Technical: Generative AI tools used to make this work
Sound:
- Gertrude Stein's voice was cloned in 11ElevenLabs (https://elevenlabs.io/) using 40 second fragments of recordings that were cleaned up using Adobe Podcast (beta) from Penn Sound (https://writing.upenn.edu/pennsound/x/Stein.php).
- Some music and sound effects generated using the following diffusion models:
- haoheliu diffusion (https://replicate.com/haoheliu/audio-ldm)
- riffusion/riffusion (https://replicate.com/riffusion)
Images were generated using the following tools:
- Midjourney (https://www.midjourney.com/)
- Adobe Firefly (https://www.adobe.com/sensei/generative-ai/firefly.html)
- Dall-e in ChatGPT-4 (https://chat.openai.com/)
Video:
Video was generated using the following tools:
- Runway Gen 2 (https://runwayml.com/)
- Deforum - Stable diffusion (https://replicate.com/deforum)
- lucataco/seine (https://replicate.com/lucataco)
ChatGPT - 4 (https://chat.openai.com)
Bing (https://www.microsoft.com/en-us/edge/features/bing-chat?form=MT00D8)
Other tools:
- Maxon (https://www.maxon.net/en/)
- Adobe motion graphics templates (https://stock.adobe.com/)
- Topaz Video AI 4 (https://www.topazlabs.com/topaz-video-ai)
- Topaz Photo AI 2 (https://www.topazlabs.com/topaz-photo-ai)
Continue here to learn more about text-to-image generation.
This page has paths:
- In There, Behind the Door Monique Tschofen