import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("KlingTeam/RoboMaster", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]RoboMaster
It synthesizes realistic robotic manipulation video given an initial frame, a prompt, a user-defined object mask, and a collaborative trajectory describing the motion of both robotic arm and manipulated object in decomposed interaction phases. It supports diverse manipulation skills and can generalize to in-the-wild scenarios.
Usage
This is the implementation based on CogVideoX-5B. Please refer to our github for details on usage.
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support