• Linear-Probe Image Classification [see details]

  ViT-22B uses the private JFT-3B dataset.

  method	#param	IN-1K	IN-ReaL	IN-V2	IN-A	IN-R	IN-Sketch
  OpenCLIP-G	1.8B	86.2	89.4	77.2	63.8	87.8	66.4
  DINOv2-g	1.1B	86.5	89.6	78.4	75.9	78.8	62.5
  EVA-01-CLIP-g	1.1B	86.5	89.3	77.4	70.5	87.7	63.1
  MAWS-ViT-6.5B	6.5B	87.8	-	-	-	-	-
  ViT-22B*	21.7B	89.5	90.9	83.2	83.8	87.4	-
  InternViT-6B (ours)	5.9B	88.2	90.4	79.9	77.5	89.8	69.1

• Semantic Segmentation [see details]

  method	decoder	#param (train/total)	crop size	mIoU
  OpenCLIP-G (frozen)	Linear	0.3M / 1.8B	512	39.3
  ViT-22B (frozen)	Linear	0.9M / 21.7B	504	34.6
  InternViT-6B (frozen)	Linear	0.5M / 5.9B	504	47.2 (+12.6)
  ViT-22B (frozen)	UperNet	0.8B / 22.5B	504	52.7
  InternViT-6B (frozen)	UperNet	0.4B / 6.3B	504	54.9 (+2.2)
  ViT-22B	UperNet	22.5B / 22.5B	504	55.3
  InternViT-6B	UperNet	6.3B / 6.3B	504	58.9 (+3.6)

• Zero-Shot Image Classification [see details]

  method	IN-1K	IN-A	IN-R	IN-V2	IN-Sketch	ObjectNet
  OpenCLIP-G	80.1	69.3	92.1	73.6	68.9	73.0
  EVA-02-CLIP-E+	82.0	82.1	94.5	75.7	71.6	79.6
  ViT-22B*	85.9	90.1	96.0	80.9	-	87.6
  InternVL-C (ours)	83.2	83.8	95.5	77.3	73.9	80.6

• Multilingual Zero-Shot Image Classification [see details]

  EN: English, ZH: Chinese, JP: Japanese, Ar: Arabic, IT: Italian

  method	IN-1K (EN)	IN-1K (ZH)	IN-1K (JP)	IN-1K (AR)	IN-1K (IT)
  Taiyi-CLIP-ViT-H	-	54.4	-	-	-
  WuKong-ViT-L-G	-	57.5	-	-	-
  CN-CLIP-ViT-H	-	59.6	-	-	-
  AltCLIP-ViT-L	74.5	59.6	-	-	-
  EVA-02-CLIP-E+	82.0	-	-	-	41.2
  OpenCLIP-XLM-R-H	77.0	55.7	53.1	37.0	56.8
  InternVL-C (ours)	83.2	64.5	61.5	44.9	65.7

• Zero-Shot Video Classification

  method	#frame	K400	K600	K700
  OpenCLIP-G	1	65.9	66.1	59.2
  EVA-02-CLIP-E+	1	69.8	69.3	63.4
  InternVL-C (ours)	1	71.0	71.3	65.7
  ViCLIP	8	75.7	73.5	66.4
  InternVL-C (ours)	8	79.4	78.8	71.5

• English Zero-Shot Image-Text Retrieval [see details]

  model	Flickr30K						COCO						avg
  	image-to-text			text-to-image			image-to-text			text-to-image
  	R@1	R@5	R@10	R@1	R@5	R@10	R@1	R@5	R@10	R@1	R@5	R@10
  OpenCLIP-G	92.9	99.3	99.8	79.5	95.0	97.1	67.3	86.9	92.6	51.4	74.9	83.0	85.0
  EVA-02-CLIP-E+	93.9	99.4	99.8	78.8	94.2	96.8	68.8	87.8	92.8	51.1	75.0	82.7	85.1
  EVA-CLIP-8B	95.6	99.6	99.9	80.8	95.5	97.6	70.3	89.3	93.9	53.0	76.0	83.4	86.2
  InternVL-C (ours)	94.7	99.6	99.9	81.7	96.0	98.2	70.6	89.0	93.5	54.1	77.3	84.6	86.6
  InternVL-G (ours)	95.7	99.7	99.9	85.0	97.0	98.6	74.9	91.3	95.2	58.6	81.3	88.0	88.8

