Aller au contenu
Node packPrésentéExterne
Ouvrir la 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
Mainteneur@philiprodriguezBClasse

Profil du package

Statut
Présenté
Éditeur
@philiprodriguez
Source
GitHub
Étoiles
1

LIREMOI

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.

Nœuds dans ce pack

Nœud 1
  • HunyuanImageLatentToVideoLatent

Sources

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

Vérifié 9 oct.

Extraits de sources

1 extrait
Note16 juil.github.com/philiprodriguez/ComfyUI-HunyuanImageLatentToVideoLatent

Source context: Repo philiprodriguez/ComfyUI-HunyuanImageLatentToVideoLatent