#166 · Primary category: Image Generation

SkyPaint-AI-Diffusion

ai-painting aigc artificial-intelligence bert clip cv dalle2 diffusion dreambooth generative-art latent-diffusion machine-learning midjourney openai pytorch stable-diffusion text-to-image text2image

基于Stable Diffusion优化的AI绘画模型。支持输入中英文文本,可生成多种现代艺术风格的高质量图像。| An optimized text-to-image model based on Stable Diffusion. Both Chinese and English text inputs are available to generate images. The model can generate high-quality images in several modern art styles.

Project last updated:03/09/23

GitHub Stars

647

Forks

37

Contributors

1

License

MIT

Why we included this project

SkyPaint is a Stable Diffusion checkpoint tuned for Chinese-language prompts, which matters if your team writes prompts in Chinese or mixes Chinese and English in the same request. The key piece is a bilingual text encoder that keeps the standard Stable Diffusion prompting conventions, so it drops into existing diffusers workflows without retraining. The repo also includes SkyCLIP, a distilled bilingual CLIP text encoder you can pair with OpenAI's image encoder for image-text retrieval, handy for building Chinese-language search or captioning features. Note that this is a model release, not a maintained application: it hasn't been updated since early 2023, so test it against current Stable Diffusion versions before relying on it.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category