CPU3DAI tools for 3D, video and audio

EdenLive: video generator — what it does and what you need to run it

EdenLive is an open-source video generator from VAST that turns an image into a video sequence. The authors describe it as a real-time generative rendering tool for interactive worlds, driven by any visual reference.

What it does

The tool handles image-to-video: an image goes in, a video comes out. As described by the author, EdenLive is aimed at real-time generative rendering for interactive worlds. In the repository the project is tagged game, renderer and video-generation, which points to game and rendering scenarios.

The code is written in Python and built on the diffusers library. The model is published on Hugging Face, the code repository is on GitHub. The last code change is dated October 21, 2026; the repository was created on October 12, 2026.

What you need to run it

The platform, as described by the author, is CUDA. The description states verbatim: Linux x86-64, NVIDIA GPUs with 80 GB (CUDA 13 driver). That is, it requires a Linux x86-64 system and an NVIDIA GPU with 80 GB of memory and a CUDA 13 driver.

The largest model weights file is 61.2 GB; all model weights files together are 209.3 GB. That is a substantial volume to factor in when planning disk space.

The code is distributed under the Apache-2.0 license. The model weights are also released under the Apache License 2.0. The terms of the weights license permit use, modification and distribution of the work, including for commercial purposes. When distributing, you must include a copy of the license, state changes in modified files and retain attribution notices. The licensor's trademarks may not be used.

Who it suits

EdenLive is intended for those working with image-to-video generation who have access to powerful hardware: a Linux machine with an 80 GB NVIDIA GPU. The project will interest developers who want to embed generative rendering into their systems, since the code is open and the license allows commercial use and modification.

The tool is not suitable for those without an 80 GB GPU or who work on other operating systems. The 209.3 GB of model weights may also be a limitation for users with limited disk space.

EdenLive is an open tool for image-to-video generation aimed at real-time scenarios. Its practical applicability depends directly on having compatible hardware and sufficient storage.

EdenLive — video generation pipeline Real-time generative rendering for interactive worlds Input Visual reference image or frame Preparation Processing of reference diffusers Python Model EdenLive image-to-video CUDA Linux x86-64 Result Video in real time interactive Specs Developer: VAST License: Apache-2.0 Open source Weights: 209.3 GB Max file: 61.2 GB Platform: CUDA Language: Python Library: diffusers Tags: game, renderer
How the EdenLive pipeline works. The diagram is drawn from the tool’s fact sheet.

Fact sheet

Taskimage-to-video source
Code licenseApache-2.0 source
Weights licenseApache License 2.0: permissive license source
PlatformCUDA per the author’s description source
Largest weights file61.2 GB source
All weights files209.3 GB source
Librarydiffusers source
LanguagePython source
Last code change2026-10-21 source
Repository created2026-10-12 source
Changes often — as of 2026-10-22
GitHub stars311 source
Forks13 source
Downloads per month222 source
Model updated2026-10-20 source

Values are collected automatically from official sources and were checked on 2026-10-22. Each one links to its source, and values taken from the developer’s pages also carry a verbatim quote — hover over the note. Pricing and versions are shown as of the check date and change most often; verify on the vendor’s site before buying.

See also