Skip to content
Node packListedExternal
Open source

ComfyUI-HunyuanImageLatentToVideoLatent

A ComfyUI node which copies a given latent's samples tensor along the time axis ((length - 1) // 4) + 1 times to form a longer latent and then prepares a noisemask tensor of the same shape such that the value of the...

Sourcegithub.com/philiprodriguez/ComfyUI-HunyuanImageLatentToVideoLatent
Maintainer@philiprodriguezBgrade

Package profile

Status
Listed
Publisher
@philiprodriguez
Source
GitHub
Stars
1

README

A ComfyUI node which copies a given latent's samples tensor along the time axis ((length - 1) // 4) + 1 times to form a longer latent and then prepares a noise_mask tensor of the same shape such that the value of the mask for a given time step is given by the function at https://www.desmos.com/calculator/vhw74mr1vh.

Nodes in this pack

1 node
  • HunyuanImageLatentToVideoLatent

Sources

1 source
GitHubPrimary
github.com/philiprodriguez/ComfyUI-HunyuanImageLatentToVideoLatent

Verified Oct 9

Source excerpts

1 excerpt
NoteJul 16github.com/philiprodriguez/ComfyUI-HunyuanImageLatentToVideoLatent

Source context: Repo philiprodriguez/ComfyUI-HunyuanImageLatentToVideoLatent