HomeModelsImage Segmentationcocktailpeanut/rm
R

cocktailpeanut/rm

Image Segmentation·cocktailpeanut· 7.2K
transformers other Image Segmentation 220.7M params

RMBG v2.0 is our new state-of-the-art background removal model significantly improves RMBG v1.4. The model is designed to effectively separate foreground from background in a range of categories and image types. This model has been trained on a carefully selected dataset, which includes: general stock images, e-commerce, gaming, and advertising content, making it suitable for commercial use case

Open in MLForge Sign up free Desktop app Source ↗
# pull & run locally
pip install mlforge-sdk && mlforge pull cocktailpeanut/rm

Model details

Task
Image Segmentation
Provider
cocktailpeanut
Framework
transformers
Parameters
220.7M
Size
4.7 GB
License
other
Downloads
7.2K
Updated
2025-04-12

About cocktailpeanut/rm

RMBG v2.0 is our new state-of-the-art background removal model significantly improves RMBG v1.4. The model is designed to effectively separate foreground from background in a range of categories and image types. This model has been trained on a carefully selected dataset, which includes: general stock images, e-commerce, gaming, and advertising content, making it suitable for commercial use cases powering enterprise content creation at scale. The accuracy, efficiency, and versatility currently rival leading source-available models. It is ideal where content safety, legally licensed datasets, and bias mitigation are paramount.

Related Image Segmentation

C CIDAS/clipseg-rd64-refined Image Segmentation ·150.7M params 1.3M 140 🤗 HF B ZhengPeng7/BiRefNet Image Segmentation ·220.7M params 713.5K 602 🤗 HF M facebook/mask2former-swin-large-ade-semantic Image Segmentation ·216.0M params 645.3K 21 🤗 HF S nvidia/segformer-b0-finetuned-ade-512-512 Image Segmentation ·3.8M params 321.1K 190 🤗 HF R briaai/RMBG-1.4 Image Segmentation ·44.1M params 309.5K 2.0K 🤗 HF S nvidia/segformer-b2-finetuned-ade-512-512 Image Segmentation 213.6K 7 🤗 HF

Browse all Image Segmentation models →