Looking-Ahead Final Weights

This repository provides the final weights for Future Chunk Prediction (FCP) and the Teacher Forcing (TF) baseline described in the paper Looking Ahead: Modeling Future Evolution in Autoregressive Video Generation.
For more details, demonstrations, and updates, see the project page and the code repository.

Use each model with its matching configuration in the Looking-Ahead code repository.

Model	Method	Configuration	Final weights
1.3B	TF	tf_wan21_t2v_1.3b	Download
1.3B	FCP	fcp_wan21_t2v_1.3b	Download
5B	TF	tf_wan22_ti2v_5b	Download
5B	FCP	fcp_wan22_ti2v_5b	Download

Download

Run from the code repository root to download the final weights:

hf download TencentARC/Looking-Ahead --local-dir weights/Looking-Ahead

The four final weight files total approximately 63.2 GiB.

Use

After preparing the code environment and required Wan components:

uv run python inference.py \
  --config fcp_wan21_t2v_1.3b \
  --checkpoint_path weights/Looking-Ahead/fcp_wan21_t2v_1.3b/model_ema.pt \
  --use_ema \
  --image_path examples/inference/i2v/sailboat_lake.png \
  --prompt_file examples/inference/i2v/sailboat_lake.txt \
  --duration 5s --seed 42 \
  --output_path outputs/fcp_example

To use another model, change both the configuration and weight folder. Keep the filename model_ema.pt and the --use_ema flag. See the code repository for setup and further examples.

License

Apache-2.0. See NOTICE for required notices.