Phrame generates captivating and unique art by listening to conversations around it, transforming spoken words and emotions into visually stunning masterpieces. Unleash your creativity and transform the soundscape around you.
When I first discovered generative AI art, I was captivated. The ability to type any text and witness it transformed into a unique piece of art was mind-blowing. DALL·E and similar services sparked my imagination and planted the seed for an ambitious idea: a digital picture frame that creates art reflective of its environment.
After months of development and fine-tuning, I’m thrilled to introduce Phrame v1.0.0. This digital picture frame listens to conversations happening around it. Using speech recognition and Chat GPT, it transforms these dialogues into summarized text. This summary is then used with generative AI APIs to create beautiful and unique pieces of art.
Phrame offers a comprehensive README and an array of customization options for a personalized experience. Currently, it employs OpenAI’s Chat GPT to summarize transcripts and uses DALL·E 2 or Stability AI to generate art.
The user-friendly interface allows for complete control from another device via WebSockets. A gallery feature is available, offering options to filter, favorite, and delete images. All configuration options are editable, enabling customization of the AI used, the image styles, the number of images generated, their size, and much more.
I appreciate you taking the time to read about Phrame and its journey from an idea to a fully realized project. Your interest and support make a significant difference and inspire me to continue innovating and creating open source software. If you’ve had the chance to try Phrame, I would love to hear your thoughts. Your feedback is invaluable and will help shape the future development of this project. Whether it’s an idea for a new feature, a suggestion for improvement, or a bug you’ve noticed, please don’t hesitate to share. Once again, thank you for being a part of this AI journey.
Phrame operates as a single Docker container and is easily accessible using any modern browser, even without a microphone.
To take advantage of the speech recognition feature, a compatible browser and microphone are required. At this time Chrome and Safari are the only browsers that support speech recognition.
Artwork within Phrame is displayed according to the
image.order value. The latest summary and any favorite images are seamlessly merged, providing an evolving canvas of unique AI-generated art. As new images are created, they are instantly displayed by Phrame.
docker run -d --restart=unless-stopped --name=phrame -v phrame:/.storage -p 3000:3000 jakowenko/phrame
version: '3.9' volumes: phrame: services: phrame: container_name: phrame image: jakowenko/phrame restart: unless-stopped volumes: - phrame:/.storage ports: - 3000:3000
- Start Phrame
- Go to localhost:3000/config
- Add your OpenAI API key and save
- Verify OpenAI shows as configured with a green circle
- In a new window go to localhost:3000/phrame?mic and follow the on screen instructions
- Go to localhost:3000 and verify the microphone and speech recognition are working