• Chinese Zero-Shot Image-Text Retrieval [see details]

  model	Flickr30K-CN						COCO-CN						avg
  	image-to-text			text-to-image			image-to-text			text-to-image
  	R@1	R@5	R@10	R@1	R@5	R@10	R@1	R@5	R@10	R@1	R@5	R@10
  CN-CLIP-ViT-H	81.6	97.5	98.8	71.2	91.4	95.5	63.0	86.6	92.9	69.2	89.9	96.1	86.1
  OpenCLIP-XLM-R-H	86.1	97.5	99.2	71.0	90.5	94.9	70.0	91.5	97.0	66.1	90.8	96.0	87.6
  InternVL-C (ours)	90.3	98.8	99.7	75.1	92.9	96.4	68.8	92.0	96.7	68.9	91.9	96.5	89.0
  InternVL-G (ours)	92.9	99.4	99.8	77.7	94.8	97.3	71.4	93.9	97.7	73.8	94.4	98.1	90.9

• Multilingual Zero-Shot Image-Text Retrieval on XTD [see details]

  method	EN	ES	FR	ZH	IT	KO	RU	JP	average
  AltCLIP	95.4	94.1	92.9	95.1	94.2	94.4	91.8	91.7	93.7
  OpenCLIP-XLM-R-H	97.3	96.1	94.5	94.7	96.0	90.2	93.9	94.0	94.6
  InternVL-C (ours)	97.3	95.7	95.1	95.6	96.0	92.2	93.3	95.5	95.1
  InternVL-G (ours)	98.6	97.7	96.5	96.7	96.9	95.1	94.8	96.1	96.6

See "Compared with SOTA VLLMs" section.

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

model = AutoModel.from_pretrained(
    'OpenGVLab/InternViT-6B-448px-V1-5',
    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-448px-V1-5')

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

Here, we take the smaller OpenGVLab/InternVL2-8B as an example:

import numpy as np
import torch
import torchvision.transforms as T
from decord import VideoReader, cpu
from PIL import Image
from torchvision.transforms.functional import InterpolationMode
from transformers import AutoModel, AutoTokenizer

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=12, 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=12):
    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

# If you have an 80G A100 GPU, you can put the entire model on a single GPU.
# Otherwise, you need to load a model using multiple GPUs, please refer to the `Multiple GPUs` section.
path = 'OpenGVLab/InternVL2-8B'
model = AutoModel.from_pretrained(
    path,
    torch_dtype=torch.bfloat16,
    low_cpu_mem_usage=True,
    trust_remote_code=True).eval().cuda()
tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True, use_fast=False)

# set the max number of tiles in `max_num`
pixel_values = load_image('./examples/image1.jpg', max_num=12).to(torch.bfloat16).cuda()
generation_config = dict(max_new_tokens=1024, do_sample=False)

# pure-text conversation (纯文本对话)
question = 'Hello, who are you?'
response, history = model.chat(tokenizer, None, question, generation_config, history=None, return_history=True)
print(f'User: {question}\nAssistant: {response}')

question = 'Can you tell me a story?'
response, history = model.chat(tokenizer, None, question, generation_config, history=history, return_history=True)
print(f'User: {question}\nAssistant: {response}')

# single-image single-round conversation (单图单轮对话)
question = '<image>\nPlease describe the image shortly.'
response = model.chat(tokenizer, pixel_values, question, generation_config)
print(f'User: {question}\nAssistant: {response}')

# single-image multi-round conversation (单图多轮对话)
question = '<image>\nPlease describe the image in detail.'
response, history = model.chat(tokenizer, pixel_values, question, generation_config, history=None, return_history=True)
print(f'User: {question}\nAssistant: {response}')

question = 'Please write a poem according to the image.'
response, history = model.chat(tokenizer, pixel_values, question, generation_config, history=history, return_history=True)
print(f'User: {question}\nAssistant: {response}')

# multi-image multi-round conversation, combined images (多图多轮对话，拼接图像)
pixel_values1 = load_image('./examples/image1.jpg', max_num=12).to(torch.bfloat16).cuda()
pixel_values2 = load_image('./examples/image2.jpg', max_num=12).to(torch.bfloat16).cuda()
pixel_values = torch.cat((pixel_values1, pixel_values2), dim=0)

question = '<image>\nDescribe the two images in detail.'
response, history = model.chat(tokenizer, pixel_values, question, generation_config,
                               history=None, return_history=True)
print(f'User: {question}\nAssistant: {response}')

question = 'What are the similarities and differences between these two images.'
response, history = model.chat(tokenizer, pixel_values, question, generation_config,
                               history=history, return_history=True)
print(f'User: {question}\nAssistant: {response}')

