Remove unused placeholder example images

Add RoboTwin place_bread_basket example frame

Add RoboTwin open_laptop example frame

Add RoboTwin lift_pot example frame

Replace placeholder examples with real RoboTwin world-model demo inputs

World-model mode: hold flow stream fixed at clean latent, denoise only RGB; drop RoboTwin camera prefix

Prepend trained CAMERA_PREFIX to video prompt to match reference (fix garbled output)

Delete files dataset_action_robotwin.py dual_stream_capture.py example_input.jpg msgpack_numpy.py pipeline_loader.py reversible_flow_codec.py setup.py with huggingface_hub

Upload app.py with huggingface_hub

Upload folder using huggingface_hub

Upload requirements.txt with huggingface_hub

Upload folder using huggingface_hub

initial commit