Qwen2.5-VL-32B 모델로 image to text(이미지로 텍스트 생성) 해보기(Gemma3 비교)

https://huggingface.co/Qwen/Qwen2.5-VL-32B-Instruct

Qwen/Qwen2.5-VL-32B-Instruct · Hugging Face

 

전 글의 Qwen2.5-VL-32B 모델로 OCR 해보기에 이어서 이전에 Gemma3로 했던 image-to-text를 해봤습니다.

 

 

- Qwen2.5-VL-32B 사용 예시

# 최신 transformers 설치
pip install git+https://github.com/huggingface/transformers accelerate

# It's highly recommanded to use `[decord]` feature for faster video loading.
pip install qwen-vl-utils[decord]==0.0.8

from transformers import Qwen2_5_VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info

# default: Load the model on the available device(s)
model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
    "Qwen/Qwen2.5-VL-32B-Instruct", torch_dtype="auto", device_map="auto"
)

# We recommend enabling flash_attention_2 for better acceleration and memory saving, especially in multi-image and video scenarios.
# model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
#     "Qwen/Qwen2.5-VL-32B-Instruct",
#     torch_dtype=torch.bfloat16,
#     attn_implementation="flash_attention_2",
#     device_map="auto",
# )

# default processer
processor = AutoProcessor.from_pretrained("Qwen/Qwen2.5-VL-32B-Instruct")

# The default range for the number of visual tokens per image in the model is 4-16384.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# min_pixels = 256*28*28
# max_pixels = 1280*28*28
# processor = AutoProcessor.from_pretrained("Qwen/Qwen2.5-VL-32B-Instruct", min_pixels=min_pixels, max_pixels=max_pixels)

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/0052a70beed5bf71b92610a43a52df6d286cd5f3/diffusers/rabbit.jpg",
            },
            {"type": "text", "text": "이미지에 대해 자세히 설명해줘"},
        ],
    }
]

# Preparation for inference
text = processor.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True
)
image_inputs, video_inputs = process_vision_info(messages)
inputs = processor(
    text=[text],
    images=image_inputs,
    videos=video_inputs,
    padding=True,
    return_tensors="pt",
)
inputs = inputs.to("cuda")

# Inference: Generation of the output
generated_ids = model.generate(**inputs, max_new_tokens=1000)
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)

 

Gemma3 때와 비교를 위해 같은 rabbit 이미지 받았고요.

 

- Qwen2.5-VL-32B 답변

 

- Gemma3-27B 답변

 

같은 명령과 max_tokens(1000)를 사용하였는데 Qwen2.5가 훨씬 상세하네요.

 

Image-to-text 기능도 매우 잘 해냄을 확인했습니다.