r""" Args: prompt (`str` or `List[str]`, *optional*): prompt to be encoded prompt_2 (`str` or `List[str]`, *optional*

Predict the sample from the previous timestep by reversing the SDE. This function propagates the diffusion process from the learned model out

r""" Function invoked when calling the pipeline for generation. Args: prompt (`str` or `List[str]`, *optional*): The prom

Load lines from a file. First tries to load from `path` directly, and if that doesn't exist, searches the `d3po_pytorch/assets` directory for

Locate an object by name or dotted path, importing as necessary. This is similar to the pydoc function `locate`, except that it checks for

Score all records via LMM API and aggregate by category/law.

Generate images for each test sample and save metadata.

Parse the nvidia-smi output and extract the memory used stats.

Extract overall/reality score from LMM JSON response.

Send image + prompt to an OpenAI-compatible multimodal API.

Calls the scheduler's `set_timesteps` method and retrieves timesteps from the scheduler after the call. Handles custom timesteps. Any kwargs