from transformers import AutoModelForImageTextToText, AutoProcessor

model = AutoModelForImageTextToText.from_pretrained(
    "QuixiAI/Prisma-VL-8B",
    dtype="auto",
    device_map="auto"
)

processor = AutoProcessor.from_pretrained("QuixiAI/Prisma-VL-8B")

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://static.wikia.nocookie.net/essentialsdocs/images/7/70/Battle.png/revision/latest?cb=20220523172438",
            },
            {
                "type": "text",
                "text": (
                    "Describe your thoughts and your experience of thinking. "
                    "The phenomenology is more important than the actual answer."
                ),
            },
        ],
    }
]

inputs = processor.apply_chat_template(
    messages,
    tokenize=True,
    add_generation_prompt=True,
    return_dict=True,
    return_tensors="pt"
)

inputs = inputs.to(model.device)

generated_ids = model.generate(**inputs, max_new_tokens=1280)
generated_ids_trimmed = [
    out_ids[len(in_ids):] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
]

output_text = processor.batch_decode(
    generated_ids_trimmed,
    skip_special_tokens=True,
    clean_up_tokenization_spaces=False
)

print(output_text)