https://github.com/Stability-AI/generative-models

Generative Models by Stability AI
https://github.com/Stability-AI/generative-models

Last synced: about 2 months ago
JSON representation

Generative Models by Stability AI

• Host: GitHub
• URL: https://github.com/Stability-AI/generative-models
• Owner: Stability-AI
• License: mit
• Created: 2023-06-22T00:36:35.000Z (about 1 year ago)
• Default Branch: main
• Last Pushed: 2024-07-24T15:04:56.000Z (about 2 months ago)
• Last Synced: 2024-07-25T17:18:59.149Z (about 2 months ago)
• Language: Python
• Homepage:
• Size: 50.8 MB
• Stars: 23,472
• Watchers: 252
• Forks: 2,600
• Open Issues: 283
• Metadata Files:
  • Readme: README.md
  • License: LICENSE-CODE
  • Codeowners: CODEOWNERS

Awesome Lists containing this project

• awesome-diffusion-categorized - [Code
• Awesome-Video-Diffusion - Stable Video Diffusion
• awesome-rainmana - Stability-AI/generative-models - Generative Models by Stability AI (Python)
• awesome-repositories - Stability-AI/generative-models - Generative Models by Stability AI (Python)
• AiTreasureBox - Stability-AI/generative-models - 09-13_24032_2](https://img.shields.io/github/stars/Stability-AI/generative-models.svg)|Generative Models by Stability AI| (Repos)
• ai-game-devtools - Stable Video Diffusion - to-Video. | | | Video | (<span id="video">Video</span> / <span id="tool">Tool (AI LLM)</span>)
• StarryDivineSky - Stability-AI/generative-models - Turbo，这是一款闪电般快速的文本到图像模型。 Stable Video Diffusion，一种图像到视频的模型。SDXL-base-0.9 ：在分辨率为 1024^2 的图像上，对基础模型进行了各种纵横比的训练。基本模型使用 OpenCLIP-ViT/G 和 CLIP-ViT/L 进行文本编码，而精简模型仅使用 OpenCLIP 模型。SDXL-refiner-0.9 ：精简器已经过训练，可以对高质量数据的小噪声水平进行降噪，因此不应用作文本到图像模型;相反，它只能用作图像到图像模型。 (其他_机器视觉 / 网络服务_其他)