Purge VRAM between sequential H3 clips
This commit is contained in:
@@ -13,6 +13,14 @@ The workflow is preserved in `workflow-source.json`; `workflow.json` is the trac
|
||||
|
||||
For the visual ComfyUI editor, load [`workflow-ui.json`](workflow-ui.json). It is the canvas-format version of the same validated baseline, with node positions and links. The API-format `workflow.json` remains the file used by the automated submission scripts.
|
||||
|
||||
After `CSGlideVideoCS` saves each clip, the workflow now passes its filepath
|
||||
through `LayerUtility: PurgeVRAM V2` with both cache and model purging enabled.
|
||||
This is a cleanup boundary between sequential clips: it does not alter the
|
||||
filepath, frames or audio, but asks ComfyUI to release cached models and CUDA
|
||||
memory before the next clip starts. It is intended to reduce retained VRAM
|
||||
pressure; it cannot prevent an individual clip from exceeding the card's
|
||||
capacity.
|
||||
|
||||
## Fixed test input
|
||||
|
||||
- **References:** `references/Scene022.png` as `@image1`, `references/Char034_TurnaroundFull_001.png` as `@image2`
|
||||
|
||||
Reference in New Issue
Block a user