ComfyUI Extension: comfyui-scalar-mask-blend
Run ComfyUI workflows without the setup
No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.
A lightweight ComfyUI custom node for blending two image batches using a per-frame scalar mask without requiring full resolution mask upscaling.
README
ComfyUI Scalar Mask Blend
A lightweight ComfyUI custom node for blending two image batches using a per-frame scalar mask.
This node is useful when you have a 1x1 mask per frame and do not want to upscale it to full resolution, which can consume a large amount of VRAM.
Node
ScalarMaskBlend
Inputs:
| Input | Type | Description |
|---|---|---|
| a | IMAGE | First image batch, usually LatentSync output |
| b | IMAGE | Second image batch, usually original video frames |
| mask | MASK | Per-frame mask. Can be 1x1 or any size. The node uses the mean value of each frame as scalar weight |
Output:
| Output | Type | Description |
|---|---|---|
| IMAGE | IMAGE | Blended image batch |
Blend formula:
output = a * (1 - w) + b * w
Run ComfyUI workflows without the setup
No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.