | 88 out of 100 |
| 3 | toonflow-appInfinite-canvas tool for AI short drama and comic video production | 87 out of 100 |
| #4 | InvokeAIWeb UI for diffusion image generation with inpainting canvas and node workflows | 86 out of 100 |
| #5 | ComfyUINode-graph editor for running diffusion image, video, audio and 3D workflows | 85 out of 100 |