Make per-clip H3 upscale a Second Pass replacement
This commit is contained in:
@@ -72,14 +72,16 @@ implementation.
|
||||
|
||||
### DUMAS H3 Continuum Tiled Latent Upscale (Per Clip)
|
||||
|
||||
`DumasH3ContinuumTiledLatentUpscalePerClip` applies the native H3 tiled
|
||||
upscale independently to each physical Continuum clip. It accepts the
|
||||
Continuum `refine_context` and uses the upstream refine bridge when no direct
|
||||
conditioning is connected. Its sampler, scheduler, sigma input, steps,
|
||||
denoise, CFG, and noise seed are separate from the base generation pass.
|
||||
Connected sockets take precedence over node defaults. The node preserves one
|
||||
LATENT list item per physical clip to avoid concatenating a long sequence
|
||||
into one oversized VRAM allocation.
|
||||
`DumasH3ContinuumTiledLatentUpscalePerClip` is a replacement for the upstream
|
||||
Second Pass when tiled latent upscale is required. It applies the native H3
|
||||
tiled upscale independently to each physical Continuum clip, passes the
|
||||
first-pass audio latents through unchanged, and returns the updated assembly
|
||||
plan plus status. It accepts the Continuum `refine_context` and uses the
|
||||
upstream refine bridge when no direct conditioning is connected. Its sampler,
|
||||
scheduler, sigma input, steps, denoise, CFG, and noise seed are separate from
|
||||
the base generation pass. Connected sockets take precedence over node
|
||||
defaults. The node preserves one LATENT list item per physical clip to avoid
|
||||
concatenating a long sequence into one oversized VRAM allocation.
|
||||
|
||||
The CSGlide `Render Project` control is the generation orchestrator: it renders
|
||||
clips sequentially, adopts each completed render, extracts the previous clip's
|
||||
|
||||
Reference in New Issue
Block a user