# multi-image multi-round conversation, separate images (多图多轮对话，独立图像)
pixel_values1 = load_image('./examples/image1.jpg', max_num=12).to(torch.bfloat16).cuda()
pixel_values2 = load_image('./examples/image2.jpg', max_num=12).to(torch.bfloat16).cuda()
pixel_values = torch.cat((pixel_values1, pixel_values2), dim=0)
num_patches_list = [pixel_values1.size(0), pixel_values2.size(0)]

question = 'Image-1: <image>\nImage-2: <image>\nDescribe the two images in detail.'
response, history = model.chat(tokenizer, pixel_values, question, generation_config,
                               num_patches_list=num_patches_list,
                               history=None, return_history=True)
print(f'User: {question}\nAssistant: {response}')

question = 'What are the similarities and differences between these two images.'
response, history = model.chat(tokenizer, pixel_values, question, generation_config,
                               num_patches_list=num_patches_list,
                               history=history, return_history=True)
print(f'User: {question}\nAssistant: {response}')

# batch inference, single image per sample (单图批处理)
pixel_values1 = load_image('./examples/image1.jpg', max_num=12).to(torch.bfloat16).cuda()
pixel_values2 = load_image('./examples/image2.jpg', max_num=12).to(torch.bfloat16).cuda()
num_patches_list = [pixel_values1.size(0), pixel_values2.size(0)]
pixel_values = torch.cat((pixel_values1, pixel_values2), dim=0)

questions = ['<image>\nDescribe the image in detail.'] * len(num_patches_list)
responses = model.batch_chat(tokenizer, pixel_values,
                             num_patches_list=num_patches_list,
                             questions=questions,
                             generation_config=generation_config)
for question, response in zip(questions, responses):
    print(f'User: {question}\nAssistant: {response}')

# video multi-round conversation (视频多轮对话)
def get_index(bound, fps, max_frame, first_idx=0, num_segments=32):
    if bound:
        start, end = bound[0], bound[1]
    else:
        start, end = -100000, 100000
    start_idx = max(first_idx, round(start * fps))
    end_idx = min(round(end * fps), max_frame)
    seg_size = float(end_idx - start_idx) / num_segments
    frame_indices = np.array([
        int(start_idx + (seg_size / 2) + np.round(seg_size * idx))
        for idx in range(num_segments)
    ])
    return frame_indices

def load_video(video_path, bound=None, input_size=448, max_num=1, num_segments=32):
    vr = VideoReader(video_path, ctx=cpu(0), num_threads=1)
    max_frame = len(vr) - 1
    fps = float(vr.get_avg_fps())

    pixel_values_list, num_patches_list = [], []
    transform = build_transform(input_size=input_size)
    frame_indices = get_index(bound, fps, max_frame, first_idx=0, num_segments=num_segments)
    for frame_index in frame_indices:
        img = Image.fromarray(vr[frame_index].asnumpy()).convert('RGB')
        img = dynamic_preprocess(img, image_size=input_size, use_thumbnail=True, max_num=max_num)
        pixel_values = [transform(tile) for tile in img]
        pixel_values = torch.stack(pixel_values)
        num_patches_list.append(pixel_values.shape[0])
        pixel_values_list.append(pixel_values)
    pixel_values = torch.cat(pixel_values_list)
    return pixel_values, num_patches_list

video_path = './examples/red-panda.mp4'
pixel_values, num_patches_list = load_video(video_path, num_segments=8, max_num=1)
pixel_values = pixel_values.to(torch.bfloat16).cuda()
video_prefix = ''.join([f'Frame{i+1}: <image>\n' for i in range(len(num_patches_list))])
question = video_prefix + 'What is the red panda doing?'
# Frame1: <image>\nFrame2: <image>\n...\nFrame8: <image>\n{question}
response, history = model.chat(tokenizer, pixel_values, question, generation_config,
                               num_patches_list=num_patches_list, history=None, return_history=True)
print(f'User: {question}\nAssistant: {response}')

question = 'Describe this video in detail. Don\'t repeat.'
response, history = model.chat(tokenizer, pixel_values, question, generation_config,
                               num_patches_list=num_patches_list, history=history, return_history=True)
print(f'User: {question}\nAssistant: {response}')