Instructions to use NJU-LINK/OmniCaptioner-IF-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NJU-LINK/OmniCaptioner-IF-3B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="NJU-LINK/OmniCaptioner-IF-3B")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("NJU-LINK/OmniCaptioner-IF-3B")
model = AutoModelForMultimodalLM.from_pretrained("NJU-LINK/OmniCaptioner-IF-3B")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use NJU-LINK/OmniCaptioner-IF-3B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NJU-LINK/OmniCaptioner-IF-3B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NJU-LINK/OmniCaptioner-IF-3B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/NJU-LINK/OmniCaptioner-IF-3B

SGLang

How to use NJU-LINK/OmniCaptioner-IF-3B with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "NJU-LINK/OmniCaptioner-IF-3B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NJU-LINK/OmniCaptioner-IF-3B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "NJU-LINK/OmniCaptioner-IF-3B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NJU-LINK/OmniCaptioner-IF-3B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use NJU-LINK/OmniCaptioner-IF-3B with Docker Model Runner:
```
docker model run hf.co/NJU-LINK/OmniCaptioner-IF-3B
```

OmniCaptioner-IF-3B / README.md

wang-jiahao

Update arXiv citation and resource badges

fd5935c verified about 1 month ago

preview code

Raw

History Blame Contribute Delete

3.67 kB

metadata

license: apache-2.0
library_name: transformers
pipeline_tag: image-text-to-text
tags:
  - omni-modal
  - video-captioning
  - instruction-following
  - audio-visual
  - qwen2.5-omni

OmniCaptioner-IF-3B

Quick Start

Installation

conda create -n omnicap_if python=3.12
conda activate omnicap_if
pip install torch torchvision
pip install transformers==4.57.1
pip install accelerate
pip install flash-attn --no-build-isolation
pip install qwen-omni-utils[decord] -U

Usage

import torch
from transformers import Qwen2_5OmniForConditionalGeneration, Qwen2_5OmniProcessor
from qwen_omni_utils import process_mm_info

MODEL_ID = "NJU-LINK/OmniCaptioner-IF-3B"
VIDEO_PATH = "example_video.mp4"
INSTRUCTION = (
    "Please describe this video in a Markdown table with columns "
    "'Timestamp', 'Visual Action', and 'Audio Content'. Include precise timestamps "
    "and mention the key audio-visual events."
)

MAX_PIXELS = 297920
VIDEO_MAX_PIXELS = 297920

model = Qwen2_5OmniForConditionalGeneration.from_pretrained(
    MODEL_ID,
    torch_dtype=torch.bfloat16,
    device_map="cuda",
    attn_implementation="flash_attention_2"
)
processor = Qwen2_5OmniProcessor.from_pretrained(MODEL_ID)
model.disable_talker()

conversation = [
    {
        "role": "user",
        "content": [
            {"type": "text", "text": INSTRUCTION},
            {
                "type": "video",
                "video": VIDEO_PATH,
                "max_pixels": MAX_PIXELS,
                "max_frames": 160,
                "fps": 1.0,
                "video_max_pixels": VIDEO_MAX_PIXELS
            }
        ],
    },
]

text = processor.apply_chat_template(conversation, add_generation_prompt=True, tokenize=False)
audios, images, videos = process_mm_info(conversation, use_audio_in_video=True)

inputs = processor(
    text=text,
    audio=audios,
    images=images,
    videos=videos,
    return_tensors="pt",
    padding=True,
    use_audio_in_video=True
)
inputs = inputs.to(model.device).to(model.dtype)

with torch.inference_mode():
    text_ids = model.generate(
        **inputs,
        use_audio_in_video=True,
        return_audio=False,
        thinker_max_new_tokens=1536,
        talker_max_tokens=1536
    )

response = processor.decode(text_ids[0][inputs.input_ids[0].size(0):], skip_special_tokens=True)
print(response)

Citation

@misc{wang2026omnicapifbenchmarkingimprovinginstruction,
      title={OmniCap-IF: Benchmarking and Improving Instruction Following Abilities for Omni-Video Captioning}, 
      author={Jiahao Wang and An Ping and Yanghai Wang and Yuanxing Zhang and Shihao Li and Hanyan Bian and Yichi Ren and Yize Zhang and Han Wang and Haowen Chen and Junze Li and Jiaqi Wang and Yiyang Hu and Zhuze Xu and Zijie Zhang and Jiaheng Liu},
      year={2026},
      eprint={2606.08572},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2606.08572}, 
}