Masonry (@MasonryHQ) header
Masonry (@MasonryHQ) profile picture

The most powerful AI creative agent - Try now on https://nitter.gq/t.co/6Hg69FWs7H

San Francisco, California
Joined February 2025
Photo by Masonry (@MasonryHQ)Photo by Masonry (@MasonryHQ)Photo by Masonry (@MasonryHQ)Photo by Masonry (@MasonryHQ)Photo by Masonry (@MasonryHQ)Photo by Masonry (@MasonryHQ)Photo by Masonry (@MasonryHQ)Photo by Masonry (@MasonryHQ)Photo by Masonry (@MasonryHQ)Photo by Masonry (@MasonryHQ)
This jewellery campaign looks expensive. The production? Almost entirely AI. 💎 We took jewellery beyond traditional product photography, experimenting with dramatic angles, intricate details, reflections and cinematic movement. From the first frame to the final video, every visual was part of the creative experiment. Models used: Kling 4.0 + GPT Sunburst Created on Masonry.
1
2
35
The jewellery doesn't just look good in stills. Wait till you see it move. 👀 We brought the campaign to life with AI video, using Kling 4.0. Same jewellery. Cinematic treatment. Zero traditional filming. Watch the transformation. 🎬
2
18
A man who doesn't exist says "Oui Madame" into a phone. X shows 5.4M views on that one clip 🤯 → 3.7M on the next one, posted the day after → 1.9M on a third, six days after the first → 679K views and 6,974 bookmarks on Erika, an AI influencer whose creator says she made $10K in 5 days The format is almost too simple: > one invented face you can read from a thumbnail > one deadpan line > one continuous phone take > a new everyday place every post So we made our own. Kev: 6'5", retired bodybuilder, silver pompadour, pink cardigan, tiny pink suitcase at baggage claim. One word per video. A 10-second Kev video costs about 70 cents in Masonry. Our first take gave him three arms. Where should Kev show up next? We'll make the best reply ↓
This AI influencer doesn't exist. Her creator says 13 videos made $10K in 5 days. Here's the format, and how to build your own character for under $1 a take.
1
26
Masonry retweeted
This guy built an AI pipeline that generates hyperrealistic fashion models in 47 minutes and now dropshippers pay him $1,400 to clone the entire system. He got tired of watching e-com brands lose $8K per photoshoot when a single product angle changed so he built a 9-node workflow that generates 127 product videos from one Pinterest photo without hiring a single model. Here's the exact breakdown: → Claude writes a 34-parameter JSON brand DNA before any image is touched target psychographics, price anchor, vibe matrix, anti-inspiration blacklist → Pinterest becomes the model source library but you can't just download and animate → Kling 2.6 takes that static JPG and turns it into 5-second video but only after the prompt architecture is locked → Negative prompt node runs 41 exclusion terms: no plastic skin, no CGI glow, no symmetry artifacts, no doll face, no synthetic lighting → That one step kills the "AI look" that tanks engagement by 67% in the first 3 seconds → TikTok Studio uploads 19 videos in one batch with zero manual captioning because the brand voice was pre-programmed in step one → Atlas scrapes Amazon product links and auto-generates a Shopify store with hero images, pricing tiers, scarcity copy, and mobile-optimized checkout in 90 seconds → The store goes live before the first TikTok video finishes processing The key move 94% of people skip: you can't animate the photo before you inject the negative prompt. If you send a raw Pinterest image straight into image-to-video the face morphs into a wax figure. The fabric loses texture. The hands grow extra fingers. The whole thing screams "AI" and your CTR dies. His system runs the exclusion filter first so the model moves like she's shot on an iPhone 15 Pro in natural light. One brand hit 2.6M views on TikTok in 11 days with zero paid ads and converted at 3.7% because the videos looked like organic UGC not polished studio content. Brands now pay him $1,400 for the full pipeline setup + $340/month to keep the store synced with new product drops and seasonal video batches. The entire system runs on $23/month in API costs and one laptop. No photographer. No model agency. No product samples. Just a prompt template, a Pinterest account, and the discipline to filter out the AI artifacts before you render movement.
