Changjiang Jiang
Changjiang Jiang
so why design for " def tokenize(texts: Union[str, List[str]], context_length: int = 77, truncate: bool = False) -> torch.LongTensor: ", what should I change context_length?
> Live preview is not yet support, FR of which is tracked [here](https://github.com/aidenlx/media-extended/issues/107)
I never use it to extract image, but you can extract image by coordinate and pymupdf: for example, you can reference my code: ```python import fitz def get_image_from_corrd(pdf_path, coord, to_path,...