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
Having a lot of fun building a tool inside Rive runtime ! here's a sneak peek of a way to draw in Blender to AI so that it does proper VFX for the upcoming (hopefully if I meet deadlines lol) haloween submission
Nice project @dat
That´s what I'm talking about, looking great!!! @Dat dsgnr
which AI are you using, Sonnet 5.5 is doing all the work for me actually
this looks pretty awesome
Thanks @Jonathan Haines ! Can't wait to see the whole thing coming together ahah
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
Related posts
The Haunted Room is an interactive, cozy-spooky desktop fidget toy, a little haunted parlor you can leave open on your screen and poke at whenever you need a break.
No instructions. No hints. Nothing will tell you what to press. Just a cozy haunted room full of secrets, waiting to be poked at your own pace.
▶️ Play it on desktop: https://haunted-room-wcc682.rive.to/
🎬 Watch video on YouTube: https://youtu.be/xDFD62jbs_I
FEATURES USED: Rive CLI + GPU Canvas (both) 🖥️ Rive CLI The entire scene was built from the terminal with the Rive CLI and Claude Code as my coding agent, writing the scene in RML with a live preview.
I worked in stages: layout first, then one interaction at a time, iterating by feel on every timing and effect.
✨ GPU Canvas (WGSL shaders) Custom shaders power the animated fireplace, the rippling portrait transformation and the twinkling stars in the landscape painting. ⚙️ Also used: State Machines (every hover and click interaction), Data Binding (a view model links the systems together, so lighting the fire warms the room, deepens the shadows and scares away the wall eyes), Scripting (looping background music with a mute toggle) and Audio.
🎨 Human Touch I art-directed the whole room: generated a concept, then cut, cleaned and composited every piece of art by hand. I made the calls on what stayed and what went. A bandage whip, a "Happy Halloween" garland and a spider web were all built and cut because they crowded the scene. I finished it in the Rive Editor, adding shadows by hand so every object sits in the room. The music was picked to feel playful-haunted, not scary, so it's something you'd actually want to leave running.
App and video created by Ashley Phillips
Music: Mikhail Smusev via Pixabay
Sound effects: freesound_community via Pixabay
Voice: ElevenLabs generated
Wow! Exactly the horror vibes I love.
All Eyes on You!!👀
100 eyes. One cursor. And absolutely nowhere to hide.
Built for the Rive Halloween Challenge with RML, Luau, and WGSL shaders.
looking scary af 🔥
Can a designer push Lovable as hard as any design tool?
Yes, and the method is simpler than you'd think. Three steps. I'll show each one on real slides from this challenge.
First, why I'm back. I sat out the last couple of challenges: I needed a real break, and other projects needed me more. I hadn't opened Lovable in a bit over a year. When this one landed, I thought: let's see if a designer can take it to the limit, the way I do with every other tool. So far, it's holding.
The client is Endorphin, a run club in Turin. Every Thursday, 19:00, under the Arco del Valentino, free, any pace. Here's the method.
1. Design every state before you prompt. Default, hover, spots left, full, waitlist, booked, past. Look at the third slide: each chip is a different state of the same event, "You're in", "23 left", "31 going". If a state isn't designed, Lovable guesses it. So I never leave it a guess.
2. Write the prompt like a spec. Real sizes, real colors, real timings. Mine says things like: the slide takes 480ms, easing cubic-bezier(0.2, 0.8, 0.2, 1), no bounce. Then I attach the Figma export of that exact state and write "match this pixel for pixel". That's how the calendar on the last slide got its hover: the cell lifts, a preview card shows cover, time, place and spots left, and Book sits right there.
3. One prompt at a time. I send a piece, compare it with my board, and only then send the next. The phone view on slide two came out that way: a booking sheet with two fields and one line, "No account. No password. Just show up." Above it, a molecule where every dot is a moment from a Thursday.
The first slide shows the result of all three: the whole night as single cards. Price, distance, time, meeting point, crowd. One idea each.
The tool is only as sharp as the brief you give it.
If you've built with an AI tool: where did you hit the wall first, design or logic?
great designs, all made in lovable right?