InternVL Family: Closing the Gap to Commercial Multimodal Models with Open-Source Suites —— A Pioneering Open-Source Alternative to GPT-4V

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

model = AutoModel.from_pretrained(
    'OpenGVLab/InternViT-6B-224px',
    torch_dtype=torch.bfloat16,
    low_cpu_mem_usage=True,
    trust_remote_code=True).cuda().eval()

image = Image.open('./examples/image1.jpg').convert('RGB')

image_processor = CLIPImageProcessor.from_pretrained('OpenGVLab/InternViT-6B-224px')

pixel_values = image_processor(images=image, return_tensors='pt').pixel_values
pixel_values = pixel_values.to(torch.bfloat16).cuda()

outputs = model(pixel_values)

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


model = AutoModel.from_pretrained(
    'OpenGVLab/InternVL-14B-224px',
    torch_dtype=torch.bfloat16,
    low_cpu_mem_usage=True,
    trust_remote_code=True).cuda().eval()

image_processor = CLIPImageProcessor.from_pretrained('OpenGVLab/InternVL-14B-224px')

tokenizer = AutoTokenizer.from_pretrained(
    'OpenGVLab/InternVL-14B-224px', use_fast=False, add_eos_token=True)
tokenizer.pad_token_id = 0  # set pad_token_id to 0

images = [
    Image.open('./examples/image1.jpg').convert('RGB'),
    Image.open('./examples/image2.jpg').convert('RGB'),
    Image.open('./examples/image3.jpg').convert('RGB')
]
prefix = 'summarize:'
texts = [
    prefix + 'a photo of a red panda',  # English
    prefix + '一张熊猫的照片',  # Chinese
    prefix + '二匹の猫の写真'  # Japanese
]

pixel_values = image_processor(images=images, return_tensors='pt').pixel_values
pixel_values = pixel_values.to(torch.bfloat16).cuda()
input_ids = tokenizer(texts, return_tensors='pt', max_length=80,
                      truncation=True, padding='max_length').input_ids.cuda()

# InternVL-C
logits_per_image, logits_per_text = model(
    image=pixel_values, text=input_ids, mode='InternVL-C')
probs = logits_per_image.softmax(dim=-1)
# tensor([[9.9609e-01, 5.2185e-03, 6.0070e-08],
#         [2.2949e-02, 9.7656e-01, 5.9903e-06],
#         [3.2932e-06, 7.4863e-05, 1.0000e+00]], device='cuda:0',
#        dtype=torch.bfloat16, grad_fn=<SoftmaxBackward0>)

# InternVL-G
logits_per_image, logits_per_text = model(
    image=pixel_values, text=input_ids, mode='InternVL-G')
probs = logits_per_image.softmax(dim=-1)
# tensor([[9.9609e-01, 3.1738e-03, 3.6322e-08],
#         [8.6060e-03, 9.9219e-01, 2.8759e-06],
#         [1.7583e-06, 3.1233e-05, 1.0000e+00]], device='cuda:0',
#        dtype=torch.bfloat16, grad_fn=<SoftmaxBackward0>)

# please set add_eos_token to False for generation
tokenizer.add_eos_token = False
image = Image.open('./examples/image1.jpg').convert('RGB')
pixel_values = image_processor(images=image, return_tensors='pt').pixel_values
pixel_values = pixel_values.to(torch.bfloat16).cuda()

tokenized = tokenizer("English caption:", return_tensors='pt')
pred = model.generate(
    pixel_values=pixel_values,
    input_ids=tokenized.input_ids.cuda(),
    attention_mask=tokenized.attention_mask.cuda(),
    num_beams=5,
    min_new_tokens=8,
)
caption = tokenizer.decode(pred[0].cpu(), skip_special_tokens=True).strip()
# English caption: a red panda sitting on top of a wooden platform

from transformers import AutoTokenizer, AutoModel
import torch
import torchvision.transforms as T
from PIL import Image

from torchvision.transforms.functional import InterpolationMode


IMAGENET_MEAN = (0.485, 0.456, 0.406)
IMAGENET_STD = (0.229, 0.224, 0.225)


def build_transform(input_size):
    MEAN, STD = IMAGENET_MEAN, IMAGENET_STD
    transform = T.Compose([
        T.Lambda(lambda img: img.convert('RGB') if img.mode != 'RGB' else img),
        T.Resize((input_size, input_size), interpolation=InterpolationMode.BICUBIC),
        T.ToTensor(),
        T.Normalize(mean=MEAN, std=STD)
    ])
    return transform


def find_closest_aspect_ratio(aspect_ratio, target_ratios, width, height, image_size):
    best_ratio_diff = float('inf')
    best_ratio = (1, 1)
    area = width * height
    for ratio in target_ratios:
        target_aspect_ratio = ratio[0] / ratio[1]
        ratio_diff = abs(aspect_ratio - target_aspect_ratio)
        if ratio_diff < best_ratio_diff:
            best_ratio_diff = ratio_diff
            best_ratio = ratio
        elif ratio_diff == best_ratio_diff:
            if area > 0.5 * image_size * image_size * ratio[0] * ratio[1]:
                best_ratio = ratio
    return best_ratio


def dynamic_preprocess(image, min_num=1, max_num=6, image_size=448, use_thumbnail=False):
    orig_width, orig_height = image.size
    aspect_ratio = orig_width / orig_height

