DreamCube: 3D Panorama Generation via Multi-plane Synchronization
Paper • 2506.17206 • Published • 23
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("KevinHuang/DreamCube", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]DreamCube Pipeline. Project page: https://yukun-huang.github.io/DreamCube/
The current model weights are only used for sanity testing. Official model weights will be released soon.
- Downloads last month
- 160
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 7 Ask for provider support
Model tree for KevinHuang/DreamCube
Base model
stabilityai/stable-diffusion-2