Single-file model formats for the SeC (Segment Concept) video object segmentation model, optimized for use with ComfyUI SeC Nodes.

Format	Size	Description	GPU Requirements
SeC-4B-fp16.safetensors	7.35 GB	Recommended - Best balance of quality and size	All CUDA GPUs
SeC-4B-fp8.safetensors	3.97 GB	VRAM-constrained systems (saves 1.5-2GB VRAM)	RTX 30 series or newer
SeC-4B-bf16.safetensors	7.35 GB	Alternative to FP16	All CUDA GPUs
SeC-4B-fp32.safetensors	14.14 GB	Full precision	All CUDA GPUs

SeC (Segment Concept) uses Large Vision-Language Models for video object segmentation, achieving +11.8 points improvement over SAM 2.1 on complex semantic scenarios (SeCVOS benchmark).

Key features:

• Concept-driven tracking with semantic understanding
• Handles occlusions and appearance changes
• Bidirectional tracking support
• State-of-the-art performance on multiple benchmarks

These models are designed for use with the ComfyUI SeC Nodes custom nodes.

Installation:

1. Download your preferred model format
2. Place in ComfyUI/models/sams/
3. Install ComfyUI SeC Nodes
4. The model will be automatically detected and available in the SeC Model Loader

These are converted single-file versions of the original model:

• Original Repository: OpenIXCLab/SeC-4B
• Paper: arXiv:2507.15852
• Official Implementation: github.com/OpenIXCLab/SeC

Original Model: Developed by OpenIXCLab

• Model architecture and weights: Apache 2.0 License
• Paper: Zhang et al. "SeC: Advancing Complex Video Object Segmentation via Progressive Concept Construction"

Single-File Conversions: Created for ComfyUI SeC Nodes

• Conversion script and ComfyUI integration: 9nate-drake
• FP8 quantization support via torchao

Apache 2.0 (same as original SeC-4B model)

If you use this model in your research, please cite the original SeC paper:

@article{zhang2025sec,
  title     = {SeC: Advancing Complex Video Object Segmentation via Progressive Concept Construction},
  author    = {Zhixiong Zhang and Shuangrui Ding and Xiaoyi Dong and Songxin He and
               Jianfan Lin and Junsong Tang and Yuhang Zang and Yuhang Cao and
               Dahua Lin and Jiaqi Wang},
  journal   = {arXiv preprint arXiv:2507.15852},
  year      = {2025}
}