A Human-in-the-Loop workflow for creating HD images from text.

DALL·E Flow is an interactive workflow for generating high-definition images from text prompts. Developers and generative artists can use it to generate image candidates, choose a candidate, then enrich its texture and background. Finally, the image is upscaled to 1024x1024 for higher detail and resolution.


  • Landscape with great castle in middle of forest
  • Log cabin in a forest by a lake with sunset in the background
  • Ocean beach front view in Van Gogh style
  • City, top view, cyberpunk, digital realistic art
  • An oil painting of monkey using computer
  • A husky dog wearing a hat with sunglasses
  • DALL·E Flow


    DALL·E Flow is built with Jina in a client-server architecture, which gives it high scalability, non-blocking streaming, and a modern Pythonic interface. A client can interact with the server via gRPC/WebSockets/HTTP with TLS.

    Why have a Human-in-the-Loop? Generative art is a creative process. While recent advances of DALL·E unleash people's creativity, having a single-prompt-single-output interface locks the imagination to a single possibility, which is bad no matter how fine this single result is. DALL·E Flow is an alternative to the one-liner, by formalizing generative art as an iterative procedure.

    Ready to get started?

    Let your creativity flow with DALL·E Flow.