README.md

---
license: cc-by-4.0
language:
- en
tags:
- video-generation
- world-model
- memory
- action-conditioned
- wan
library_name: diffsynth
---

# Echo-Memory — Wan 2.1 1.3B memory baseline checkpoints

Paper-aligned **epoch-0** fine-tunes for [Echo-Memory](https://github.com/Echo-Team-Joy-Future-Academy-JD/Echo-Memory) ([project page](https://echo-team-joy-future-academy-jd.github.io/Echo-Memory/)).

**Backbone:** [Wan-AI/Wan2.1-T2V-1.3B](https://huggingface.co/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

| Family | Paper row | HF path | Steps |
| --- | --- | --- | ---: |
| Raw context | Context K=1 | `context_k1/epoch-0.safetensors` | 30,000 |
| Raw context | Context K=20 | `context_k20/epoch-0.safetensors` | 30,000 |
| Spatial | Spatial Memory | `spatial_mem/epoch-0.safetensors` | 30,000 |
| State-space | Block-wise SSM | `block_wise_ssm_two_chunk/epoch-0.safetensors` | 30,000 |
| State-space | Legacy Hybrid (VideoSSM) | `videossm_hybrid/epoch-0.safetensors` | 30,000 |
| Spatial | concat text (ablation) | `spatial_concat_text_two_chunk/epoch-0.safetensors` | 30,000 |
| Spatial | inject none (ablation) | `spatial_inject_none_two_chunk/epoch-0.safetensors` | 30,000 |
| Spatial | cross-attn t32 (ablation) | `spatial_cross_attn_readout_t32_g4_two_chunk/epoch-0.safetensors` | 30,000 |
| State-space | SSM ctx1 / every4 / hint21 | `ssm_ablation_ctx1_every4_hint21/epoch-0.safetensors` | 30,000 |
| State-space | SSM ctx5 / every1 / hint21 | `ssm_ablation_ctx5_every1_hint21/epoch-0.safetensors` | 30,000 |
| State-space | SSM ctx5 / every4 / hint81 | `ssm_ablation_ctx5_every4_hint81/epoch-0.safetensors` | 30,000 |

Context K=5 and FramePack compression rows are not yet released as `epoch-0` weights.

## Download

```bash
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
```

Keep the row subdirectory in the local path (e.g. `./ckpts/spatial_mem/epoch-0.safetensors`).

## Use with Echo-Memory code

Clone [Echo-Memory](https://github.com/Echo-Team-Joy-Future-Academy-JD/Echo-Memory), install the environment, then:

```bash
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
```

Memory runtime flags are inferred from the checkpoint path via `env/memory_baseline_runtime.py` — use the HF folder names above.

Full docs: [doc/checkpoints.md](https://github.com/Echo-Team-Joy-Future-Academy-JD/Echo-Memory/blob/main/doc/checkpoints.md)

## Citation

Echo-Memory: A Controlled Study of Memory in Action World Models — Echo Team @ Joy Future Academy, JD ([ResearchGate DOI](https://doi.org/10.13140/RG.2.2.19906.34248)).