Sapiens Pretrain 0.6b

🚀 Pretrain-Sapiens-0.6B

Sapiens is a vision transformer family pretrained on 300 million high - resolution human images, offering strong generalization for human - centric vision tasks.

🚀 Quick Start

The pretrained 0.6B model can be used for feature extraction, fine - tuning, or as a starting point for training new models.

✨ Features

• Sapiens is a family of vision transformers pretrained on 300 million human images at 1024 x 1024 image resolution. When finetuned for human - centric vision tasks, the pretrained models can generalize to in - the - wild conditions.
• Sapiens - 0.6B natively support 1K high - resolution inference. The resulting models show remarkable generalization to in - the - wild data, even when labeled data is scarce or entirely synthetic.

📚 Documentation

Model Details

• Developed by: Meta
• Model type: Vision Transformer
• License: Creative Commons Attribution - NonCommercial 4.0
• Task: pretrain
• Format: original
• File: sapiens_0.6b_epoch_1600_clean.pth

Model Card

More Resources

• Repository: https://github.com/facebookresearch/sapiens
• Paper: https://arxiv.org/abs/2408.12569
• Demo: Sapiens Gradio Spaces
• Project Page: https://about.meta.com/realitylabs/codecavatars/sapiens
• Additional Results: https://rawalkhirodkar.github.io/sapiens
• HuggingFace Collection: https://huggingface.co/collections/facebook/sapiens-66d22047daa6402d565cb2fc

📄 License

This model is licensed under the Creative Commons Attribution - NonCommercial 4.0 license.