process_vision_info

def process_vision_info(
    conversations: Union[List[Dict[str, Any]], List[List[Dict[str, Any]]]],
    return_video_kwargs: bool = False,
    return_video_metadata: bool = False,
    image_patch_size: int = 14,
) -> Tuple[Optional[List[Image.Image]], Optional[List[Union[torch.Tensor, List[Image.Image]]]], Optional[Dict[str, Any]]]

from transformers import Qwen2VLForConditionalGeneration, AutoProcessor
from qwen_vl_utils import process_vision_info

messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "image": "file:///path/to/image.jpg"},
            {"type": "text", "text": "Describe this image."}
        ]
    }
]

processor = AutoProcessor.from_pretrained(model_path)
model = Qwen2VLForConditionalGeneration.from_pretrained(
    model_path, torch_dtype="auto", device_map="auto"
)

text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
images, videos = process_vision_info(messages)
inputs = processor(text=text, images=images, videos=videos, padding=True, return_tensors="pt")

generated_ids = model.generate(**inputs)

from transformers import Qwen2_5_VLForConditionalGeneration, AutoProcessor
from qwen_vl_utils import process_vision_info

messages = [
    {
        "role": "user",
        "content": [
            {"type": "video", "video": "file:///path/to/video.mp4", "fps": 2.0},
            {"type": "text", "text": "Describe this video."}
        ]
    }
]

processor = AutoProcessor.from_pretrained(model_path)
model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
    model_path, torch_dtype="auto", device_map="auto"
)

text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
images, videos, video_kwargs = process_vision_info(messages, return_video_kwargs=True)
inputs = processor(
    text=text, images=images, videos=videos, 
    padding=True, return_tensors="pt", **video_kwargs
)

generated_ids = model.generate(**inputs)

from transformers import Qwen3VLForConditionalGeneration, AutoProcessor
from qwen_vl_utils import process_vision_info

messages = [
    {
        "role": "user",
        "content": [
            {"type": "video", "video": "file:///path/to/video.mp4"},
            {"type": "text", "text": "Describe this video."}
        ]
    }
]

processor = AutoProcessor.from_pretrained(model_path)
model = Qwen3VLForConditionalGeneration.from_pretrained(
    model_path, dtype="auto", device_map="auto"
)

text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
images, videos, video_kwargs = process_vision_info(
    messages, image_patch_size=16, return_video_kwargs=True, return_video_metadata=True
)

if videos is not None:
    videos, video_metadatas = zip(*videos)
    videos, video_metadatas = list(videos), list(video_metadatas)
else:
    video_metadatas = None

inputs = processor(
    text=text, images=images, videos=videos, 
    video_metadata=video_metadatas, return_tensors="pt", 
    do_resize=False, **video_kwargs
)
inputs = inputs.to(model.device)

generated_ids = model.generate(**inputs)

# Local file
{"type": "image", "image": "file:///path/to/image.jpg"}

# URL
{"type": "image", "image": "http://example.com/image.jpg"}

# Base64
{"type": "image", "image": "data:image;base64,/9j/..."}

# PIL Image
{"type": "image", "image": pil_image}

# With custom dimensions
{
    "type": "image",
    "image": "file:///path/to/image.jpg",
    "resized_height": 280,
    "resized_width": 420
}

# Video file
{"type": "video", "video": "file:///path/to/video.mp4"}

# Frame sequence
{
    "type": "video",
    "video": [
        "file:///path/to/frame1.jpg",
        "file:///path/to/frame2.jpg",
        "file:///path/to/frame3.jpg"
    ]
}

# With custom parameters
{
    "type": "video",
    "video": "file:///path/to/video.mp4",
    "fps": 2.0,
    "resized_height": 280,
    "resized_width": 280
}