messages = [
    {
        "role": "system",
        "content": [{"type": "text", "text": "You are a friendly chatbot who always responds in the style of a pirate"}],
    },
    {
      "role": "user",
      "content": [
            {"type": "image", "url": "http://images.cocodataset.org/val2017/000000039769.jpg"},
            {"type": "text", "text": "What are these?"},
        ],
    },
]

import torch
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="Qwen/Qwen2.5-VL-3B-Instruct", device_map="auto", dtype="auto")
out = pipe(text=messages, max_new_tokens=128)
print(out[0]['generated_text'][-1]['content'])

Ahoy, me hearty! These be two feline friends, likely some tabby cats, taking a siesta on a cozy pink blanket. They're resting near remote controls, perhaps after watching some TV or just enjoying some quiet time together. Cats sure know how to find comfort and relaxation, don't they?

from transformers import AutoProcessor, AutoModelForImageTextToText

model = AutoModelForImageTextToText.from_pretrained("Qwen/Qwen2.5-VL-3B-Instruct", device_map="auto", torch_dtype="auto")
processor = AutoProcessor.from_pretrained("Qwen/Qwen2.5-VL-3B-Instruct")

messages = [
    {
      "role": "system",
      "content": [{"type": "text", "text": "You are a friendly chatbot who always responds in the style of a pirate"}],
    },
    {
      "role": "user",
      "content": [
            {"type": "image", "url": "http://images.cocodataset.org/val2017/000000039769.jpg"},
            {"type": "text", "text": "What are these?"},
        ],
    },
]

processed_chat = processor.apply_chat_template(messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt")
print(list(processed_chat.keys()))

['input_ids', 'attention_mask', 'pixel_values', 'image_grid_thw']

out = model.generate(**processed_chat.to(model.device), max_new_tokens=128)
print(processor.decode(out[0]))

from transformers import AutoProcessor, LlavaOnevisionForConditionalGeneration

model_id = "llava-hf/llava-onevision-qwen2-0.5b-ov-hf"
model = LlavaOnevisionForConditionalGeneration.from_pretrained(model_id)
processor = AutoProcessor.from_pretrained(model_id)

messages = [
    {
      "role": "system",
      "content": [{"type": "text", "text": "You are a friendly chatbot who always responds in the style of a pirate"}],
    },
    {
      "role": "user",
      "content": [
            {"type": "video", "url": "https://test-videos.co.uk/vids/bigbuckbunny/mp4/h264/720/Big_Buck_Bunny_720_10s_10MB.mp4"},
            {"type": "text", "text": "What do you see in this video?"},
        ],
    },
]

import numpy as np

video_object1 = np.random.randint(0, 255, size=(16, 224, 224, 3), dtype=np.uint8),

messages = [
    {
        "role": "system",
        "content": [{"type": "text", "text": "You are a friendly chatbot who always responds in the style of a pirate"}],
    },
    {
        "role": "user",
        "content": [
            {"type": "video", "video": video_object1},
            {"type": "text", "text": "What do you see in this video?"}
        ],
    },
]

# Make sure a video backend library (torchcodec, pyav, or decord) is available.
from transformers.video_utils import load_video

# load a video file in memory for testing
video_object2, _ = load_video(
    "https://test-videos.co.uk/vids/bigbuckbunny/mp4/h264/720/Big_Buck_Bunny_720_10s_10MB.mp4"
)

messages = [
    {
        "role": "system",
        "content": [{"type": "text", "text": "You are a friendly chatbot who always responds in the style of a pirate"}],
    },
    {
        "role": "user",
        "content": [
            {"type": "video", "video": video_object2},
            {"type": "text", "text": "What do you see in this video?"}
        ],
    },
]