The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
I built Threadline for the $100k Higgsfield App Contest
I just entered Threadline into the Higgsfield App Contest — an AI launch studio for streetwear and fashion brands. Upload one product mockup, and it turns into a full launch pack: styled product photos, a lookbook video, a UGC-style clip, and ready-to-post captions.
The whole thing was built by Claude, through Higgsfield's own MCP server — direct git access to the app's repo, real deploys, iterating live against the actual running app instead of a local mockup. No hand-written scaffolding.
A few things I focused on: mixing different AI models per asset (or locking one model so the same person shows up across every photo and video), editing any generated photo with a prompt, and a full history so nothing you generate is ever lost. Full technical breakdown, including what I ran into building on Higgsfield's own design system: https://contra.com/p/mP2FqcZc-ai-powered-app-threadline-for-higgsfield-supercomputer
Try it live: threadline.higgsfield.app — or on the Higgsfield platform itself: https://higgsfield.ai/supercomputer/apps/0eabe215-ee8b-4c39-9457-b3ae3cca9004/view
If you're in this community and already build with Higgsfield — come test it and tell me what's broken and what could be better. This is v1, and I want to keep pushing it until it's an actual tool people reach for, not just a contest demo.
Turning one mockup into a full lookbook video with consistent style is pure magic. The fact that this was built as a real tool rather than just a demo really shows. Super impressive v1 ❤️ go get that win! 🚀🚀🚀
Thank you so much, this really means a lot! 🙏 Already collecting feedback for v2 — if anything comes to mind after playing with it more, I'd love to hear it!
Claude iterating live against the actual running app through Higgsfield's MCP server instead of a local mockup is a pretty different workflow than most people are describing right now. What broke first when you moved from local scaffolding to deploying straight against the real app?
There wasn’t a local mockup at all — I went straight into Higgsfield’s design system from day one. And honestly, I was impressed by how solid and complete it is, so I wouldn’t say anything really “broke.” It’s more about understanding the platform and its specific design...
Super impressive work🔥
Thank you so much — really appreciate that!
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Trending
Claude
Claude has entered the design space. How are you using Claude Design?
Contra University
Learn from expert creatives how to earn more using next-gen AI tools.
creativeaiflow
Creative AI workflows are evolving. What tools do you use, and what are their strengths and weaknesses?
freelancerlife
Freelancer life is wins, pivots, and everything in between. What’s yours right now?
Related posts
Terra — AI Environmental Risk Platform
Designed the landing page and product UI for Terra — a platform that helps land developers and engineering teams see environmental risk (soil stability, tree canopy loss, water table depth) before breaking ground.
The challenge:
Development decisions are usually based on estimates, not real ground data — and by the time issues show up, it’s often too late to reverse them. The interface needed to make complex sensor/AI data feel immediate and trustworthy, without losing emotional weight.
The solution:
Raw, organic photography (wildflowers, grass, natural terrain) paired with clean glass-panel data cards — creating a visual tension between “nature” and “precision engineering.” Bold editorial typography carries the emotional message, while translucent metric cards surface real numbers: soil stability, canopy loss %, water table depth.
A strong example of turning dense environmental data into something a non-technical stakeholder can understand in seconds.
Nice one
The Future in Black was built for Joy Fennell to hold a story that needed more than a standard portfolio site. Our goal from the start was to make the site feel archival and alive at once, part digital exhibit, part living brand presence, so every design decision was made to support that feeling rather than just present information.
We started with structure: how should a visitor move through this content, and what pace should that movement have? That question shaped our use of Finish Layer's block animations. Text reveals on scroll, so the story unfolds in beats instead of arriving all at once, closer to reading a book than scrolling a website. Images use hover interactions to invite a second look without pulling focus from the words around them.
From there we layered in movement. Shapes transform and shift position as the visitor scrolls, adding depth and a sense of motion that a static layout couldn't carry. This was the piece that took the most iteration, getting the timing and scale of these transforms to feel intentional rather than gimmicky meant testing several versions before landing on the current pacing.
Typography carried a lot of the brand's identity, so we uploaded Million and Inter Tight rather than relying on Squarespace's native font library. Million gives the site its editorial voice in headlines, and Inter Tight keeps body copy clean and legible against it.
The result is a site built on Squarespace's foundation, using Finish Layer's native tools alongside custom CSS and JS, pushed toward something that reads as custom, editorial, and specific to one person's story rather than a repeatable formula.
FigmasquarespacedesignsquarespacewebsitesSquarespace Website DesignWebsite CSSSquarespacesquarespacechallenge
Hey @Golden Launch this is awesome but it looks like the link you included in the comments isn't working. make sure the link is active in order for your submission to be judged 😃
Apocrypha: Human by Design
For the EnvatoChallenge, I wanted to explore a different relationship between AI and creativity.
I created Apocrypha, a collectible card universe where every artifact begins as an AI-assisted concept but only becomes part of the archive through human taste, creative direction, and design.
Instead of asking AI to create finished pieces, I used Envato as the main creative toolkit throughout the entire project. I explored its stock image and video library to build moodboards, collect textures, study compositions, and define the visual language of the world. I also used Envato AI to generate concepts for characters, artifacts, and environments, then refined, combined, and reworked them into a cohesive universe. Some of the concepts were even manually painted over to push them beyond the original AI output.
Alongside the cards, I designed ArchiveOS, a living creative bible where I organize collections, lore, references, prompts, and every creative decision behind the project. It became the place where the entire world of Apocrypha could grow consistently.
The biggest creative decision wasn't generating images. It was deciding what deserved to exist. Knowing when an idea felt wrong, when an artwork needed more work, when a concept should evolve, or when it should be discarded completely. AI gave me possibilities, but every final artifact exists because of human judgment.
I'd love to hear what you think about this approach to AI-assisted worldbuilding.
