LongLive 2.0 Robot-M

Autoregressive robot-video generation weights. M is trained on a mixture of short and medium-length sequences. S and M describe training sequence length, not model size.

Download

hf download Efficient-Large-Model/LongLive2.0-Robot-M --local-dir ./weights/LongLive2.0-Robot-M

Inference

Instantiate the matching LongLive 2.0 generator, then load the FP32 weights:

import torch

state_dict = torch.load("model.pt", map_location="cpu", mmap=True, weights_only=True)
model.load_state_dict(state_dict, strict=True)

Run the loading example from the downloaded directory. The matching inference runtime, VAE and text encoder are required separately; this is not a standalone pipeline. Optimizer and other training states are not included.

Original upstream model terms continue to apply.