LIBERO Causal Wan 2.2 5BTI2V

--- license: other base_model: - Wan-AI/Wan2.2-TI2V-5B tags: - video-generation - robotics - libero - causal-video-modeling - wan2.2 - ti2v library_name: pytorch pipeline_tag: text-to-video --- # LIBERO-Causal-Wan2.2-5BTI2V This repository contains a Causal-Forcing / AR diffusion checkpoint for LIBERO robot video generation, adapted from Wan2.2-TI2V-5B. The checkpoint was trained with the LightEWM LIBERO-Causal example on LIBERO videos with dense prompts. ## Checkpoint - File: `model.pt` - Training step: `145000` - Base model family: Wan2.2-TI2V-5B - Backend: Causal-Forcing AR diffusion - Dataset adapter: `lightewm.dataset.causal_forcing.CausalForcingJsonlAdapter` - Training data metadata: `data/libero_i2v_train/metadata_dense_prompt.csv` ## Training Setup The training configuration follows `examples/LIBERO-Causal/train.yaml` in LightEWM: - Official backend config: `configs/ar_diffusion_tf_framewise_wan22_ti2v_5b_maze.yaml` - Resolution: `224 x 224` - Video length: `49` RGB frames - FPS: `10` - Inference latent frames / output frames: `13` - `variable_num_frames_train`: `false` - `max_training_video_frames`: `49` - `model_kwargs.timestep_shift`: `5.0` - `model_kwargs.seq_len`: `1029` - Distributed training: `8` processes The LIBERO preprocessing pipeline resamples LIBERO demonstrations to 10 FPS and uses dense prompts generated for the converted metadata. ## Usage Place `model.pt` under a local checkpoints directory and point the LightEWM LIBERO-Causal inference config at it: ```yaml runner: params: checkpoint_path: checkpoints/LIBERO-Causal-Wan2.2-5BTI2V/model.pt ``` Then run: ```bash python run.py --config examples/LIBERO-Causal/infer.yaml ``` The default LIBERO-Causal inference example uses: - `224 x 224` - `49` RGB frames - `num_output_frames: 13` - dense prompt metadata at `data/libero_i2v_train/metadata_dense_prompt.csv` ## Intended Use This checkpoint is intended for research on robot video prediction/generation and LIBERO-style manipulation trajectories. It is not intended for deployment in safety-critical robotic control systems without additional validation. ## Limitations - The model is specialized to the LIBERO data distribution and may not generalize to unrelated robot embodiments, scenes, or camera viewpoints. - Outputs are generated videos, not verified executable robot policies. - Performance depends on using matching...

Source context: 0 downloads · 3 likes · Pipeline text-to-video · Library pytorch · Repo XuWuLingYu/LIBERO-Causal-Wan2.2-5BTI2V