Day 1 of 30. Lawrence of Arabia. One of the greatest cinematography achievements in film history. No reference images. No color palettes. No crew. Just a prompt. This is the ceiling of what AI image generation can extract from pure language and I wanted to find out exactly where that ceiling is. Freddie Young spent months in the Arabian desert with 65mm Panavision cameras and the actual sun as his key light. I had a text box. No disrespect to the legend. Every pixel here is a tribute to how precisely his visual language can be described and how far prompt engineering has come. 30 films. 30 cinematographers. Zero reference images. Follow along. 🎬
right now the best in the business, well deserved team 🖖
Pretty sure @rubbrbandHQ stole it!!
The night changes depending on where you look.
Created in @stages_ai. Can you guess which image tool I used? ;)
@dustinhollywood
🤖 Made with AI
Brilliant!! I can't imagine completing all this stuff in 10 days. Would actually like to have a conversation with this guy Vinu.
I made a live-action series – 'Penumbra' – on invideo’s Agent One without the screenplay, pre-production plan or script locked going in.
I started with a vague idea about two characters and built the episode scene by scene, pulling references on the fly and brainstorming with the agents the way I would with a real crew.Had around 20-25 agents working in parallel by the end of it.
Took me ~10 days. ~$6,540.
Full breakdown in the video and the thread.































































