Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,110 @@
+---
+license: apache-2.0
+library_name: pytorch
+pipeline_tag: text-to-video
+tags:
+  - long-video-generation
+  - autoregressive
+  - retrieval-augmented-generation
+  - video-generation
+  - wan
+  - longlive
+language:
+  - en
+---
+
+# LongLive-RAG — Checkpoints & Toy Data
+
+This repository hosts the model checkpoints, prompt files, and a toy latent set for
+**LongLive-RAG: A General Retrieval-Augmented Framework for Long Video Generation**.
+
+- 📄 **Paper:** arXiv (coming soon)
+- 💻 **Code:** https://github.com/qixinhu11/LongLive-RAG
+- 🔍 **TL;DR:** LongLive-RAG turns long video generation into a *retrieval problem*. An
+  autoregressive (AR) video generator looks back over the video it has *already* generated
+  and pulls in the most relevant past latents as extra context — cutting error accumulation,
+  identity drift, and background flicker over long horizons, **without retraining the base
+  generator**.
+
+## What's in here
+
+```
+checkpoints/
+├── causal_forcing.pt              # Causal-Forcing AR backbone
+├── self_forcing.pt                # Self-Forcing AR backbone
+├── longlive_base.pt               # LongLive AR backbone
+├── longlive_lora.pt               # LongLive LoRA (paired with longlive_base.pt)
+├── ae_latent_mem.pt               # Retrieval autoencoder (default for inference)
+├── moviegenbench_128_refined.txt  # 128 MovieGenBench prompts
+└── vidprom_filtered_extended.txt  # Self-Forcing prompt pool (for generate_latent.py)
+toydatasets/
+└── latent_0000xx.pt               # tiny example latent set for the training demo
+```
+
+- **AR backbones** (`causal_forcing.pt`, `self_forcing.pt`, `longlive_base.pt` + `longlive_lora.pt`)
+  are the frozen base generators LongLive-RAG plugs into.
+- **`ae_latent_mem.pt`** is the trainable retrieval encoder (a small latent autoencoder) —
+  the only component LongLive-RAG actually trains.
+- **`toydatasets/`** is a tiny set of clean latent blocks, enough to smoke-test the AE
+  training pipeline end-to-end.
+
+> The base **WAN VAE** (`Wan-AI/Wan2.1-T2V-1.3B`) that LongLive-RAG operates in the latent
+> space of is **not** included here — download it separately (see below).
+
+## Download
+
+Everything restores into the code repo's expected layout with two commands:
+
+```bash
+# Base WAN VAE — LongLive-RAG operates in its latent space
+hf download Wan-AI/Wan2.1-T2V-1.3B --local-dir wan_models/Wan2.1-T2V-1.3B
+
+# All LongLive-RAG assets — restores checkpoints/ and toydatasets/ in place
+hf download qixinhu11/LongLive-RAG --local-dir .
+```
+
+Older setups can swap `hf download` for `huggingface-cli download` (same arguments).
+
+To pull a single file instead of the whole repo:
+
+```bash
+hf download qixinhu11/LongLive-RAG checkpoints/ae_latent_mem.pt --local-dir .
+```
+
+## Usage
+
+Clone the [code repository](https://github.com/qixinhu11/LongLive-RAG), download the assets
+above, then run the shipped 3 × 2 grid (three backbones × two context-assembly methods):
+
+```bash
+# Main result: LongLive backbone + LongLive-RAG retrieval
+bash inference.sh longlive latentmem
+
+# Baseline: native sliding-window
+bash inference.sh causal_forcing native
+```
+
+See the [GitHub README](https://github.com/qixinhu11/LongLive-RAG) for full installation,
+inference, and training instructions.
+
+## License
+
+Released under the [Apache 2.0](https://github.com/qixinhu11/LongLive-RAG/blob/main/LICENSE)
+license. The included AR backbones and WAN VAE latent space derive from their respective
+upstream projects ([LongLive](https://github.com/NVlabs/LongLive),
+[Self-Forcing](https://github.com/guandeh17/Self-Forcing),
+[Causal-Forcing](https://github.com/thu-ml/Causal-Forcing),
+[Wan](https://github.com/Wan-Video/Wan2.1)) — please also respect their original licenses.
+
+## Citation
+
+```bibtex
+@article{longliverag2026,
+  title         = {LongLive-RAG: A General Retrieval-Augmented Framework for Long Video Generation},
+  author        = {Hu, Qixin and Yang, Shuai and Huang, Wei and Han, Song and Chen, Yukang},
+  journal       = {arXiv preprint arXiv:},
+  archivePrefix = {arXiv},
+  eprint        = {},
+  year          = {2026}
+}
+```