import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("XuejiFang/LeWAM", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]LeWAM
LeWAM predicts 32 robot actions per inference call using 10 denoising steps by default. This repository contains the LeWAM predictor, the frozen I-JEPA-Huge vision encoder, the scheduler, and RoboTwin action statistics.
Download all weights together:
hf download XuejiFang/LeWAM --local-dir outputs/lewam
Use the LeWAM inference code for RoboTwin evaluation. The bundled I-JEPA-Huge encoder is licensed under CC BY-NC 4.0.
- Downloads last month
- 19
Model tree for XuejiFang/LeWAM
Base model
facebook/ijepa_vith14_22k