From the model card
Fields below are copied from the tags and counters on the HuggingFace repository Freepik/nsfw_image_detector at our last fetch. They are set by the uploader, not verified by us; rows with no tag are omitted. How this page is made.
- Publisher (HF namespace)
- Freepik
- Pipeline tag
- image-classification
- Library
- Transformers
- Framework tags
- PyTorch
- Weight formats
- safetensors
- License tag
mit— read the license file in the repo before relying on it- Lineage
- Papers cited
- arXiv:2303.11331
- Downloads (HF counter at last fetch)
- 398,274
- Likes (HF counter at last fetch)
- 61
- Model card
- https://huggingface.co/Freepik/nsfw_image_detector
Use cases
- Content moderation pipeline for user-generated images
- Automated NSFW filtering before image generation output
- Platform safety enforcement for image uploads
- Research into image safety classifier behavior and failure modes
Pros
- MIT license — commercial integration permitted
- Training source (Freepik) suggests large, production-quality labeled dataset
- Transformers-compatible image classification pipeline
- Maintained by an organization with real-world moderation use case
Cons
- Binary/multi-class NSFW detection has high false-positive rates on artistic nudity vs explicit content
- not-for-all-audiences tag indicates model card restriction for minors
- No published precision/recall figures for specific NSFW categories
- timm_wrapper requires timm library — additional dependency
Tags
transformerssafetensorstimm_wrapperimage-classificationpytorcharxiv:2303.11331base_model:timm/eva02_base_patch14_448.mim_in22k_ft_in22k_in1kbase_model:finetune:timm/eva02_base_patch14_448.mim_in22k_ft_in22k_in1klicense:mitendpoints_compatibleregion:usnot-for-all-audiencesdeploy:azure