#7474th of 75 in Image and videoFor image, video and design, video and animation
videocrafter
Text-to-video and image-to-video diffusion models with inference scripts
- Stars
- 5.1k
- License
- custom license
- Last commit
- Jan 2026
- Last release
- Jan 2024
- Language
- Python
5,013 on 22 Apr 20265,113 on 11 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
VideoCrafter is a research toolbox of video diffusion models built on Stable Diffusion code. It provides VideoCrafter2 and VideoCrafter1 text-to-video checkpoints (320x512, 576x1024) and image-to-video checkpoints (320x512, 640x1024), with shell inference scripts and a local Gradio app. Use is restricted to personal, research and non-commercial purposes.
Who it is for: Researchers and hobbyists experimenting with open video diffusion models
Strengths
- Ships both text-to-video and image-to-video checkpoints on Hugging Face
- Includes a local Gradio app via python gradio_app.py
- Tech reports on arXiv for VideoCrafter1 and VideoCrafter2
- Plain scripts (run_text2video.sh, run_image2video.sh) for inference
Weaknesses
- Non-commercial research-only disclaimer; license is not a standard open-source one
- Last release January 2024; newer I2V work moved to DynamiCrafter
- VideoCrafter2 checkpoint is only 320x512
- Manual checkpoint download and placement; Python 3.8.5 conda environment, no Docker
What it needs
- Needs conda, Hugging Face checkpoints
- Models: VideoCrafter2 T2V 320x512, VideoCrafter1 T2V 576x1024, VideoCrafter1 T2V 320x512, VideoCrafter1 I2V 640x1024, VideoCrafter1 I2V 320x512
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 |