import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("dummy9996/SwiftVR-bf16", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]SwiftVR: Real-Time One-Step Generative Video Restoration
Original model is at https://huggingface.co/H-oliday/SwiftVR
Install:
git clone https://github.com/H-oliday/SwiftVR
cd SwiftVR
uv pip install -e .
hf auth login --token {token}
hf download dummy9996/SwiftVR-bf16 --local-dir checkpoints/
Run:
from swiftvr import SwiftVRPipeline
pipe = SwiftVRPipeline.from_pretrained("checkpoints/").to("cuda", dtype="bfloat16")
pipe.restore_video("before.mp4", "after.mp4", upscale=2)
- Downloads last month
- 21
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for dummy9996/SwiftVR-bf16
Base model
H-oliday/SwiftVR