Generative AI models are a broad area in Machine Learning that instead of Classification focus on creating data. Classification is about prediction which is really cool; Nostradamus ;) However, the ability to create is superior; We become Gods, new kind of gods that really exist! Also, if you can create, you can predict.

With that introduction, we can jump into the edge of research in this field. This field is growing really fast and has gained a lot of attention from the public and media recently, especially the famous ChatGpt model by OpenAI.

In this blogpost, I talk about the most recent and interesting generative models and I will update this post with the new advancements in the field. Let’s get started:

Text-to-Text Models

ChatGPT

Perplexity.ai

perplexity.ai is an attempt to make a tool such as chatgpt more like a search engine.

Tex-to-Image Models

DALL.E

Imagen

Text-to-Audio Models

AudioGPT

AudioGPT is a text-to-audio model where you provide a text prompt, and the model generates an auido regarding your promp. You can play with this model on the huggingface hub.

MusicLM

https://blog.google/technology/ai/musiclm-google-ai-test-kitchen/?utm_source=alphasignalai.beehiiv.com&utm_medium=newsletter&utm_campaign=is-this-the-end-of-regulation-free-ai

Text-to-Video Models

• Runway: https://research.runwayml.com/gen2?utm_source=alphasignalai.beehiiv.com&utm_medium=newsletter&utm_campaign=meta-s-new-and-powerful-text-to-music-model

Stability AI stable animation

https://stability.ai/blog/stable-animation-sdk?mc_cid=c59d71288a&mc_eid=03e4a944e9

Multimodal Generative Models