Who developed Modnet and how large is it?

Modnet is developed by Xenova. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Modnet?

Modnet is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Name: Modnet
Author: Xenova

Modnet is an open-source language model by Xenova. Features: LLM, License: apache-2.0, LLM Explorer Score: 0.17.

Model Type

Image Segmentation

Use Cases

Primary Use Cases:

Portrait Matting

Additional Notes

The model is used for trimap-free portrait matting in real-time.

Input Output

Accepted Modalities:

image

LLM Name	Modnet
Repository 🤗	https://huggingface.co/Xenova/modnet
Updated	2026-07-30
Maintainer	Xenova
Model Type	modnet
Model Architecture	AutoModel
License	apache-2.0

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives	Context / RAM	Downloads	Likes
Distil Longformer Base 4096	4K / 0.4 GB	6	0
Daedalus 1	1K / GB	9	1
Opengpt2 Pytorch Backward	1K / 6 GB	325	1
Tiny Random Detr	1K / 0.2 GB	15	0
Opengpt2 Pytorch Forward	1K / 6 GB	2	1
Finsent Transformer	0.5K / 0.4 GB	1	1
Bert Chinese L 12 H 768 A 12	0.5K / 0.4 GB	9	1
Simbert Chinese Base	0.5K / 0.4 GB	11	0
Simbert Chinese Tiny	0.5K / 0 GB	9	0
Bert Tiny	0.5K / 0 GB	1360936	147