keye-vl-utils 1.5.2

Keye Vision Language Model Utils - PyTorch

keye-vl-utils

Keye-VL Utils contains a set of helper functions for processing and integrating visual language information with KeyeVL1.5.

Install

pip install keye-vl-utils==1.5.2

Usage

KeyeVL

from transformers import AutoModel, AutoProcessor
from keye_vl_utils import process_vision_info


# You can directly insert a local file path, a URL, or a base64-encoded image into the position where you want in the text.
messages = [
    # Image
    ## Local file path
    [{"role": "user", "content": [{"type": "image", "image": "file:///path/to/your/image.jpg"}, {"type": "text", "text": "Describe this image."}]}],
    ## Image URL
    [{"role": "user", "content": [{"type": "image", "image": "http://path/to/your/image.jpg"}, {"type": "text", "text": "Describe this image."}]}],
    ## Base64 encoded image
    [{"role": "user", "content": [{"type": "image", "image": "data:image;base64,/9j/..."}, {"type": "text", "text": "Describe this image."}]}],
    ## PIL.Image.Image
    [{"role": "user", "content": [{"type": "image", "image": pil_image}, {"type": "text", "text": "Describe this image."}]}],
    # Video
    ## Local video path
    [{"role": "user", "content": [{"type": "video", "video": "file:///path/to/video1.mp4"}, {"type": "text", "text": "Describe this video."}]}],
    ## Local video frames
    [{"role": "user", "content": [{"type": "video", "video": ["file:///path/to/extracted_frame1.jpg", "file:///path/to/extracted_frame2.jpg", "file:///path/to/extracted_frame3.jpg"],}, {"type": "text", "text": "Describe this video."},],}],
    ## Model dynamically adjusts video nframes, video height and width. specify args if required.
    [{"role": "user", "content": [{"type": "video", "video": "file:///path/to/video1.mp4"}, {"type": "text", "text": "Describe this video."}]}],
]

processor = AutoProcessor.from_pretrained("Kwai-Keye/Keye-VL-1.5-8B", trust_remote_code=True)
model = AutoModel.from_pretrained("Kwai-Keye/Keye-VL-1.5-8B", torch_dtype="auto", device_map="auto", trust_remote_code=True)
text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
images, videos, **processor_args = process_vision_info(messages)
inputs = processor(text=text, images=images, videos=videos,  return_tensors="pt", **processor_args)
print(inputs)
generated_ids = model.generate(**inputs)
print(generated_ids)