from llava.model.builder import load_pretrained_model
from llava.constants import (
    DEFAULT_IMAGE_TOKEN,
    IMAGE_TOKEN_INDEX,
)
from llava.mm_utils import (
    KeywordsStoppingCriteria,
    get_model_name_from_path,
    tokenizer_image_token,
    process_images
)
from llava.conversation import SeparatorStyle, conv_templates

overwrite_config = {}
overwrite_config["mm_spatial_pool_stride"] = 2
overwrite_config["mm_spatial_pool_mode"] = 'bilinear'
overwrite_config["mm_pooling_position"] = 'after'
overwrite_config["mm_newline_position"] = 'no_token'

model_path = "Inst-IT/LLaVA-Next-Inst-It-Vicuna-7B"
model_name = get_model_name_from_path(model_path)

tokenizer, model, image_processor, max_length = load_pretrained_model(
            model_path=model_path, 
            model_base=None, 
            model_name=model_name,
            device_map="auto", 
            torch_dtype='bfloat16', 
            overwrite_config=overwrite_config,
            attn_implementation='sdpa')

Image Inference

Inference without SoMs

Our model can perform inference on images without Set-of-Marks visual prompts, in this case, it can be used in the same way as its base mode LLaVA-NeXT.

python

import torch
import requests
from PIL import Image

img_url = "https://github.com/inst-it/inst-it/blob/main/assets/demo/image.jpg?raw=true"
image = Image.open(requests.get(img_url, stream=True).raw)
image_tensor = process_images([image], image_processor, model.config).bfloat16()
image_sizes = [image.size]

question = "Describe this image."
question = DEFAULT_IMAGE_TOKEN + "\n" + question

conv_template = 'vicuna_v1'
conv = conv_templates[conv_template].copy()
conv.append_message(conv.roles[0], question)
conv.append_message(conv.roles[1], None)
prompt = conv.get_prompt()

input_ids = tokenizer_image_token(prompt, tokenizer, IMAGE_TOKEN_INDEX, return_tensors="pt").unsqueeze(0).cuda()

pad_token_ids = tokenizer.pad_token_id if tokenizer.pad_token_id is not None else tokenizer.eos_token_id
attention_masks = input_ids.ne(pad_token_ids).long().cuda()

stop_str = conv.sep if conv.sep_style != SeparatorStyle.TWO else conv.sep2
keywords = [stop_str]
stopping_criteria = KeywordsStoppingCriteria(keywords, tokenizer, input_ids)

with torch.inference_mode():
    output_ids = model.generate(
        inputs=input_ids,
        images=image_tensor,
        attention_mask=attention_masks,
        modalities="image",
        image_sizes=image_sizes,
        use_cache=True,
        stopping_criteria=[stopping_criteria],
        max_new_tokens=4096
    )

pred = tokenizer.batch_decode(output_ids, skip_special_tokens=True)[0].strip()
print(pred)

Inference with SoMs

Our model performs more fine-grained understanding when Set-of-Marks visual prompts are provided. You can refer to the instances that you are interested in using their IDs. Compared to the previous inference code, the following code has no modifications except for the input image, which is visual prompted with Set-of-Marks. Refer to this link to learn how to generate SoMs for an image.

python

import torch
import requests
from PIL import Image

img_url = "https://github.com/inst-it/inst-it/blob/main/assets/demo/image_som.jpg?raw=true"
image = Image.open(requests.get(img_url, stream=True).raw)
image_tensor = process_images([image], image_processor, model.config).bfloat16()
image_sizes = [image.size]

# You can use [id] to refer to the instances that you are interested in
question = "Describe [8] in detail."
question = DEFAULT_IMAGE_TOKEN + "\n" + question

conv_template = 'vicuna_v1'
conv = conv_templates[conv_template].copy()
conv.append_message(conv.roles[0], question)
conv.append_message(conv.roles[1], None)
prompt = conv.get_prompt()

input_ids = tokenizer_image_token(prompt, tokenizer, IMAGE_TOKEN_INDEX, return_tensors="pt").unsqueeze(0).cuda()

pad_token_ids = tokenizer.pad_token_id if tokenizer.pad_token_id is not None else tokenizer.eos_token_id
attention_masks = input_ids.ne(pad_token_ids).long().cuda()

stop_str = conv.sep if conv.sep_style != SeparatorStyle.TWO else conv.sep2
keywords = [stop_str]
stopping_criteria = KeywordsStoppingCriteria(keywords, tokenizer, input_ids)

with torch.inference_mode():
    output_ids = model.generate(
        inputs=input_ids,
        images=image_tensor,
        attention_mask=attention_masks,
        modalities="image",
        image_sizes=image_sizes,
        use_cache=True,
        stopping_criteria=[stopping_criteria],
        max_new_tokens=4096
    )

pred = tokenizer.batch_decode(output_ids, skip_special_tokens=True)[0].strip()
print(pred)

Video Inference

For the video, we organize each frame into a list. You can use the format <t> to refer to a specific timestamp (e.g. <1>).

