Welcome. I'm Jordano one of the Directors at DreamCodeFilms. This community exists because most AI video looks the same, same prompts, same outputs, no point of view. We do the opposite. Here we direct AI, we don't just generate with it. The craft comes first; the tools serve the story. So before anything else — introduce yourself in the comments. Tell us three things: 👋 Who you are (and where you're posting from) 🎬 What you're making right now, the project or style you're into 🎯 The one thing you want to be able to create by the time you leave here Everyone in this room started exactly where you are. Drop your intro below and say hi — and reply to one other person while you're here. That's how this place stays alive. Stuck or just want to talk shop? DM me anytime. I'm here. — Jordano

The Aruban Retiree – It's not for retiring in Aruba because it's much more expensive than Santiago de Chile, and it's much more expensive than in Europe. Tons of wealthy Americans come to Aruba and tip 20% everywhere, just like at home. I filmed the Aruba Carnival from a Marriott terrace. Enjoy! https://youtu.be/6etJleAJxFg .... I worked with AI for the thumbnails, title, and description. While working, AI added drone descriptions, so I have to publish another movie from a drone - and link it inside the description (the other option was to cut the description - so AI forced me to publish more 🤖😍 ) ... All this work while doing some edits for a huge movie and just playing some recent raw movies

These days I've been building films with invideo Agent One. Instead of prompting, you just talk to an agent and it builds the film with you. You describe what you want, it makes the move, you give notes back, like directing a real crew. Here was the full workflow for this psychedelic concert shot. Start from a frame I gave it the starting frame: a four piece rock band mid set in a smoky basement club, magenta and cyan neon, a warm key light, haze in the air. Everything after this is just talking to the agent about that room. Let it draw the camera path I asked it to build a camera path through the room from that frame, and to draw the flight path straight on the image: push in past the bassist, lift up to the singer at the front mic, track across to the second mic, then drop down to the drummer. It marks the move on the frame so you can read the whole shot before you commit to a render. Keep the arrows out of the render One thing that tripped me up early was the drawn arrows bleeding into the shot. So I told it to keep the arrows as guidance only. They mark the move for you, they never show up in the final. Clean plate, just the camera motion. Set the energy Then I locked the feel. Handheld camera, quick loose movement, full psychedelic music video energy. Fast whip moves between the band, neon haze held through the whole take. Push the grade I asked it to push the neon harder. Magenta and cyan bleeding off every light source, soft lens bloom on each one, a light haze over the whole frame. Run it as one take Last step, I told it to run the whole path in one continuous handheld take. Follow the arrows, start on the bassist, end on the drummer. One shot, no cuts. That is the whole thing. No timeline, no manual keyframes, just a conversation with the agent until the shot was right.

TL;DR: You already know how to make a shot look cinematic. The place that control slips is a phone shot, a video call or a selfie, where your film instinct takes over and the result reads as a film still, not a phone. Take it back by keeping the cinematic base and directing the phone-camera grammar on top: name the device, put the body in the lens, add the phone tells. Tell Agent One on invideo to blend both. Where the control slips A pure cinematic look is gorgeous, which is exactly why a video call or a selfie comes out wrong. Shallow depth of field, film grain, dramatic lighting, a tripod-stable color-graded frame. But a phone is not shot like a movie, so the audience reads it as a film still and never believes there is a phone in his hand. The polish is the tell, and you handed that detail to the model instead of directing it. Take it back: direct the phone grammar Keep the cinematic base, then layer the phone on top. Three moves carry it. First, name the device: a front phone camera, a video-call feed, so the model knows what is recording. Second, put the body in the lens: his arm extended holding the phone, his eyes looking straight into it. Third, add the phone tells: the wide selfie lens, the on-screen call UI, the screen glow on his face. Let Agent One blend both Tell Agent One on invideo to keep the cinematic look but render it as a phone POV, and it blends both into one believable shot. You direct both layers. The film grade gives it weight, the phone grammar makes it real.

I'm deep in a project right now mixing Blender and AI, and I also put together this one (Below). Drop a comment with what you're planning to work on this weekend. Always love seeing what the community's building.