Activity
Mon
Wed
Fri
Sun
Dec
Jan
Feb
Mar
Apr
May
Jun
Jul
Aug
Sep
Oct
Nov
What is this?
Less
More
4 contributions to AI Architects
Update: Motion Graphics Editor + Microsoft Clipchamp
I have been plugging away at this video editing pipeline this week (after my weekly Claude tokens were renewed on Thursday) It runs locally on my computer. The Beach Whisper video is the first video I made since I added the motion graphic editing features into the control panel. In the explainer vid below, you'll see that it took just a couple of messages to get all the video motion assets into the timeline. I think it's coming along nicely. BUT ... After reviewing the example video for Beach Whisper, I think it needs a sound effect feature to overlay in the timeline.
Update: Motion Graphics Editor + Microsoft Clipchamp
0 likes • 28d
Wow Tara, this is really cool. Sign me up. I like the way you added the prompt into the UI/UX. That way you can experiment with prompt variations and corrections. This is not a **criticism** but a comment that reflects my interest. It was not clear to me whether the prompt → model was for the video or the app itself. <tl:dr> My area of interest is creating variations in infotainment short forms so that I can then acquire metrics from the social platforms to evaluate viewer performance. For example: in your surf movie, does having a dog shot get more views and likes that not having the dog shot. Did split screen keep the viewer engaged better than without it. Is beach sound better than music. Is surf music better than soft background music. Do titles help keep engagement? So my use case would be creating variations quickly while still having a quality video. I would be looking to use the model to build templates to automate the production. Point the app at a folder full of clips and click produce.
1 like • 25d
My SM (social media being abbr as SM is probably significant. ha ha) strategy is like a fish or plant. Sew 1000 seeds and let the audience metrics tell you which survive. The use the metrics to design your next video. Automate for engagement metrics. Speed produce the content through prompt engineering. Your viewer count problem is exactly the issue I am trying to address. Most content creators think that the trick is to produce quality videos. I disagree. The trick is to produce videos that sell. Would you rather 10 viewers see your beautiful video or 10,000 see your ugly video? My attachment tells you why I think that. I am still in the Research phase. A/B testing is the key. I am going to attach a rather large file (>1100 lines) that is a transcript of my conversation with my AIs. An AI can summarize it for you. You can save tokens by attaching it to a prompt, so that the contents do not hit your prompt tokens. Claude will still eat the file and summarize. Your token bill is the link to the file and Claude's response.
10/19 - 10/22 ✄ Live Show Cut Up by Topic (the Daily Pulse 🔥)
Hey Architects! - PAID members can access all live segments anytime (✄ cut and organized by topic) - FREE members can access the last unedited video for 24 hours only (see below👇) 📆 Upcoming: Mon-Thur (calendar) 🖥️ Watch now 10/19 - AI Makes You Stupid 10/21 - AI Subscription Models 10/22 - Solving Technical Problems - Selling MCPs As A Subscription Service 👥 Community Update - 💬 Video request? - Make a video request and I'll cover it (click here) 💪
1 like • 27d
AI Makes You Stupid makes me stupid enough to click the link and get a paywall because this video is from yesterday at 10:00 AM. It is now 10/20 3:33PM Los Angeles time. Your bot needs to remove the watch now from this post or expire the link somehow.
1 like • 25d
@Stephen G. Pope I am not trying to be critical and a jerk, I was letting you know that you promised in the bullet points that FREE members, that's me, can access for 24 hours. I was acknowledging that and letting you know that the link was not disabled after 24 hours.
Cancel Your Adobe Creative Cloud Subscription - TODAY!
No affiliation whatsoever, but it seems like a very familiar interface and feature set that we all know in love from another company is finally gaining some traction. I’ve heard rumours that it was happening, kept an eye on the GitHub repository, but just not sure how well it would come out in the end. It’s a fascinating look into things bigger than just software and more about human society in general - not sure this falls into that category, but still very interesting for our world….until maybe some lawyers step in 🤣 Might have to put it through its paces and see how well it compares; obviously won’t have all the same features, etc., but might be a great option for educational use, folks just starting out, etc. https://getartcraft.com/apps
0 likes • 28d
Adobe real problem is that they are using AI to enhance their features, but are neglecting the ability to have AI direct the program actions. Their online help is so complicated as to render it useless. I have the entire Creative Cloud and many ideas on what I want it to do, but I cannot figure out how to do 'this specific thing' that I am trying to do. I generally ask Copilot how to do something and it gives me a step-by-step but what I really want is a way to implement the step-by-step now and tell me how you did it so I can repeat it later. I looked at getartcraft and it looks like they have aggregated the AI versions of apps. I am not so sure that a price comparable to what I pay for CC is worth that unless they are really aggressive about keeping the child app upgraded to the latest version and are adding new ones as they happen. Things are moving so fast that todays aggregation is outdated literally tomorrow.
Creating a Media Vault
I’ve been working on a way to turn my video shoots into searchable media library. Delivering terabytes of raw footage to clients on hard drives is a pain and the raw clips are hidden in folders. The files are unsearchable, so the footage just sits there and dies. The solution is a custom, automated AI media vault built for each brand. The Stack & Workflow: Python + FFmpeg: A local script parses my export folders and automatically generates lightweight 1080p web proxies. Google Gemini Flash: Transcribes the audio, auto-tags visual metadata, and categorizes clips based on folder structure. Cloudflare R2: Secure cloud storage buckets per client. Softr: The front-end client portal. Instead of paying an editor to manually tag assets, Gemini turns spoken quotes into instant search filters. The client types in a keyword, and the exact 15-second clip isolates immediately. I’m currently rolling this out as a premium service to close higher-tier, multi-day production contracts. Here is a 2-minute demo of the workflow. Let me know if you have any questions on the Python script or the Gemini integration.
1 like • 28d
I love your automation. Breaking your raw up into clips is very useful. Making the microphone recording in the field searchable is what makes finding clip useful. I suspect your are annotating the clips while you are recording so you can search for clips in two ways: 1. what the interviewee said and what you annotated the scene with an audio snap board. So you can refer to clips by content in addition to time-line. I do not know what they call that scene description board that they use in film production that marks the scene. A very useful tool and automation. Congratulations. I also liked your production values on the YT video.
1-4 of 4
Nick Stein
1
1 point to level up
@nick-stein-5892
Retired Software Engineer

Active 4d ago
Joined Oct 3, 2026
Powered by