This was the first community I joined, and my first real go at AI beyond just talking to a chat window. I found it pretty much by chance, lurked for a few months, and High Tea 6 was my first call. I didn't realise at the time how much that would shape things. The picture I got here was a healthy one. Build the thing, watch how it actually behaves, be honest about the bits that don't work. I've spoken to enough people since who came in through paid courses to know that isn't the norm. Nobody here sold me a shortcut, and I got pretty lucky landing here first rather than somewhere else. Something happened recently that made me take a step back. I met someone at an open networking event who runs corporate training and is writing a textbook alongside it. What she needs is her course turned into per-module walkthrough videos - her own slides on screen, voiceover over the top, one video per module. I built it as ICM, because that's just how I build now. Numbered stage folders, one agent reading the right files at the right moment, markdown carrying the context, and local scripts doing all the mechanical work that never needed a model in the first place. Her voice cloned from a module she'd already recorded, the deck walked and exported as frames, one script and one audio file per slide. The durations of those audio files become the cue sheet that stitches the whole thing together, so there's no separate timing step to get wrong. One module's through it end to end. 21 slides, 21 scripts, 21 audio files, one finished MP4. And there's around ten hours of modules to put through the same pipeline. As an 18-year-old that's a really good opportunity, and it's going to generate me some serious income. I wouldn't have built any of it without what I picked up in here first, so thank you to everyone who's answered a question of mine along the way. Nothing's finished yet. I've still got a lot to come and plenty I haven't cracked. It just felt worth stopping on rather than quietly getting on with the next thing.

What it does: image and video generation. I use it for a lot more than one thing. Stills, renders, video, and the film I'm working on right now. I've got Claude Code driving it, so the folder holds the anchors and the shot descriptions and Higgsfield does the generating. What I like about it: it's the render step, not the working environment, and that took me a while to sort out. Everything that matters happens in the folder before I ever call it. Anchor images, what each act looks like, the shot list. Higgsfield just executes. So when something comes back wrong I go fix a file instead of fiddling with settings inside another app. It also means one tool covers a lot of ground. I'm using it for the creative work and for actual business stuff, renders and stills and video, and I'm not learning a different app for each of those. How it's helped me: I'm partway through a film and the thing that would have killed it a year ago is drift. Act three stops looking like act one and there's no way back except starting over. Because the anchors live in the folder and I check them before anything else runs, there's always something consistent to point at when it generates. That's saved me more than any speed improvement would have, and what not. The limit that I am trying to fix: motion inside a shot is Higgsfield's call, not mine. I get at it through the prompt and by picking which take I keep. If you want frame-level control over how something moves, this isn't it. At least I haven't found it...

Thanks to a conversation I read between @Alex Brown and @Danney Tee my character continuity is starting to actually get on track. I know this is short but for me it is light years ahead of where I was just yesterday. I was was previously trying to train a character using LoRa and that still got me a different character in every clip. But, just using one one image and instead of using text to describe the character, I'm giving it the single character reference and then telling the ai what I want that character to do. This was a case where I was giving too much context. I know it isn't perfect but I'm still pleased with where I am at the present https://youtube.com/shorts/NzzQDYkEYGs?feature=share

I'm building a 48-second Christmas ad. Not in an app: the whole thing is an ICM folder, Claude Code reads it, and Higgsfield is just the tool on the end of the pipe that renders what the folder asks for. The ad ends on the house a girl wished for, and late in the build I changed that house: out with the generated storybook cottage, in with a real home we actually build. A late change to a foundational element usually means a rebuild. This one didn't, and three ICM principles are why. christmas-wish-short-ad/ ├── CLAUDE.md routing only, no content ├── CONTEXT.md the pipeline + status on one screen ├── _shared/ │ └── inherited.md pointers into the reference workspace. Nothing copied. ├── _templates/ └── stages/ ├── 01_brief/ script + which existing asset each beat reuses ├── 02_shotplan/ every shot bound to a specific still ├── 03_boards/ the house-swap candidates, grades, and decision ├── 04_scenes/ generate the gaps, then the motion pass └── 05_assembly/ edit, composite, watermark, submit Configure the factory, not the product. The reference material lives in its own workspace. The ad is one product coming off it, not a copy of it. One home per fact. The house is a single row in a single element registry. Every shot points at that row. Nothing holds a second copy that can drift. Every output is an edit surface. The candidates, the grades, and the decision itself are plain files sitting in an output folder. Anyone can open it and see where the build stands. The swap still cost me three shots to regenerate. The win isn't that changes are free. It's that I could price the change in about a minute, before committing, because the structure already knew which shots depend on the house. That's the part worth stealing. The generator is swappable. The structure is the thing you own. Let me know if there are any improvements...

After a call with @Danney Tee who kindly demo'd his full system at Reelix and gave me inspiration for what he had done. I decided to have a bit of fun and create my own mechanism, scoping in on one of the areas, which is AI being able to watch and analyze videos.... So I built codename "Argus" -- Still in development but showing some insanely promising results! Argus is the layer that watches a published video and writes down what was on screen, second by second. It is also the cleanest ICM structure I have built, for a boring reason: a pipeline already has stages, so you let the folders be them. - The stages - 01 to 08 in flow order. Each is a folder holding its own script, its own CONTEXT.md of local rules, and its own output. - The root context - only the rules that genuinely cross every stage. What a frame is, how a missing value is recorded, what the system never claims. - _config - the channel. Vocabularies, the editorial ladder, the thresholds. The stages hold the engine, the config holds the channel. The flow reads straight off the folder names. Stages 01 to 05 describe: fetch the video, cut it into frames, measure the frames, ask a model what is happening in each second, roll it up into buckets. Stage 06 synchronises, mapping the editorial plan for that video onto what was described. Stages 07 and 08 derive, joining to the retention curve and rendering the written product, and they are not allowed to add any new observation - only to compute from what came before. The ICM part is that a job sent to stage 03 opens stage 03. It reads that folder's rules and its inputs, and inherits nothing else except the handful of root rules that actually apply everywhere. No stage carries the whole pipeline in its head. That is the difference between a pipeline in folders and one long instruction file trying to describe eight things at once, and it is why I can hand a stage to a job without re-explaining the system around it.