Skip to content

lyua1225

clip-huge-zh-75k-steps-bs4096

lyua1225/clip-huge-zh-75k-steps-bs4096

clip-huge-zh-75k-steps-bs4096 is a zero-shot image classification model from lyua1225. Use it for the zero-shot image classification task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as creativeml-openrail-m.

训练该模型的目的是使用中文文本指导stable diffusion 2模型进行生成。冻结openclip的CLIP-VIT-H图像编码部分,训练文本编码部分以对齐英文语义空间, 训练样本均来自LAION-5B的中文子集

Downloads · 30 days

46

2% of all-time downloads

All-time downloads

2.3K

Public

Repo size

7.9 GB

Likes

18

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin3.9 GB · 100%

At a glance

Task
Zero-Shot Image Classification
Library
transformers
License
creativeml-openrail-m
Model type
clip
Access
Public
Created
Dec 16, 2022
Updated
Dec 16, 2022
SHA
4db24730
Task
Zero-Shot Image Classification
Library
transformers
Type
clip
License
creativeml-openrail-m
Languages
zh
Created
Dec 16, 2022
Updated
Dec 16, 2022