PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers
Paper • 2506.05573 • Published • 82
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("wgsxm/PartCrafter-Scene", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers (Scene Level)
PartCrafter is a structured 3D generative model that jointly generates multiple parts and objects from a single RGB image in one shot. This HuggingFace🤗 repo stores pretrained model weights for PartCrafter on scene level.
For more details about usage, please refer to the official GitHub repo.
- Project page: https://wgsxm.github.io/projects/partcrafter/
- Code: https://github.com/wgsxm/PartCrafter
- Paper: https://arxiv.org/abs/2506.05573
- Downloads last month
- 16
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support