Quick tip for my graphic designers,
In PS, open up to a smart object text layer. Filter, Blur Gallery, Field Blur
Add 3-4 Blur points.
Combine the text & background, then head to
Filter, Filter Gallery, Grain ~(55,95).
Distressed blur.
OpenAI Whisper (speech2text) is trained on 680K hours of audio. VALL-E is only trained on 60K hours.
This means the potential of text2speech models is way under-tapped. OpenAI can just scale up VALL-E 10x on their private training set and nail it. It's such a low-hanging fruit.
On #Ansa, rain is a vital element for the lives of many species. Some thrive and prosper in the humidity it brings, while others must adapt to survive. It's a fascinating planet where every drop of rain counts. Follow for more.
#newEden#storytelling#midjourney#AIcinema