Clarify ScaleNav usage and fix page previews

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+replay.mp4 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -11,6 +11,14 @@ tags:
 - video-diffusion
 - image-text-to-action
 - safetensors
+library_name: scalenav
+pipeline_tag: robotics
+widget:
+- example_title: 'ScaleNav: three real-robot navigation demos'
+  output:
+    url: replay.mp4
+datasets:
+- Yangyihui/ScaleNav-Data
 ---
 
 # ScaleNav
@@ -19,70 +27,65 @@ tags:
 
 [Paper](https://arxiv.org/abs/2610.25690) · [Code](https://github.com/MachEmbodied/ScaleNav) · [Data](https://huggingface.co/datasets/Yangyihui/ScaleNav-Data) · [Project page](https://zju3dv.github.io/ScaleNav/) · [Collection](https://huggingface.co/collections/Yangyihui/scalenav-6ad591e8ff62bb75ec75f645)
 
-ScaleNav learns navigation priors from Internet egocentric videos through
-action-free pretraining and transfers them to action generation for
-language-conditioned local navigation. The goal is to reach a language-specified
-target visible in the initial observation and stop at the instructed location.
+ScaleNav learns navigation priors through action-free pretraining on Internet
+videos, then turns an RGB observation and a language instruction into robot actions.
+It navigates to a target visible in the initial view and stops at the instructed location.
 
-## License
+**5B parameters · 10.02 GB checkpoint · [CC BY-NC 4.0](LICENSE)**
 
-The ScaleNav fine-tuned checkpoint is released under [CC BY-NC 4.0](LICENSE)
-for noncommercial use. When sharing it or adaptations, provide attribution,
-link to the license, and indicate any changes.
-
-ScaleNav modifies [Wan2.2-TI2V-5B](https://huggingface.co/Wan-AI/Wan2.2-TI2V-5B)
-through navigation pretraining, action alignment and joint fine-tuning. The
-CC BY-NC 4.0 terms apply to the ScaleNav contributions; upstream Wan materials
-retain their [Apache-2.0 license](LICENSE-WAN). The
-[code](https://github.com/MachEmbodied/ScaleNav/blob/main/LICENSE) is separately
-licensed under Apache-2.0, and [dataset components](https://huggingface.co/datasets/Yangyihui/ScaleNav-Data#sources-and-license)
-retain their respective terms.
+Watch the three real-robot demos in the video preview, or visit the
+[project page](https://zju3dv.github.io/ScaleNav/#demos).
 
 ## Download
 
-Install ScaleNav using the [installation guide](https://github.com/MachEmbodied/ScaleNav#installation),
-then run from the code repository root. This model repository is public;
-authentication is optional:
+Complete the [installation](https://github.com/MachEmbodied/ScaleNav/blob/main/docs/INSTALL.md#environment),
+then run from the ScaleNav code repository root:
 
 ```bash
 python scripts/download_checkpoint.py --output checkpoints/scalenav
 ```
 
-The downloader uses the revision and file checksums in the
-[download manifest](https://github.com/MachEmbodied/ScaleNav/blob/main/docs/checkpoint-download-manifest.json),
-resumes interrupted downloads and verifies SHA-256.
+The downloader resumes interrupted transfers and verifies the pinned
+[checkpoint checksums](https://github.com/MachEmbodied/ScaleNav/blob/main/docs/checkpoint-download-manifest.json).
+No HF login is required for this checkpoint.
+
+Also download the **Wan VAE, text encoder and tokenizer** (14.20 GB) following
+the [checkpoint setup](https://github.com/MachEmbodied/ScaleNav/blob/main/docs/INSTALL.md#checkpoints).
+For inference, use a BF16-capable NVIDIA GPU; **24 GB GPU memory and 64 GB system RAM**
+are recommended.
 
-To download directly with the Hugging Face CLI:
+<details>
+<summary>Download with the Hugging Face CLI</summary>
 
 ```bash
 hf download Yangyihui/ScaleNav --revision 8808b3589142b52e3bf0719aa0ecff8f86715a4a --local-dir checkpoints/scalenav \
   --include 'transformer/*' ar_model.pt train_meta.pt SHA256SUMS.json
 ```
 
-Download the Wan VAE, text encoder and tokenizer using the
-[installation and checkpoint guide](https://github.com/MachEmbodied/ScaleNav#checkpoints).
+</details>
 
 ## Inference
 
-Prepare the paired observation and its original instruction using the
-[single-image inference guide](https://github.com/MachEmbodied/ScaleNav/blob/main/docs/INFERENCE.md#single-image-inference), then run:
+Use ScaleNav's `awm` CLI with your own image and an instruction describing a target
+visible in it:
 
 ```bash
 awm check --checkpoint checkpoints/scalenav --sha256
 awm infer --checkpoint checkpoints/scalenav \
   --base-model checkpoints/Wan2.2-TI2V-5B \
-  --image data/example/observation.png \
-  --prompt "$(cat data/example/instruction.txt)" --seed 1065612570 \
+  --image /path/to/observation.png \
+  --prompt "Walk to the chair visible in the initial view." \
   --output outputs/example
 ```
 
-This saves the nine-step action trajectory as `observation_trajectory.npy` and
-a trajectory visualization as `observation_trajectory.png`. Add `--decode-video`
-to also save nine predicted RGB frames as `observation_generated_raw.mp4`.
-Actions are per-frame forward/right/clockwise-yaw displacements in
-metres/metres/radians.
-Continuous navigation uses incoming camera frames through
-[`awm serve`](https://github.com/MachEmbodied/ScaleNav/blob/main/docs/INFERENCE.md).
+Replace the image path and instruction with a matching pair. This saves nine
+per-frame action deltas in `observation_trajectory.npy` and a visualization in
+`observation_trajectory.png`. Actions are forward/right/clockwise-yaw displacements
+in metres/metres/radians. Add `--decode-video` to save the nine predicted RGB frames.
+
+For continuous navigation, use [`awm serve`](https://github.com/MachEmbodied/ScaleNav/blob/main/docs/INFERENCE.md#http-api).
+See the [inference guide](https://github.com/MachEmbodied/ScaleNav/blob/main/docs/INFERENCE.md)
+for paired examples, outputs and the robot adapter.
 
 ## Model settings
 
@@ -115,3 +118,17 @@ The released checkpoint is the final joint-fine-tuning checkpoint at step 6500.
 It contains model weights and deployment metadata. Optimizer, scheduler and RNG
 state for exact training resumption are not included. The Wan VAE, text encoder
 and tokenizer are downloaded separately.
+
+## License
+
+The ScaleNav fine-tuned checkpoint is released under [CC BY-NC 4.0](LICENSE)
+for noncommercial use. When sharing it or adaptations, provide attribution,
+link to the license, and indicate any changes.
+
+ScaleNav modifies [Wan2.2-TI2V-5B](https://huggingface.co/Wan-AI/Wan2.2-TI2V-5B)
+through navigation pretraining, action alignment and joint fine-tuning. The
+CC BY-NC 4.0 terms apply to the ScaleNav contributions; upstream Wan materials
+retain their [Apache-2.0 license](LICENSE-WAN). The
+[code](https://github.com/MachEmbodied/ScaleNav/blob/main/LICENSE) is separately
+licensed under Apache-2.0, and [dataset components](https://huggingface.co/datasets/Yangyihui/ScaleNav-Data#sources-and-license)
+retain their respective terms.

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e94499518683dad0c9a8ebfc6b8ceffc0c7c68f8bf5a6fe280fd6dc1c0803265
+size 7621843