license: other
library_name: pytorch
pipeline_tag: image-to-video
tags:
- longlive-2.0
- robotics
- autoregressive
LongLive 2.0 Robot-L
Autoregressive robot-video generation weights. L continues from Robot-M with long-sequence training; this is the final Stage-L checkpoint at step 3,972. S, M and L describe training sequence length, not model size.
Download
hf download Efficient-Large-Model/LongLive2.0-Robot-L --local-dir ./weights/LongLive2.0-Robot-L
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. This release contains the online generator only (825 FP32 tensors, 4,999,787,712 parameters). Optimizer, EMA and other training states are not included.
All 20 Stage-L fixed-video validation gates were accepted; the final panel contains 24 videos evaluated with 50 sampling steps, CFG 3.0 and base seed 20260711. These checks are release validation, not a robot-control safety or benchmark claim. See the Long-WAM Stage 1 guide for the matching runtime and inference instructions.
Original upstream model terms continue to apply.