Before you jump in, there’s one important thing to understand about this community. AIography exists to explore how AI is reshaping filmmaking, storytelling, and creative workflows from script to screen. This is a place for learning, sharing experiments, asking smart questions, and helping each other navigate a rapidly changing creative landscape. To help keep the signal high and reduce spam, posting is unlocked once you reach Level 2. You’ll get there quickly by engaging in discussions, reacting to posts, and participating thoughtfully. What this community is NOT: - A place to pitch “make money” schemes - A place to drop affiliate links, funnels, or cold offers - A place to self-promote unrelated products or services If your first instinct after joining is to sell something, this is not the right room for you. What is encouraged: - Thoughtful discussion around AI tools and workflows - Sharing work in context (what you tried, what worked, what didn’t) - Helping others learn and think more clearly about AI and creativity - Genuine collaboration and curiosity Promotion may be allowed later and in the right context, but it is never the starting point here. Posts or comments that ignore this will be removed. Repeated behavior will result in removal from the community — no drama, no warnings loop. We’re here to build understanding and craft, not noise. If that sounds like your mindset, you’re in exactly the right place. If not, it’s better to know that now. — Larry

So I got a bunch of Tavily API credits for completing their course AND I wanted to show how to use a Boilerplate template to start apps. Combined this with a system (Claude Code Plugin) I've been developing the past couple of months I'm calling 'Apex Spec System' and I made a pretty awesome and good looking app. Complete open-source here: https://github.com/moshehbenavraham/tavily-app How it works: - Phases → major feature groups - Sessions → focused implementation units - Specs → detailed requirements per session - Task checklists → 15-30 items to complete - Validation gates → quality checks before moving on The result: - 15 sessions across 3 phases - FastAPI backend + React frontend + PostgreSQL - Auth, CRUD, 4 Tavily operations, save results with metadata - ~15K lines of production-ready code - 2 afternoons The key insight: AI doesn't drift when it has clear scope, explicit constraints, and traceable progress. It's not magic—it's just structured prompting at the project level. Video below! Curious if anyone else is experimenting with structured AI dev workflows such as BMAD, Github Spec Kit, etc. What's working for you?

Hey guys!) I’ve been exploring whether it’s possible to actually evoke emotion through AI-generated content, beyond noise, speed, and pure technical flexing. Less spectacle, more atmosphere. Less demo, more feeling. I put together a short sequence as an experiment, almost a proof of concept, to see how far you can go when the goal is to make people feel something, not just impress them. Sharing the link here.👇 https://x.com/Three_Wars/status/2001695151715226011?s=20 Really curious to hear what it triggers for you, what works, and what doesn’t.Let’s keep exploring.

Hi everybody! I’m Melanie, I’m new here (: I’m a filmmaker and visual artist that recently got into this craziness of A.I and I’m loving it! I’m finding myself being able to bring my hand drawn beings to life, and it just feel is so damn good! I’ve been working on a series of tiny forest creatures that were born from my sketch book and transformed into AI characters. I’d love your opinion! 🥹

This is My First Cinematic A Video with my own face I try with Photoshop nano bana and Google veo3.1