手机端实现GPT-4o级别多模态大模型：单图、多图与高帧率视频理解

import torch
from PIL import Image
from transformers import AutoModel, AutoTokenizer

torch.manual_seed(100)

model = AutoModel.from_pretrained('openbmb/MiniCPM-V-4_5', trust_remote_code=True, # or openbmb/MiniCPM-o-2_6
    attn_implementation='sdpa', torch_dtype=torch.bfloat16) # sdpa or flash_attention_2, no eager
model = model.eval().cuda()
tokenizer = AutoTokenizer.from_pretrained('openbmb/MiniCPM-V-4_5', trust_remote_code=True) # or openbmb/MiniCPM-o-2_6

image = Image.open('./assets/minicpmo2_6/show_demo.jpg').convert('RGB')

enable_thinking=False # If `enable_thinking=True`, the thinking mode is enabled.
stream=True # If `stream=True`, the answer is string

# First round chat 
question = "What is the landform in the picture?"
msgs = [{'role': 'user', 'content': [image, question]}]

answer = model.chat(
    msgs=msgs,
    tokenizer=tokenizer,
    enable_thinking=enable_thinking,
    stream=True
)

generated_text = ""
for new_text in answer:
    generated_text += new_text
    print(new_text, flush=True, end='')

# Second round chat, pass history context of multi-turn conversation
msgs.append({"role": "assistant", "content": [generated_text]})
msgs.append({"role": "user", "content": ["What should I pay attention to when traveling here?"]})

answer = model.chat(
    msgs=msgs,
    tokenizer=tokenizer,
    stream=True
)

generated_text = ""
for new_text in answer:
    generated_text += new_text
    print(new_text, flush=True, end='')

# round1
The landform in the picture is karst topography. Karst landscapes are characterized by distinctive, jagged limestone hills or mountains with steep, irregular peaks and deep valleys—exactly what you see here These unique formations result from the dissolution of soluble rocks like limestone over millions of years through water erosion.

This scene closely resembles the famous karst landscape of Guilin and Yangshuo in China’s Guangxi Province. The area features dramatic, pointed limestone peaks rising dramatically above serene rivers and lush green forests, creating a breathtaking and iconic natural beauty that attracts millions of visitors each year for its picturesque views.

# round2
When traveling to a karst landscape like this, here are some important tips:

1. Wear comfortable shoes: The terrain can be uneven and hilly.
2. Bring water and snacks for energy during hikes or boat rides.
3. Protect yourself from the sun with sunscreen, hats, and sunglasses—especially since you’ll likely spend time outdoors exploring scenic spots.
4. Respect local customs and nature regulations by not littering or disturbing wildlife.

By following these guidelines, you'll have a safe and enjoyable trip while appreciating the stunning natural beauty of places such as Guilin’s karst mountains.

## The 3d-resampler compresses multiple frames into 64 tokens by introducing temporal_ids. 
# To achieve this, you need to organize your video data into two corresponding sequences: 
#   frames: List[Image]
#   temporal_ids: List[List[Int]].

import torch
from PIL import Image
from transformers import AutoModel, AutoTokenizer
from decord import VideoReader, cpu    # pip install decord
from scipy.spatial import cKDTree
import numpy as np
import math

model = AutoModel.from_pretrained('openbmb/MiniCPM-V-4_5', trust_remote_code=True,  # or openbmb/MiniCPM-o-2_6
    attn_implementation='sdpa', torch_dtype=torch.bfloat16) # sdpa or flash_attention_2, no eager
model = model.eval().cuda()
tokenizer = AutoTokenizer.from_pretrained('openbmb/MiniCPM-V-4_5', trust_remote_code=True)  # or openbmb/MiniCPM-o-2_6

MAX_NUM_FRAMES=180 # Indicates the maximum number of frames received after the videos are packed. The actual maximum number of valid frames is MAX_NUM_FRAMES * MAX_NUM_PACKING.
MAX_NUM_PACKING=3  # indicates the maximum packing number of video frames. valid range: 1-6
TIME_SCALE = 0.1 

def map_to_nearest_scale(values, scale):
    tree = cKDTree(np.asarray(scale)[:, None])
    _, indices = tree.query(np.asarray(values)[:, None])
    return np.asarray(scale)[indices]


def group_array(arr, size):
    return [arr[i:i+size] for i in range(0, len(arr), size)]

def encode_video(video_path, choose_fps=3, force_packing=None):
    def uniform_sample(l, n):
        gap = len(l) / n
        idxs = [int(i * gap + gap / 2) for i in range(n)]
        return [l[i] for i in idxs]
    vr = VideoReader(video_path, ctx=cpu(0))
    fps = vr.get_avg_fps()
    video_duration = len(vr) / fps
        
    if choose_fps * int(video_duration) <= MAX_NUM_FRAMES:
        packing_nums = 1
        choose_frames = round(min(choose_fps, round(fps)) * min(MAX_NUM_FRAMES, video_duration))
        
