This a list of AI tools and applications we find especially interesting, useful, or informative. This list is not comprehensive, and mostly contains things that are featured in our course content.

Generative AI platforms:

Image generators:

<aside> ➡️ Dream Studio - Official Stable Diffusion interface. The new release Stable Diffusion XL is especially proficient in photorealism.

</aside>

<aside> ➡️ Adobe Firefly - Beta version of Adobe's image generator.

</aside>

<aside> ➡️ MidJourney - A model of its own (not stable diffusion) proficient in photorealism (among other things).

</aside>

<aside> ➡️ Dall-E - Easy-to-use and cheap, but doesn’t make the cut of looking like IRL imagery (in real life).

</aside>

Voice generators:

<aside> ➡️ **Play.ht** - Ultra-realistic Text-to-Speech (TTS) generator.

</aside>

<aside> ➡️ **ElevenLabs -** Another Text-to-Speech service which also offers ways to create voiceovers in your own voice.

</aside>

Video generators:

<aside> ➡️ **Runway ML -** can add special effects to existing videos or create short videos in response to text prompts.

</aside>

Music generators:

Note: These are still very beta and, dare I call them, weird (or artistic, depending on how you see it)..

<aside> 💡 AudioGen & MusicGen - free-to-use, simple and controllable models for audio generation on HuggingFace.

</aside>

<aside> 💡 Soundful - closed-source, commercial music generation model for creating royalty free background music.

</aside>

<aside> 💡 BoomyAI - Offers a song-generation platform even for non-musically inclined, as well as a platform where to post this music and get paid when someone listens to it.

</aside>

Innovative applications:

<aside> ➡️ Elicit - AI Research Assistant; Find relevant papers, summarize takeaways & extract key information

</aside>