Ethanfel
0fecfcee37
Vendor minimal diffsynth subset for FlashVSR inference (full/tiny pipelines, v1 and v1.1 checkpoints auto-downloaded from HuggingFace). Includes segment-based processing with temporal overlap and crossfade blending for bounded RAM on long videos. Nodes: Load FlashVSR Model, FlashVSR Upscale, FlashVSR Segment Upscale. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
3 lines
154 B
Python
3 lines
154 B
Python
from .flashvsr_full import FlashVSRFullPipeline
|
|
from .flashvsr_tiny import FlashVSRTinyPipeline
|
|
from .flashvsr_tiny_long import FlashVSRTinyLongPipeline |