Avaren

PARALLEL — a film I made as a tribute to a feeling.The words are fifteen years old. I wrote them long before I knew who they were for. The feeling is much newer, and this film is what I did with it instead of keeping quiet.Five minutes. Everything human in it is real, and everything around it was made. We shot it on phones — an office, a room, the two of us filming ourselves separately, never in the same place, meeting only at the very end of the film. That is the whole shape of it, and it happens to be true offscreen too.Real: our faces, our hands, the dance, the voice. I trained my voice and sang the song myself, the whole thing, before a single note went into Suno.Made: a birch grove at dawn, the meadows, a gazebo over the water, and the sky over the river that goes purple only at the end.The method, in one line: your own footage is the character sheet. I cut my own clips into video reference elements and locked both faces — mine and Adam's — to them. Nothing about us was invented. The model only carried what we actually filmed into places that don't exist. What kept it honest: → one file, one job, one prompt line → write the result, never the negation → change two things per pass, not five → check every output against the source, every single time #Seedance 2.5, omni-reference, video edit in @higgsfield_ai . @suno for the track.Full pipeline breakdown, if you want to make one too: one-room-film.higgsfield.app And the warmest thank you to @AvarenFocus . He filmed his part, he cut the final edit, and he stayed in it with me while it was still shapeless. Some things are easier to build than to say out loud — so I built this one. It's as much his as it is mine.

This video was made for our 1,000 Hours in Power Users Live stream. ❤️‍🔥 But really, it was made for the community, about the community, and because of the community. Reaching 1,000 hours live would not have been possible without all of you — the people who kept showing up, streaming, watching, creating, helping, laughing, testing, supporting each other, and keeping the Power Users Live room alive for so long. The video is built around the people who directly helped carry this room. Each character sheet was made for a specific person, with small details, traits, moments, and little “perks” connected to who they are in the community. There are more than 30 character sheets in the project. Some parts were made by @PeterKL87 , some by me, and @AvarenFocus also helped with the final #edit and music. A lot of it came together overnight, with very little sleep, but a lot of #love for this server and everyone inside it. The #stream itself was a beautiful moment. And honestly, I’m just very grateful that we have a community where people notice each other, support each other, celebrate each other’s strengths, and help each other keep growing. When someone is not around, someone else usually shows up. When someone gets stuck, someone else offers a hand. When someone creates something, there is always someone there to watch, react, give feedback, or simply say: “keep going.” That kind of genuine human connection, mixed with the ability to make art together no matter what, is something really special. I love this #Discord. I love this #community. Thank you for being here, for being yourselves, and for making this place feel alive. 💚 @higgsfield #Higgsfield1000

I got In the Mood for Love (2000) in our Film DNA Roulette challenge, and what started as a reference exercise turned into a much bigger experiment than I expected. I basically sat down during a 24-hour stream, opened Seedance 2.5, and started taking the film apart piece by piece - color, framing, rhythm, use of space, the way time passes, when the camera moves and when it simply watches. At first, there wasn’t really a #story. I was mostly playing with the language of the #film itself - testing the pacing, the framing, the colors, the way it handles #time - and somewhere along the way the story just started appearing on its own. I think that was actually the most interesting part for me. I’m usually the opposite of a slow-film person 😅 My brain constantly wants something to move, change, happen. So staying inside this much quieter rhythm for so long felt a little unusual. But after spending enough time with it, I started enjoying all those tiny things I would normally rush past. A different light already tells you that time has moved forward. Clothes and color can quietly show how two people are changing. The same type of shot repeated a few times starts to mean something different each time. And when the camera is restrained for most of the film, even a very small movement suddenly has weight. There’s almost this funny point where you stop thinking, “nothing is happening,” because actually quite a lot is happening - it’s just not being explained to you. And I really liked that you could remove almost all dialogue and still understand the emotional movement of the story. I collected the whole process here - what I took from the original film, what I tested, what worked for me, what I changed, and how the final story slowly came together: film-dna-workshop.higgsfield… I probably still won’t become a person who watches five extremely slow films in a row 😅 but experimenting in this kind of rhythm was surprisingly nice. Now I want to try the same thing with something completely different and see what it does to the way I build a story. @higgsfield_ai

I’ve been experimenting a lot lately with AI Employees inside @higgsfield #Supercomputer, and these four videos are all outputs from one of the Employees I’m currently building and training. The idea behind this one is pretty simple: give it a brand, product, or website, and let it handle much more of the advertising workflow itself - research the brand, understand its visual DNA, look at the competitive space, choose a direction, build the concept and pre-production, and then move into actual video generation. What I find especially interesting is that this isn’t really about making AI “press one button and magically create an ad.” It’s much closer to building your own production logic. You can teach an Employee how you want it to research, how much freedom it should have, which models and workflows to use, what makes a concept good enough to move forward, how strict it should be about product consistency, when it should create storyboards first, how it should approach camera language, and even how it should QC the final result. And then you keep refining it. Some of these workflows can easily take 10–20 minutes from the initial task to finished generations, especially when #research and pre-production are involved. But the interesting part is that I don’t really have to sit there and manually execute every stage anymore. And because Supercomputer can run multiple tasks at the same time, the equation changes even more. Instead of spending those 10–20 minutes producing one direction manually, I can launch several different tasks or creative directions in parallel and come back to a much larger pool of material in roughly the same window of time. That’s probably the part I’m enjoying the most right now: not just saving individual clicks, but multiplying how many ideas I can actually explore. The Employee itself is still very much a work in #progress. I’m constantly changing instructions, testing where it needs more #control and where it actually performs better with more creative freedom. Some decisions still need human judgment, and there are plenty of things I want to improve. But these four #videos came out of that process - different directions, different executions, all produced through the same evolving system. And the #results are already making me very curious about where this way of working goes next. AI Employees become much more interesting when you stop treating them like assistants and start treating them like #workflows you can teach, test, and continuously improve.