Zoo serves as an innovative playground, allowing users to generate photo-realistic images from text inputs using diverse text-to-image AI models. Leveraging latent text-to-image diffusion models, including STABILITY-AISTABLE-DIFFUSION 1.5, STABILITY-AISTABLE-DIFFUSION 2.1, AI-FOREVERKANDINSKY-2, and OpenAI’s DALL-E, Zoo offers a rich exploration experience. Here are the key aspects of Zoo:

Key Models:

  • STABILITY-AISTABLE-DIFFUSION 1.5 and 2.1: Latent text-to-image diffusion models for generating images based on natural language descriptions.
  • AI-FOREVERKANDINSKY-2: A text2img model trained on internal and LAION HighRes datasets.
  • OpenAI’s DALL-E: An AI system creating realistic images and art representations from natural language descriptions.


  • Users input text descriptions (e.g., “a tilt shift photo of fish tonalism by Ugo Nespolo”) to generate corresponding images.
  • Runs on a PostgreSQL database and file storage provided by Supabase.
  • Open-source repository available on GitHub.

Powered by Replicate:

  • Zoo is powered by Replicate, specializing in providing infrastructure for AI and machine learning projects.

Collaborative Space:

  • Valuable resource for researchers and developers exploring text-to-image AI models and their applications.
  • Offers an accessible and collaborative platform for exploring advancements in computer vision AI.

Zoo, with its array of models and open-source framework, stands as a collaborative hub for those interested in delving into the possibilities of text-to-image AI, making it a valuable resource in the field of computer vision research and development.

Sign In


Reset Password

Please enter your username or email address, you will receive a link to create a new password via email.