Echo Memory

--- language: - en library_name: diffsynth license: cc-by-4.0 pipeline_tag: image-to-video base_model: - Wan-AI/Wan2.1-T2V-1.3B arxiv: 2606.09803 tags: - video-generation - world-model - memory - action-conditioned - wan - image-to-video --- # Echo-Memory — Wan 2.1 1.3B memory checkpoints Validated **30,000-step** fine-tunes for [Echo-Memory](https://github.com/Echo-Team-Joy-Future-Academy-JD/Echo-Memory), built on [Wan-AI/Wan2.1-T2V-1.3B](https://huggingface.co/Wan-AI/Wan2.1-T2V-1.3B). [Paper](https://huggingface.co/papers/2606.09803) · [Project page](https://echo-team-joy-future-academy-jd.github.io/Echo-Memory/) · [Code](https://github.com/Echo-Team-Joy-Future-Academy-JD/Echo-Memory) · [**Interactive demo**](https://huggingface.co/spaces/hugging-apps/echo-memory) · [Dataset](https://huggingface.co/datasets/Echo-Team/Echo-Memory-Data) Try the model in the browser (ZeroGPU, no local GPU): **[hugging-apps/echo-memory](https://huggingface.co/spaces/hugging-apps/echo-memory)** ## Available checkpoints | Family | Checkpoint | Steps | SHA256 | | --- | --- | ---: | --- | | Raw context | `context_k1/epoch-0.safetensors` | 30,000 | See LFS metadata | | Compression | `framepack_len_r8/epoch-0.safetensors` | 30,000 | `dd57625506a2c68c402dc05de8f3c6fc5f5376fcac77d7fb6f26eb6ace1d74bf` | | State-space | `block_wise_ssm_causal_v2/epoch-0.safetensors` | 30,000 | `0dd90ea3f3423644f4d68c6d1185d7d717d328f5922ee21f745fc85abe9a01a9` | MoC, geometry-grounded spatial memory, legacy SSM, and VideoSSM weights are not part of this validated release. ## Download ```bash huggingface-cli download Echo-Team/Echo-Memory \ block_wise_ssm_causal_v2/epoch-0.safetensors \ framepack_len_r8/epoch-0.safetensors \ --local-dir ./ckpts ``` Keep the row folder in the local path. Echo-Memory auto-detects the profile and restores the trained context order, FramePack strategy, and camera-RT continuation. ## Multi-chunk inference ```bash export WAN_BASE_MODEL=/path/to/Wan2.1-T2V-1.3B export CONTEXT_IMAGE=/path/to/first_frame.png export ACTION_PATH=/path/to/81_frame_camera_action.json CKPT=./ckpts/block_wise_ssm_causal_v2/epoch-0.safetensors NUM_CHUNKS=4 \ bash inference/memory_baselines_basic/run_infer_block_wise_ssm_causal_v2.sh CKPT=./ckpts/framepack_len_r8/epoch-0.safetensors NUM_CHUNKS=4 \ bash inference/memory_baselines_basic/run_infer_framepack_len_r8.sh ``` ## Citation `...

--- language: - en library_name: diffsynth license: cc-by-4.0 pipeline_tag: image-to-video tags: - video-generation - world-model - memory - action-conditioned - wan --- # 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). [**Paper**](https://huggingface.co/papers/2606.09803) | [**Project Page**](https://echo-team-joy-future-academy-jd.github.io/Echo-Memory/) | [**GitHub**](https://github.com/Echo-Team-Joy-Future-Academy-JD/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 cod...

Source context: 0 downloads · 2 likes · Pipeline image-to-video · Library diffsynth · Repo Echo-Team/Echo-Memory