--- license: apache-2.0 library_name: diffusers pipeline_tag: image-to-video tags: - world-model - robotics - teleoperation - video-generation - image-to-video - egocentric - diffusion base_model: Wan-AI/Wan2.2-TI2V-5B-Diffusers ---
π« Project Page | π€ Hugging Face | π€ ModelScope | π Video | π arXiv
--- ## π Abstract We introduce **RynnWorld-Teleop**, a robot-centric generative world model that instantiates the paradigm of **digital teleoperation**βdecoupling robot data collection from physical hardware constraints. By transforming an operator's real-time hand-pose stream into high-fidelity egocentric robotic videos from a single reference image, RynnWorld-Teleop enables the scaling of expert trajectories in a purely virtual environment. Our framework integrates depth-aware skeletal conditioning with a progressive human-to-robot training curriculum, allowing it to inherit rich manipulation priors from large-scale human datasets. To support interactive use, we distill the model into a causal, autoregressive student capable of real-time streaming. Policies trained exclusively on RynnWorld-Teleop synthetic data achieve effective zero-shot Sim2Real transfer, demonstrating its power as a high-fidelity data engine for scaling dexterous robotic learning. --- ## π° News * **[2026.07.07]** π₯π₯ Release our Technical Report !! * **[2026.07.07]** π₯π₯ Release our code and model checkpoints!! --- ## π¦ This Repository This repository hosts the **SFT (full fine-tune) checkpoint** of RynnWorld-Teleop. Given a first-frame image and a hand-pose / skeleton control video, the model generates a high-fidelity egocentric robotic video. ### Model Zoo | Model | HuggingFace | ModelScope | | :--------------- | :---------: | :--------: | | SFT | [Link](https://huggingface.co/Alibaba-DAMO-Academy/RynnWorld-Teleop) | [Link](https://www.modelscope.cn/models/DAMO_Academy/RynnWorld-Teleop) | | Causal | [Link](https://huggingface.co/Alibaba-DAMO-Academy/RynnWorld-Teleop-Causal) | [Link](https://www.modelscope.cn/models/DAMO_Academy/RynnWorld-Teleop-Causal) | --- ## π Quick Start Please refer to the [code repository](https://github.com/alibaba-damo-academy/RynnWorld-Teleop) for the full setup, training, and inference pipeline. ### π§ Environment Setup ```bash conda create -n "rynnworld-teleop" python=3.10 -y conda activate rynnworld-teleop pip3 install torch torchvision --index-url https://download.pytorch.org/whl/cu121 pip install -r requirements.txt ``` ### π Download the Checkpoint Our model is developed on top of [Wan2.2-TI2V-5B](https://huggingface.co/Wan-AI/Wan2.2-TI2V-5B-Diffusers). Download the base model and place it under `pretrained/`: ``` RynnWorld-Teleop/ βββ pretrained/ βββ Wan2.2-TI2V-5B-Diffusers/ βββ model_index.json βββ scheduler/ βββ transformer/ βββ vae/ βββ ... ``` Then download our fine-tuned weights: ```bash mkdir -p pretrained/RynnWorld-Teleop huggingface-cli download Alibaba-DAMO-Academy/RynnWorld-Teleop --local-dir pretrained/RynnWorld-Teleop ``` --- ## π¬ Inference Given a first-frame image and a control video (hand-pose / OpenPose mp4), the model generates the corresponding egocentric video. ```bash python inference_user.py \ --image