Facetune runs nearly 70 latency-critical AI features and services on fal Serverless, with performance up to 39% faster than before the migration.

Facetune is one of the world's most known apps, with millions of MAUs who use Facetune to feel like their best version. Its newest features are generative: skin retouching, object removal, lighting, hairstyles, and instruction-based edits. Each feature is a diffusion pipeline that must return a result within seconds - to support a quick iteration cycle and a positive user experience.
The challenge
A Facetune edit starts with a tap, and the user expects a result almost immediately. Every delay adds up across a session, and speed can't come at the cost of identity preservation, realism, or image quality.
On its previous inference setup, the same team that builds Facetune's models also ran the serving stack: Kubernetes clusters, per-feature GPU capacity, scaling, and monitoring. Given the strategic nature of these tasks, the Facetune team decided to find a serving partner that could take on the load while meeting a strict latency bar - this is how fal become a part of Facetune's daily operations.
Preparing the ground
Facetune spent four weeks of infrastructure work turning its existing workers into fal workers. Once that foundation was in place, the integration itself went quickly, and feature after feature moved to fal.
Running on fal
- One app per feature. Each feature runs as its own fal app, with its own queue and autoscaling.
- Capacity that follows the traffic. Dedicated reserved capacity covers Facetune's baseline, and the same apps burst onto fal's shared fleet at peak, so Facetune no longer provisions GPUs by hand for every feature.
- Monitoring inside Facetune's stack. Facetune's Grafana scrapes fal's Prometheus metrics endpoint, placing request latency, queue depth, and GPU, VRAM, and CPU utilization next to Facetune's own application metrics. Scoped API keys mean the monitoring integration never carries deploy permissions.
- Shared alerting. Alerts designed with Facetune's engineers watch for traffic drops, requests queuing for a GPU, and server-error spikes, and post to a shared channel.
- Stable through the move. Reliability held through the cutover and the tuning work that followed.
Diagnosing a slow start
Right after migrations, some features took a hit in performance. All rides can start off bumpy, but the dedication and collaboration from the fal Serverless team is what made them the right partner. fal's team was responsive and creative, and worked side-by-side with Facetune's team to support a quick mitigation and further optimize runtimes. Today, every feature measured runs faster on fal than it did on the previous setup, between 9% and 39%.
| Feature | Previous setup | fal, after optimization | Now vs previous setup |
|---|---|---|---|
| Vanish (object removal) | 1.00 s | 0.91 s | 9% faster |
| Skin retouching | 0.78 s | 0.70 s | 10% faster |
| Hair color | 1.81 s | 1.30 s | 28% faster |
| Lighting | 2.88 s | 1.76 s | 39% faster |
Working together
Throughout the process, fal stayed close to Facetune's team. It joined the weekly investigation, gave Facetune control over traffic, and built the monitoring Facetune asked for.
"When latency and uptime matter, fal shows up. They tuned inference across datacenters, built the monitoring we asked for, and stayed close to our team every step of the way. They understand our requirements and their importance to our business, and operate as true partners and not only providers."
Gilad Schreiber, Engineering Manager, AI Features & Backend, Facetune
Facetune builds the models and pipelines and sets the quality bar. fal runs the serving layer underneath. The two teams keep working from the same data toward the same latency goal.
.png)


