Backbone: Wan-AI/Wan2.1-T2V-1.3B Training: static in-domain pool · 1 epoch · 30,000 steps · 640×352 · 81-frame chunks Layout: {row id}/epoch-0.safetensors Checkpoint index
Model source
Source description
Sources
1 sourceSource excerpts
3 excerptslanguage: en libraryname: diffsynth license: cc-by-4.0 pipelinetag: image-to-video tags: video-generation world-model memory action-conditioned wan
{row_id}/epoch-0.safetensorscontext_k1/epoch-0.safetensorscontext_k20/epoch-0.safetensorsspatial_mem/epoch-0.safetensorsblock_wise_ssm_two_chunk/epoch-0.safetensorsvideossm_hybrid/epoch-0.safetensorsspatial_concat_text_two_chunk/epoch-0.safetensorsspatial_inject_none_two_chunk/epoch-0.safetensorsspatial_cross_attn_readout_t32_g4_two_chunk/epoch-0.safetensorsssm_ablation_ctx1_every4_hint21/epoch-0.safetensorsssm_ablation_ctx5_every1_hint21/epoch-0.safetensorsssm_ablation_ctx5_every4_hint81/epoch-0.safetensorsepoch-0bash pip install -U "huggingface_hub[cli]" # one row huggingface-cli download Echo-Team/Echo-Memory context_k1/epoch-0.safetensors --local-dir ./ckpts # all rows huggingface-cli download Echo-Team/Echo-Memory --local-dir ./ckpts ./ckpts/spatial_mem/epoch-0.safetensorsbash export WAN_BASE_MODEL=/path/to/Wan2.1-T2V-1.3B export DATASET_BASE_PATH=data/Context-as-Memory-Dataset export PYTHONPATH=$PWD:${PYTHONPATH:-} export CKPT=./ckpts/spatial_mem/epoch-0.safetensors # in-domain replay + revisit bash eval/v2/run_static_consistency_loop_and_revisit.sh bash eval/v2/run_basic_replay_gt.sh # open-domain revisit (first frames in repo) PHASE=stage1 OOD_DIR=assets/opendomain_revisit \ bash eval/v2/revisit_suite/run_one_click_revisit_eval.sh env/memory_baseline_runtime.pybibtex @article{king2026echomemory, title={Echo-Memory: A Controlled Study of Memory in Action World Models}, author={King, Wayne and Xue, Zeyue and Bian, Yuxuan and Huang, Jie and Li, Haoran and Li, Yaowei and Su, Yaofeng and Li, Yuming and Wang, Haoyu and Zhang, Shiyi and Zhang, Songchun and Niu, Yuwei and Xu, Sihan and Zhuang, Junhao and Huang, Haoyang and Duan, Nan}, journal={arXiv preprint arXiv:2606.09803}, year={2026}, month={jun}, eprint={2606.09803}, archivePrefix={arXiv}, primaryClass={cs.CV}, url={https://arxiv.org/abs/2606.09803} } Backbone: Wan-AI/Wan2.1-T2V-1.3B Training: static in-domain pool · 1 epoch · 30,000 steps · 640×352 · 81-frame chunks Layout: {row id}/epoch-0.safetensors Checkpoint index
Echo-Team/Echo-Memory