@OpenAI@literallydenis 2/ Something that AI headlines don't always capture is that as a human, you actually have a lot of artistic input in what the AI paints. The AI didn't draw all this automatically - I prompted it to draw certain elements
@OpenAI@literallydenis 3/ Here's a sampling of the prompts I used. For each prompt, I added "painting by Johannes Vermeer" at the end for style
4/ I used a process called "inpainting" which allows you to modify an existing image. You can also use this feature to "extend" the canvas. I learned how to do this from @guskamp
5/ Shoutout to @literallydenis who first used DALL-E to expand famous paintings last month. I was inspired by his series and wanted to try making a video version that showed some of the variations I went through
• • •
Missing some Tweet in this thread? You can try to
force a refresh
It’s still early days of AI video - this tech will only get better. A whole new generation of filmmakers is gonna be able to make whatever they want on zero budget
NeRF update: Dollyzoom is now possible using @LumaLabsAI
I shot this on my phone. NeRF is gonna empower so many people to get cinematic level shots
Tutorial below -