StereoCrafter: Diffusion-based Generation of Long and High-fidelity Stereoscopic 3D from Monocular Videos
Paper • 2409.07447 • Published • 1
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("TencentARC/StereoCrafter", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]StereoCrafter: Diffusion-based Generation of Long and High-fidelity Stereoscopic 3D from Monocular Videos
Sijie Zhao*
Wenbo Hu*
Xiaodong Cun*
Yong Zhang†
Xiaoyu Li†
Zhe Kong
Xiangjun Gao
Muyao Niu
Ying Shan
* equal contribution † corresponding author
Tencent AI Lab ARC Lab, Tencent PCG
Introduction
We propose a novel framework to convert any 2D videos to immersive stereoscopic 3D ones that can be viewed on different display devices, like 3D Glasses, Apple Vision Pro and 3D Display. It can be applied to various video sources, such as movies, vlogs, 3D cartoons, and AIGC videos.
- Downloads last month
- 205
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support