Ethanfel/Comfyui-STAR
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add segment-based processing for long videos to reduce RAM usage

Browse Source 
Process videos in overlapping segments (25% overlap with linear crossfade
blending) so peak memory is bounded by one segment rather than the full
video. New segment_size parameter on the Super-Resolution node (default 0
= all at once, recommended 16-32 for long videos). Also update README
clone URL to GitHub mirror.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Ethanfel
2026-02-14 23:28:01 +01:00
parent 5f9287cfac
commit f7021e95f4
3 changed files with 122 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
README.md
View File

@@ -21,7 +21,7 @@ Search for `ComfyUI-STAR` in ComfyUI Manager and install.
```bash
cd ComfyUI/custom_nodes
git clone --recursive git@192.168.1.1:Ethanfel/Comfyui-STAR.git
git clone --recursive https://github.com/ethanfel/Comfyui-STAR.git
cd Comfyui-STAR
pip install -r requirements.txt
```
@@ -56,6 +56,7 @@ Runs the STAR diffusion pipeline on an image batch.
| **max_chunk_len** | Max frames per chunk (4–128, default 32). Lower = less VRAM for long videos. |
| **seed** | Random seed for reproducibility. |
| **color_fix** | `adain` (match color stats), `wavelet` (preserve low-frequency color), or `none`. |
| **segment_size** | Process video in segments of this many frames to reduce RAM usage (0–256, default 0). 0 = process all at once. Recommended: 16–32 for long videos. Segments overlap by 25% with linear crossfade blending. |
## VRAM Requirements