FramePack
Open-source image-to-video generator that runs long clips on a 6 GB GPU.
About FramePack
FramePack is an open-source image-to-video tool from lllyasviel, the developer behind ControlNet. You upload a still image, write a prompt, and it builds the clip section by section using a 13B video diffusion model, with previews appearing as it goes. Because it compresses earlier frames to a fixed-size context, memory use stays flat as the video gets longer: 6 GB of GPU memory is enough for a 60-second, 30 fps clip. It needs an Nvidia RTX 30, 40 or 50 series card on Windows or Linux. On an RTX 4090 it runs at about 1.5 to 2.5 seconds per frame, and laptop GPUs are roughly 4 to 8 times slower. Windows gets a one-click package; the model files (over 30 GB) download on first run. The author says the GitHub repo is the only official source and sites like framepack.co are not affiliated.
Key Features
💰 Pricing
Free and open source (Apache-2.0). Runs locally on your own Nvidia GPU.
Frequently Asked Questions
Is FramePack free?
What is FramePack used for?
What platforms does FramePack work on?
What are the best alternatives to FramePack?
Reviews
Loading reviews...
Questions & Answers
Questions submitted will appear here soon
Join the community to share knowledge about FramePack
📊 Comparison vs Alternatives
| Feature | ||||
|---|---|---|---|---|
| Pricing | Free | Paid | Freemium | Paid |
| Rating | — | — | ⭐ 4.3 | ⭐ 4.7 |
| Free Tier | ✅ | ❌ | ✅ | ❌ |
| Popularity | 50% | 85% | 82% | 82% |
Are you the creator of FramePack?
Claim this listing to get a verified badge, edit tool details, and respond to reviews. You’ll sign in and confirm a work email so we can verify ownership.
Claim this listingQuick Stats
Categories
FramePack Alternatives
The Weekly AI Tools & Skills Digest
Launching soon: trending agent skills, new tools, and what's actually worth trying. Sign up to get the first issue.
Free forever. Unsubscribe anytime.