This doesn't work because you rely on LTXV separate and join nodes, and those are NOT compatible with H3. Any "upscale' you performed is pure luck
#16
by niko20 - opened
bah
Those nodes just have silly names and work well with H3.
This is the documentation for that node.
"Merge a video latent and an audio latent into a joint AV latent (any AV model, e.g. LTXV or MiniMax H3)."
I'm having a hard time understanding the point of your comment, other than to act like a total hater who doesn't really seem to understand how this upscaler works.
