Envision3D: One Image to 3D with Anchor Views Interpolation
Paper • 2403.08902 • Published • 2
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("pytttttt/Envision3D", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Envision3D: One Image to 3D with Anchor Views Interpolation
Model Details
S1 model fine-tuned from Stable Diffusion Image Variants.
S2 model fine-tuned from Stable Video Diffusion.
- Repository: [https://github.com/PKU-YuanGroup/Envision3D]
- Paper: [https://arxiv.org/abs/2403.08902]
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support