HumanDreamer: Generating Controllable Human-Motion Videos via Decoupled Generation
Paper • 2503.24026 • Published
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("chuanshuogushi/HumanDreamer", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0][CVPR2025]HumanDreamer: Generating Controllable Human-Motion Videos via Decoupled Generation
Usage on gitHub: https://github.com/GigaAI-research/HumanDreamer
Our MotionVid Dataset: MotionVid
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support