Two-node package wrapping the STAR (ICCV 2025) diffusion-based video upscaling pipeline: - STAR Model Loader: loads UNet+ControlNet, OpenCLIP text encoder, and temporal VAE with auto-download from HuggingFace - STAR Video Super-Resolution: runs the full diffusion pipeline with configurable upscale factor, guidance, solver mode, chunking, and color correction Includes three VRAM offload modes (disabled/model/aggressive) to support GPUs from 12GB to 40GB+. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
7 lines
75 B
Plaintext
7 lines
75 B
Plaintext
easydict
|
|
einops
|
|
open-clip-torch
|
|
torchsde
|
|
diffusers>=0.25.0
|
|
huggingface_hub
|