Performs a single turn of conversation, optionally including visual input. Supports a two-phase generation process with a "thinking_b

Build single-model Gradio demo interface.

Extract a fixed number of frames from the video file.

Run an inference example with multiple image inputs.

Run an inference example with a single image input.

Run an inference example with text-only input.

Run an inference example with a video input.

Rescales the image so that the following conditions are met: 1. Both dimensions (height and width) are divisible by 'factor'. 2. The t

Fills the input Tensor with values drawn from a truncated normal distribution. The values are effectively drawn from the normal distribution :

Initialize the weights

Reset all inputs and outputs.

Restore UI status after generation ends.