Use Continuum refine context for per-clip upscale
tests / test (push) Canceled after 0s
tests / windows-storage (push) Canceled after 0s

This commit is contained in:
2026-10-14 14:45:40 +00:00
parent 92f6ab860d
commit 2a804f7194
3 changed files with 58 additions and 21 deletions
+8 -2
View File
@@ -3,14 +3,20 @@
## Dumas per-clip tiled latent upscale
This fork adds **H3 Continuum Tiled Latent Upscale (Per Clip)**. Connect the
`video_latents` list from a Continuum sampler, the same model/conditioning,
and the native `MMH3 Latent Upscale` and `MMH3 Spatial Split Params` nodes.
`video_latents`, `assembly_plan`, and `refine_context` outputs from the
Continuum sampler, plus its `model` and `CLIP`, and connect the native
`MMH3 Latent Upscale` and `MMH3 Spatial Split Params` nodes.
Each physical clip is sent through `MMH3UltimateUpscale` independently, with
its own upscale sampler, scheduler, steps, denoise, CFG and seed controls.
The result remains a LATENT list, so clips do not get concatenated into one
larger VRAM allocation before the tiled pass. Temporal length is validated and
cannot silently change.
The node consumes `refine_context` directly and internally performs the same
context-to-conditioning adaptation as **H3 Continuum Conditioning Bridge V3.5**.
The separate `conditioning` input is optional for advanced legacy graphs; it is
not needed in the normal Continuum wiring.
The node is an adapter around ComfyUI's native MiniMax H3 tiled-upscale
implementation; it does not include model weights or vendor the upstream
implementation. Install this repository as a normal custom-node folder and