    else:
        packing_nums = math.ceil(video_duration * choose_fps / MAX_NUM_FRAMES)
        if packing_nums <= MAX_NUM_PACKING:
            choose_frames = round(video_duration * choose_fps)
        else:
            choose_frames = round(MAX_NUM_FRAMES * MAX_NUM_PACKING)
            packing_nums = MAX_NUM_PACKING

    frame_idx = [i for i in range(0, len(vr))]      
    frame_idx =  np.array(uniform_sample(frame_idx, choose_frames))

    if force_packing:
        packing_nums = min(force_packing, MAX_NUM_PACKING)
    
    print(video_path, ' duration:', video_duration)
    print(f'get video frames={len(frame_idx)}, packing_nums={packing_nums}')
    
    frames = vr.get_batch(frame_idx).asnumpy()

    frame_idx_ts = frame_idx / fps
    scale = np.arange(0, video_duration, TIME_SCALE)

    frame_ts_id = map_to_nearest_scale(frame_idx_ts, scale) / TIME_SCALE
    frame_ts_id = frame_ts_id.astype(np.int32)

    assert len(frames) == len(frame_ts_id)

    frames = [Image.fromarray(v.astype('uint8')).convert('RGB') for v in frames]
    frame_ts_id_group = group_array(frame_ts_id, packing_nums)
    
    return frames, frame_ts_id_group


video_path="video_test.mp4"
fps = 5 # fps for video
force_packing = None # You can set force_packing to ensure that 3D packing is forcibly enabled; otherwise, encode_video will dynamically set the packing quantity based on the duration.
frames, frame_ts_id_group = encode_video(video_path, fps, force_packing=force_packing)

question = "Describe the video"
msgs = [
    {'role': 'user', 'content': frames + [question]}, 
]


answer = model.chat(
    msgs=msgs,
    tokenizer=tokenizer,
    use_image_id=False,
    max_slice_nums=1,
    temporal_ids=frame_ts_id_group
)
print(answer)

import torch
from PIL import Image
from transformers import AutoModel, AutoTokenizer

model = AutoModel.from_pretrained('openbmb/MiniCPM-V-4_5', trust_remote_code=True,
    attn_implementation='sdpa', torch_dtype=torch.bfloat16) # sdpa or flash_attention_2
model = model.eval().cuda()
tokenizer = AutoTokenizer.from_pretrained('openbmb/MiniCPM-V-4_5', trust_remote_code=True)

image1 = Image.open('image1.jpg').convert('RGB')
image2 = Image.open('image2.jpg').convert('RGB')
question = 'Compare image 1 and image 2, tell me about the differences between image 1 and image 2.'

msgs = [{'role': 'user', 'content': [image1, image2, question]}]

answer = model.chat(
    msgs=msgs,
    tokenizer=tokenizer
)
print(answer)

import torch
from PIL import Image
from transformers import AutoModel, AutoTokenizer

model = AutoModel.from_pretrained('openbmb/MiniCPM-V-4_5', trust_remote_code=True,
    attn_implementation='sdpa', torch_dtype=torch.bfloat16)
model = model.eval().cuda()
tokenizer = AutoTokenizer.from_pretrained('openbmb/MiniCPM-V-4_5', trust_remote_code=True)

question = "production date" 
image1 = Image.open('example1.jpg').convert('RGB')
answer1 = "2023.08.04"
image2 = Image.open('example2.jpg').convert('RGB')
answer2 = "2007.04.24"
image_test = Image.open('test.jpg').convert('RGB')

msgs = [
    {'role': 'user', 'content': [image1, question]}, {'role': 'assistant', 'content': [answer1]},
    {'role': 'user', 'content': [image2, question]}, {'role': 'assistant', 'content': [answer2]},
    {'role': 'user', 'content': [image_test, question]}
]

answer = model.chat(
    msgs=msgs,
    tokenizer=tokenizer
)
print(answer)

@misc{yu2025minicpmv45cookingefficient,
      title={MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe}, 
      author={Tianyu Yu and Zefan Wang and Chongyi Wang and Fuwei Huang and Wenshuo Ma and Zhihui He and Tianchi Cai and Weize Chen and Yuxiang Huang and Yuanqian Zhao and Bokai Xu and Junbo Cui and Yingjing Xu and Liqing Ruan and Luoyuan Zhang and Hanyu Liu and Jingkun Tang and Hongyuan Liu and Qining Guo and Wenhao Hu and Bingxiang He and Jie Zhou and Jie Cai and Ji Qi and Zonghao Guo and Chi Chen and Guoyang Zeng and Yuxuan Li and Ganqu Cui and Ning Ding and Xu Han and Yuan Yao and Zhiyuan Liu and Maosong Sun},
      year={2025},
      eprint={2509.18154},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/2509.18154}, 
}

@article{yao2024minicpm,
  title={MiniCPM-V: A GPT-4V Level MLLM on Your Phone},
  author={Yao, Yuan and Yu, Tianyu and Zhang, Ao and Wang, Chongyi and Cui, Junbo and Zhu, Hongji and Cai, Tianchi and Li, Haoyu and Zhao, Weilin and He, Zhihui and others},
  journal={Nat Commun 16, 5509 (2025)},
  year={2025}
}