We’re excited to announce that Remade has been acquired by @fal !
Two years ago, we started Remade in our university dorm room with a simple idea: build an interface for creative intelligence, a place where anyone could turn imagination into something real.
Since then, this little side project turned into a wild ride: we grew a community of 8,000 creators on Discord, open-sourced models that hit over 250,000 downloads, and built the Remade canvas, an intelligent workspace used by hundreds of creative teams around the world.
Joining fal feels like the perfect next step. Their mission to accelerate generative media aligns perfectly with everything we’ve been building towards.
We're extremely grateful to our users, investors, friends, and family who made this journey possible. None of this happens without you.
The story continues, just on a bigger canvas 💫
Generate beautiful voxel game assets in minutes, built using @fal 👾
Text → Image (nano-banana-2) → 3D mesh (Hunyuan 3D v3.1) → Voxelize (with variable voxel size) → export GLB, OBJ or VOX to use in your game!
Making good progress on my game - got the meadow biome looking very close to what I imagined! 🌳
Hardest thing so far: getting a good algorithm down for procedural trees, lots of iteration on branch distribution + multi-shade leaves
Google Earth now allows importing ANY 3D model, so I used @tripoai on @fal to get Godzilla into Tokyo, and my Chrome extension to transform it into a movie scene 🎥
I love using fal to make developing fal easier.
Using GPT Image 2 + Seedance 2 and review and prompt instruction is done by Opus 4.7 with Claude Managed Agents
To celebrate GPT Image 2 launching on @fal, I've made some BIG improvements to the sprite sheet creator!
What's new:
→ GPT Image 2 support (low/medium/high quality)
→ Sprite size sliders to fix scale without regenerating
→ Map size + position sliders for quick alignment fixes
Full side-scroller flow on GPT Image 2 low ≈ $0.08
The universe in your browser 🌌
1.4M real galaxies and quasars from DESI DR1, positioned by their spectroscopic redshifts via Planck18 cosmology, rendered in three.js. Click a point for its sky coordinates and lookback time, then @fal's FLUX.2 klein imagines what it looks like
Image to world + image to playable character to explore it! 🍻
Made this app using image-to-world through @theworldlabs, image-to-3D + auto-rigging through @MeshyAI on @fal, rendered with Spark.js + three.js
Turn any webpage into a museum! 🏛️
Made this Chrome extension that uses Hunyuan 3D v3.1 on @fal to turn any image into a 3D model, and three.js for the interactive viewer
Minecraft 3D generation now at the highest quality ever, built using @fal ⛏️
Text → Image (nano-banana-pro) → 3D mesh (Hunyuan 3D v3.1) → Voxelize → Texture mapping → Minecraft structure!
Built Diffusion Canvas an infinite 2D canvas where every direction is a different prompt.
Define two semantic axes, pan around, and images generate in real-time as you explore the latent space. Every pixel coordinate is a unique point in embedding space.
In 432 BC the Parthenon was covered in bright painted colors. I wanted to see what that looked like, so I made this @fal-powered Chrome extension to capture anywhere on Google Earth, transform it, and turn it into a beautiful drone shot 🏛️
Generate ANY playable character in Unreal Engine 5, built using @fal 🎮
Text → 3D model (Hunyuan 3D v3.1) → auto-rig & animate (@MeshyAI) → playable character!