Inference without SoMs

Our model can perform inference on videos without Set-of-Marks visual prompts, in this case, it can be used in the same way as its base mode LLaVA-NeXT.

python

import torch
import requests
from PIL import Image

frame_urls = [
    "https://github.com/inst-it/inst-it/blob/main/assets/demo/frame_1.jpg?raw=true",
    "https://github.com/inst-it/inst-it/blob/main/assets/demo/frame_2.jpg?raw=true",
    "https://github.com/inst-it/inst-it/blob/main/assets/demo/frame_3.jpg?raw=true",
    "https://github.com/inst-it/inst-it/blob/main/assets/demo/frame_4.jpg?raw=true",
    "https://github.com/inst-it/inst-it/blob/main/assets/demo/frame_5.jpg?raw=true",
    "https://github.com/inst-it/inst-it/blob/main/assets/demo/frame_6.jpg?raw=true",
    "https://github.com/inst-it/inst-it/blob/main/assets/demo/frame_7.jpg?raw=true",
    "https://github.com/inst-it/inst-it/blob/main/assets/demo/frame_8.jpg?raw=true"
]
video = [Image.open(requests.get(frame_url, stream=True).raw) for frame_url in frame_urls]
video = image_processor.preprocess(video, return_tensors="pt")["pixel_values"].cuda()
video = video.bfloat16()
videos = [video]

question = "Describe the video."  # overall video caption
question = "What happens at frame <1>?"  # caption a specific moment
question = DEFAULT_IMAGE_TOKEN + "\n" + question

conv_template = 'vicuna_v1'
conv = conv_templates[conv_template].copy()
conv.append_message(conv.roles[0], question)
conv.append_message(conv.roles[1], None)
prompt = conv.get_prompt()

input_ids = tokenizer_image_token(prompt, tokenizer, IMAGE_TOKEN_INDEX, return_tensors="pt").unsqueeze(0).cuda()

pad_token_ids = tokenizer.pad_token_id if tokenizer.pad_token_id is not None else tokenizer.eos_token_id
attention_masks = input_ids.ne(pad_token_ids).long().cuda()

stop_str = conv.sep if conv.sep_style != SeparatorStyle.TWO else conv.sep2
keywords = [stop_str]
stopping_criteria = KeywordsStoppingCriteria(keywords, tokenizer, input_ids)

with torch.inference_mode():
    output_ids = model.generate(
        inputs=input_ids,
        images=videos,
        attention_mask=attention_masks,
        modalities="video",
        use_cache=True,
        stopping_criteria=[stopping_criteria],
        max_new_tokens=4096
    )

pred = tokenizer.batch_decode(output_ids, skip_special_tokens=True)[0].strip()
print(pred)

Inference with SoMs

Our model performs more fine-grained understanding when Set-of-Marks visual prompts are provided. You can refer to the instances that you are interested in using their IDs. Compared to the previous inference code, the following code has no modifications except for the input video, which is visual prompted with Set-of-Marks. Refer to SAM2 and SoM to learn how to generate SoMs for a video.

python

import torch
import requests
from PIL import Image

frame_urls = [
    "https://github.com/inst-it/inst-it/blob/main/assets/demo/som_frame_1.jpg?raw=true",
    "https://github.com/inst-it/inst-it/blob/main/assets/demo/som_frame_2.jpg?raw=true",
    "https://github.com/inst-it/inst-it/blob/main/assets/demo/som_frame_3.jpg?raw=true",
    "https://github.com/inst-it/inst-it/blob/main/assets/demo/som_frame_4.jpg?raw=true",
    "https://github.com/inst-it/inst-it/blob/main/assets/demo/som_frame_5.jpg?raw=true",
    "https://github.com/inst-it/inst-it/blob/main/assets/demo/som_frame_6.jpg?raw=true",
    "https://github.com/inst-it/inst-it/blob/main/assets/demo/som_frame_7.jpg?raw=true",
    "https://github.com/inst-it/inst-it/blob/main/assets/demo/som_frame_8.jpg?raw=true"
]
video = [Image.open(requests.get(frame_url, stream=True).raw) for frame_url in frame_urls]
video = image_processor.preprocess(video, return_tensors="pt")["pixel_values"].cuda()
video = video.bfloat16()
videos = [video]

# You can use [id] to refer to the instances that you are interested in
question = "Is [3] visible at <1>?"
question = DEFAULT_IMAGE_TOKEN + "\n" + question

conv_template = 'vicuna_v1'
conv = conv_templates[conv_template].copy()
conv.append_message(conv.roles[0], question)
conv.append_message(conv.roles[1], None)
prompt = conv.get_prompt()

input_ids = tokenizer_image_token(prompt, tokenizer, IMAGE_TOKEN_INDEX, return_tensors="pt").unsqueeze(0).cuda()

pad_token_ids = tokenizer.pad_token_id if tokenizer.pad_token_id is not None else tokenizer.eos_token_id
attention_masks = input_ids.ne(pad_token_ids).long().cuda()

stop_str = conv.sep if conv.sep_style != SeparatorStyle.TWO else conv.sep2
keywords = [stop_str]
stopping_criteria = KeywordsStoppingCriteria(keywords, tokenizer, input_ids)

with torch.inference_mode():
    output_ids = model.generate(
        inputs=input_ids,
        images=videos,
        attention_mask=attention_masks,
        modalities="video",
        use_cache=True,
        stopping_criteria=[stopping_criteria],
        max_new_tokens=4096
    )

pred = tokenizer.batch_decode(output_ids, skip_special_tokens=True)[0].strip()
print(pred)

Contact

Feel free to contact us if you have any questions or suggestions

Email (Wujian Peng): wjpeng24@m.fudan.edu.cn
Email (Lingchen Meng): lcmeng20@fudan.edu.cn

Citation

bibtex

@article{peng2024inst,
  title={Inst-IT: Boosting Multimodal Instance Understanding via Explicit Visual Prompt Instruction Tuning},
  author={Peng, Wujian and Meng, Lingchen and Chen, Yitong and Xie, Yiweng and Liu, Yang and Gui, Tao and Xu, Hang and Qiu, Xipeng and Wu, Zuxuan and Jiang, Yu-Gang},
  journal={arXiv preprint arXiv:2412.03565},
  year={2024}
}