T

Taiyi Stable Diffusion 1B Chinese EN V0.1

Developed by IDEA-CCNL
The first open-source Chinese-English bilingual Stable Diffusion model, trained on 20 million filtered Chinese image-text pairs
Downloads 182
Release Time : 11/1/2022

Model Overview

A Chinese-English bilingual text-to-image generation model based on the Stable Diffusion architecture, supporting high-quality image generation from Chinese prompts

Model Features

Chinese-English Bilingual Support
The first open-source Stable Diffusion model supporting both Chinese and English prompts
High-Quality Training Data
Trained on 20 million Chinese image-text pairs filtered with CLIP score >0.2
Two-Stage Training
First freezes text encoder for concept alignment, then jointly trains to optimize Chinese prompt adaptability

Model Capabilities

Text-to-Image Generation
Art Style Transfer
Creative Image Synthesis

Use Cases

Art Creation
Famous Painting Style Transfer
Transform ordinary scenes into painting styles of artists like Van Gogh
Example images show the Van Gogh style transformation effect of a small bridge and flowing water scene
Watercolor Painting Generation
Generate watercolor-style images based on Chinese descriptions
Example images show the watercolor style effect of a small bridge and flowing water scene
Creative Design
Fun Image Synthesis
Generate creative composite images, such as a husky in a spacesuit
Example images show a husky wearing a spacesuit
Artistic Transformation of Daily Scenes
Transform daily scenes into artistic styles, such as a cat eating rice noodles
Example images show the artistic effect of a cat eating rice noodles
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
© 2025AIbase