---
title: "Echo-Memory"
description: "JD Echo-Memory identity permanently pinned to context_k1 (K=1). Wan2.1-1.3B. CC-BY-4.0. 2026-07-20 A100 clip is historical — native CUDA artifact pending."
modelId: "echo-memory-context-k1"
pageSource: authored
---
Echo-Memory Context K=1 is **one identity** in JD's Echo-Memory family: a Wan2.1-T2V-1.3B interactive world that differs from siblings **only** in memory. This card is permanently bound to `context_k1/epoch-0.safetensors` — each new chunk conditions on **K=1** context frame. You do **not** pick a memory method at runtime. Pipeline: `EchoMemoryContextK1Pipeline`. Aliases `echo-context-k1` and `echo-memory` resolve here.
Paper: [arXiv 2606.09803](https://arxiv.org/abs/2606.09803). Project: [echo-team-joy-future-academy-jd.github.io/Echo-Memory](https://echo-team-joy-future-academy-jd.github.io/Echo-Memory/). Code: [Echo-Team-Joy-Future-Academy-JD/Echo-Memory](https://github.com/Echo-Team-Joy-Future-Academy-JD/Echo-Memory). Weights: `Echo-Team/Echo-Memory` (**cc-by-4.0**) plus `Wan-AI/Wan2.1-T2V-1.3B` (**apache-2.0**).
A **2026-07-20** A100 artifact **predates** the NativeDiffusionPipeline cutover and is **historical only**. Fresh CUDA artifact, official sample parity, and bench scoring are **pending**. Visual quality is research-preview (1.3B).
## What it is for
Echo memory-context K1 slots, not the Infinity long-video card.
Launch `worldfoundry-eval run echo-memory-context-k1`.
Score on [MemoBench](/docs/evaluation/benchmark-hub/memobench) — purpose-built for evaluating long-horizon memory in interactive world models.
## Runtime contract
Required: `prompt` and `image`; optional: `video`; `actions`: camera_trajectory; artifacts: `generated_world_video` and `echo-memory-context-k1.mp4`.
| Knob | Default |
| --- | --- |
| Size | **640×352** |
| Frames | **81** |
| FPS | **15** |
| Chunks | **2** |
| Context frames | **1** |
| Sample steps | **50** |
| Sample shift | **5.0** |
| Camera trajectory | `z*80` (stationary) |
| Camera translation step | **0.00125** per frame (`w*80` moves +Y 0.1 per chunk) |
| Camera rotation step | **0.5625°** per frame (`left*80` turns 45° per chunk) |
| Finetune | `Echo-Team/Echo-Memory` (`cc-by-4.0`) |
| Backbone | `Wan-AI/Wan2.1-T2V-1.3B` (`apache-2.0`) |
Pass `camera_trajectory="w*80"` to request the published forward action scale, or `"left*80"` for a 45° turn. A camera move mentioned only in the prompt does not replace the default stationary action. `camera_translation_step` and `camera_rotation_step_degrees` can override the per-frame distances.
## Run in WorldFoundry
Status: **Runner parity pending**. Unified environment `worldfoundry-unified-cu128` (Python 3.11, CUDA 12.8). Stage `Echo-Team/Echo-Memory`, `Wan-AI/Wan2.1-T2V-1.3B`, and `Echo-Team/Echo-Memory` among others locally — missing files fail at load, nothing is downloaded. Run `worldfoundry-eval run echo-memory-context-k1`. License: CC-BY-4.0 and apache-2.0. Catalog VRAM is unset.
`worldfoundry/base_models/diffusion_model/models/networks/echo_memory` holds checkpoint-specific network blocks only. It is not a CLI. Memory lifecycle, model assembly, and the runtime contract stay in the shared diffusion infrastructure. How to add a new immutable recipe is on the [inference guide](/docs/guides/inference#echo-memory-context-k1). Checkpoint staging is on [local assets](/docs/guides/local-assets).