Instructions to use ClareNie/Light-Omni with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ClareNie/Light-Omni with Transformers:

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

pipe = pipeline("image-text-to-text", model="ClareNie/Light-Omni")
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("ClareNie/Light-Omni")
model = AutoModelForMultimodalLM.from_pretrained("ClareNie/Light-Omni")
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 ClareNie/Light-Omni with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ClareNie/Light-Omni"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ClareNie/Light-Omni",
		"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/ClareNie/Light-Omni

SGLang

How to use ClareNie/Light-Omni 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 "ClareNie/Light-Omni" \
    --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": "ClareNie/Light-Omni",
		"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 "ClareNie/Light-Omni" \
        --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": "ClareNie/Light-Omni",
		"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 ClareNie/Light-Omni with Docker Model Runner:
```
docker model run hf.co/ClareNie/Light-Omni
```

Light-Omni

Light-Omni is a multimodal agent framework for reflexive video understanding with long-term memory. It replaces costly detective-style iterative reasoning with dual contextual states: a compact global state consolidated from episodic memory, and a latent state that drives action control and semantically aligned retrieval.

This repository hosts the Light-Omni model checkpoint for inference. It contains the safetensors weight shards, tokenizer files, model configuration, and multimodal preprocessor configuration files.

Citation

@misc{nie2026lightomni,
  title={Light-Omni: Reflex over Reasoning in Agentic Video Understanding with Long-Term Memory},
  author={Nie, Chang and Wei, Jiaju and Feng, Junlan and Fu, Chaoyou and Shan,
  Caifeng},
  year={2026},
  eprint={2607.05511},
  archivePrefix={arXiv},
  primaryClass={cs.CV},
  url={http://arxiv.org/abs/2607.05511}
}

Downloads last month: 84

Safetensors

Model size

12B params

Tensor type

BF16

Space using ClareNie/Light-Omni 1

Paper for ClareNie/Light-Omni

Light-Omni: Reflex over Reasoning in Agentic Video Understanding with Long-Term Memory

Paper • 2607.05511 • Published 14 days ago • 23

ClareNie
/

Light-Omni

Light-Omni

Links

Citation

Space using ClareNie/Light-Omni 1

Paper for ClareNie/Light-Omni

Light-Omni: Reflex over Reasoning in Agentic Video Understanding with Long-Term Memory