36
160
1
1,434
539,019
A full campaign. A beach location. A model. Product shots. Props. Zero cameras. Zero production crew. Generated using ChatGPT 2 and brought together with a little creative direction on Masonry. We built an entire Alo-style campaign without a traditional shoot. And honestly? This is just the beginning of what's possible. Comment CAMPAIGN if you want the workflow.
1
42
One AI cartoon of a calm hero flattening everyone hit 1.2M views 🤯 → 1.2M views on the earliest post we found → 341K on the next one, three days later → at least seven episodes in four weeks, prompts sold to subscribers The format is almost too simple: > one hero who never notices the fight > five opponents, each bigger than the last > a random everyday item lands every four seconds > a caption that reads like the setup of a joke So we made our own. Meet Grandma Mildred: 80, 4'10", enormous handbag. A biker, a ninja, a sumo wrestler, a robot and a masked champion all come for her. She squeezes a rubber chicken, opens an umbrella, tosses a banana peel... and never notices the fight. The beat sheet, the cast and how to build yours in Masonry, all in the article ↓
1
64
A "What would you do?" AI story series hit 2.7M views in 12 posts, one creator says 🤯 So we made our own. A wallet on the platform: $2,000, a 12:20 ticket, and a photo of you asleep. Train, or hand it in? Reply A or B. The winning answer gets Part 2 ↓
1
504
One creator says her AI anime series hit 1M views in a day 🤯 → 4M+ in two weeks, by her count → 530K on one trope alone: "magic backfires" → 13 creators posting the same character within three weeks The format is almost too simple: > second person: the camera is your eyes > one character talks straight to you > one trope, escalated once > about 20 seconds, then she's gone So we made our own. Meet Hana, the top student. She offers to fix your crumpled paper crane with one flick of her wand. It works. Then it backfires: poof, cat ears. "That was... on purpose." Then "Meow!" slips out, and she storms off to tell the Dean. Her trope table, the 20-second shape and how to build your own series in Masonry, all in the article ↓
1
71
AI characters are getting paid. → 5.4M views on a single take → $10K in 5 days, by one creator's own count → $100K+ from ad deals for another account, per one report The format: one face, one line, one take. We broke it down and built our own character. Steal it:
This AI influencer doesn't exist. Her creator says 13 videos made $10K in 5 days. Here's the format, and how to build your own character for under $1 a take.
2
27
This AI influencer doesn't exist. Her creator says 13 videos made $10K in 5 days. Here's the format, and how to build your own character for under $1 a take.
2
1
2
296
This video is nothing short of a masterpiece 👏 Created with Seedance 2.5.
32
57
1
1,292
468,016
Masonry retweeted
AI can make 3D animation for Disney now
🤖 Made with AI
261
2,221
71
33,074
4,109,634
This AI video Animation is better than Disney 🔥 Seedance 2.5
46
302
10
3,133
327,572
Masonry retweeted
AI video editing right now is where AI coding was 1 year ago higgsfield just dropped their new model miracle and it is f*cking insane it splits any video into layers so you can edit one thing in the shot with a prompt and watch it change in real time the moment this hits higgsfield MCP i'm plugging it straight into claude
🤝 Paid partnership
Introducing Higgsfield Miracle. Our latest proprietary post-production technology vectorizes any video into layers for localized, pixel-level editing in real time, with world knowledge built in. Every frame holds the image depth needed for cinema-grade post-production. Now in private beta with select testers. Coming soon to Higgsfield MCP. Set up Higgsfield MCP in Claude to be the first to try it.
19
21
1
320
23,935
One idea. One prompt. One shot. This video was created using the Kling 03 model, entirely in one shot on Masonry. No complicated production workflow. No stitching together multiple generations. Just a creative direction translated into a video in a single run. We're exploring what's possible when powerful AI models meet the right creative workflow. And this is just one of the ways we're putting Masonry to work. Made on Masonry. Powered by Kling 03.
1
20
What used to take multiple shots, edits and iterations can now start with a single generation. This entire 9-second video was created in one shot using Kling 03 on Masonry. The creative possibilities are getting interesting. What's the first thing you'd make?
4