Add Echo-Memory community pipeline for Wan 2.1 1.3B

[WayneJin0918]

Summary

• Add examples/community/pipeline_echo_memory.py, a WanPipeline subclass that overlays the released Echo-Memory context_k1 row onto official Wan-AI/Wan2.1-T2V-1.3B-Diffusers.
• Key remap matches scripts/convert_wan_to_diffusers.py and covers 825 / 825 official transformer keys. Extra action-MLP / SSM slots are skipped.
• Already-converted weights: Wayne-King/echo-memory-diffusers (context_k1-diffusers/diffusion_pytorch_model.safetensors). The same pipeline class is also hosted there for custom_pipeline="Wayne-King/echo-memory-diffusers".

Paper: arXiv:2606.09803. This is a community overlay, not a new official Wan checkpoint. The multi-chunk camera-action / revisit protocol stays in Echo-Memory.

Test plan

• DiffusionPipeline.from_pretrained("Wan-AI/Wan2.1-T2V-1.3B-Diffusers", custom_pipeline="pipeline_echo_memory")
• pipe.load_echo_memory_weights() prints 825 overlaid keys, 360 skipped
• pipe.load_converted_echo_memory_weights() loads the remapped safetensors

Made with Cursor

[gonzalolater]

ok

[github-actions]

Hi @WayneJin0918, thanks for the PR! It does not appear to link an issue it fixes. If this PR addresses an existing issue, please add a closing keyword (e.g. Fixes #1234) to the PR description so the issue is linked. See the contribution guide for more details. If this PR intentionally does not fix a tracked issue, a maintainer can add the no-issue-needed label to silence this reminder.