Enhancing Perceptual Quality in Video Super-Resolution through Temporally-Consistent Detail Synthesis using Diffusion Models
Paper • 2311.15908 • Published
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("claudiom4sir/StableVSR", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]StableVSR Model Card
This model card focuses on the models associated with StableVSR, available here.
Model Details
- Developed by: Claudio Rota
- Model type: Diffusion-based video super-resolution model
- Model Description: This is the model used in this paper.
- Resources for more information: GitHub.
- Cite:
@inproceedings{rota2024enhancing,
title={Enhancing perceptual quality in video super-resolution through temporally-consistent detail synthesis using diffusion models},
author={Rota, Claudio and Buzzelli, Marco and van de Weijer, Joost},
booktitle={European Conference on Computer Vision},
pages={36--53},
year={2024},
organization={Springer}
}
- Downloads last month
- 448
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for claudiom4sir/StableVSR
Base model
stabilityai/stable-diffusion-x4-upscaler