Skip to content

LTXvideo text-to-video and image-to-video as a Space in Forge2

Notifications You must be signed in to change notification settings

DenOfEquity/forge_space_LTXvideo

Repository files navigation

Forge2 Spaces implementation of LTX-video

New Forge only.

uses diffusers

will download ~10.8GB models

Note

Install via Extensions tab; Install from URL sub-tab; use URL of this repo.

Requirements: diffusers>=0.32.0

imageio-ffmpeg

Tip

noUnload toggle keeps models in memory

lowVRAM one-way switch enables sequential model offloading - much lower VRAM usage, but slower: usually better than hitting shared memory.

Important

Size / frames you can generate is dependent on available VRAM. Start low. Most likely fail point is VAE, after inference.

Results saved to standard Outputs folder. Filename is LTXvideo_datetime.mp4.

Note

Also saves a text file with same name (LTXvideo_datetime.txt), containing generation parameters.

example.mp4

About

LTXvideo text-to-video and image-to-video as a Space in Forge2

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages