app.py

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

model = AutoModel.from_pretrained('openbmb/MiniCPM-V-2_6', trust_remote_code=True,
    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-2_6', trust_remote_code=True)

image = Image.open('car.jpg').convert('RGB')
question = 'What is in the image?'
msgs = [{'role': 'user', 'content': [image, question]}]

res = model.chat(
    image=None,
    msgs=msgs,
    tokenizer=tokenizer
)
print(res)

## if you want to use streaming, please make sure sampling=True and stream=True
## the model.chat will return a generator
res = model.chat(
    image=None,
    msgs=msgs,
    tokenizer=tokenizer,
    sampling=True,
    stream=True
)

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


#import google.generativeai as genai
#import os

#genai.configure(api_key=os.environ["AIzaSyB5WiEJf_yLMD1dMQf305EAbaPTzF_QD-I"])

#model = genai.GenerativeModel('gemini-1.5-flash')
#response = model.generate_content(
#    text_input="the color of the car is ?", 
#    image_input="car.jpg"
#)
#print(response)