    # calculate the existing image aspect ratio
    target_ratios = set(
        (i, j) for n in range(min_num, max_num + 1) for i in range(1, n + 1) for j in range(1, n + 1) if
        i * j <= max_num and i * j >= min_num)
    target_ratios = sorted(target_ratios, key=lambda x: x[0] * x[1])

    # find the closest aspect ratio to the target
    target_aspect_ratio = find_closest_aspect_ratio(
        aspect_ratio, target_ratios, orig_width, orig_height, image_size)

    # calculate the target width and height
    target_width = image_size * target_aspect_ratio[0]
    target_height = image_size * target_aspect_ratio[1]
    blocks = target_aspect_ratio[0] * target_aspect_ratio[1]

    # resize the image
    resized_img = image.resize((target_width, target_height))
    processed_images = []
    for i in range(blocks):
        box = (
            (i % (target_width // image_size)) * image_size,
            (i // (target_width // image_size)) * image_size,
            ((i % (target_width // image_size)) + 1) * image_size,
            ((i // (target_width // image_size)) + 1) * image_size
        )
        # split the image
        split_img = resized_img.crop(box)
        processed_images.append(split_img)
    assert len(processed_images) == blocks
    if use_thumbnail and len(processed_images) != 1:
        thumbnail_img = image.resize((image_size, image_size))
        processed_images.append(thumbnail_img)
    return processed_images


def load_image(image_file, input_size=448, max_num=6):
    image = Image.open(image_file).convert('RGB')
    transform = build_transform(input_size=input_size)
    images = dynamic_preprocess(image, image_size=input_size, use_thumbnail=True, max_num=max_num)
    pixel_values = [transform(image) for image in images]
    pixel_values = torch.stack(pixel_values)
    return pixel_values


path = "OpenGVLab/InternVL-Chat-V1-5"
# If you have an 80G A100 GPU, you can put the entire model on a single GPU.
model = AutoModel.from_pretrained(
    path,
    torch_dtype=torch.bfloat16,
    low_cpu_mem_usage=True,
    trust_remote_code=True).eval().cuda()
# Otherwise, you need to set device_map='auto' to use multiple GPUs for inference.
# model = AutoModel.from_pretrained(
#     path,
#     torch_dtype=torch.bfloat16,
#     low_cpu_mem_usage=True,
#     trust_remote_code=True,
#     device_map='auto').eval()

tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True)
# set the max number of tiles in `max_num`
pixel_values = load_image('./examples/image1.jpg', max_num=6).to(torch.bfloat16).cuda()

generation_config = dict(
    num_beams=1,
    max_new_tokens=512,
    do_sample=False,
)

# single-round single-image conversation
question = "请详细描述图片" # Please describe the picture in detail
response = model.chat(tokenizer, pixel_values, question, generation_config)
print(question, response)

# multi-round single-image conversation
question = "请详细描述图片" # Please describe the picture in detail
response, history = model.chat(tokenizer, pixel_values, question, generation_config, history=None, return_history=True)
print(question, response)

question = "请根据图片写一首诗" # Please write a poem according to the picture
response, history = model.chat(tokenizer, pixel_values, question, generation_config, history=history, return_history=True)
print(question, response)

# multi-round multi-image conversation
pixel_values1 = load_image('./examples/image1.jpg', max_num=6).to(torch.bfloat16).cuda()
pixel_values2 = load_image('./examples/image2.jpg', max_num=6).to(torch.bfloat16).cuda()
pixel_values = torch.cat((pixel_values1, pixel_values2), dim=0)

question = "详细描述这两张图片" # Describe the two pictures in detail
response, history = model.chat(tokenizer, pixel_values, question, generation_config, history=None, return_history=True)
print(question, response)

question = "这两张图片的相同点和区别分别是什么" # What are the similarities and differences between these two pictures
response, history = model.chat(tokenizer, pixel_values, question, generation_config, history=history, return_history=True)
print(question, response)

# batch inference (single image per sample)
pixel_values1 = load_image('./examples/image1.jpg', max_num=6).to(torch.bfloat16).cuda()
pixel_values2 = load_image('./examples/image2.jpg', max_num=6).to(torch.bfloat16).cuda()
image_counts = [pixel_values1.size(0), pixel_values2.size(0)]
pixel_values = torch.cat((pixel_values1, pixel_values2), dim=0)

questions = ["Describe the image in detail."] * len(image_counts)
responses = model.batch_chat(tokenizer, pixel_values,
                             image_counts=image_counts,
                             questions=questions,
                             generation_config=generation_config)
for question, response in zip(questions, responses):
    print(question)
    print(response)