Many Models, One Workflow — with Bria and Cloudflare Replicate
Hosted by
◕‿◕
ʘ‿ʘ
A year ago, the question was "which model?"
Today it's "which model for which job — and how do they wire together?"
Devs building real AI pipelines have stopped picking favorites. They're routing across dozens of models through Cloudflare Replicate, then composing the output with editing and control layers like Bria — background removal, generative fill, structured JSON prompts (FIBO), video tools with 1:1 audio preservation.
The new craft isn't prompting. It's orchestration.
For one night during NY Tech Week, we're putting the engineers building this layer in the same room. Come for working patterns, not slideware.
Every RSVP gets free Cloudflare Replicate + Bria API credits — leave with enough to wire something real that night.
What you'll take home
— How teams are routing tasks across model providers in production
— Where editing/control APIs fit in the stack (and where they don't)
— Cost, latency, and quality tradeoffs nobody puts in the docs
— What's actually shipping vs. what's still a demo
Schedule
5:00 — Doors, drinks, mingling
5:45 — Fireside chat + audience Q&A
6:15 — Food, drinks, more conversation
7:30 — Wrap
Speakers
Chris MacDonald — Head of Solutions, Bria
Jon Bunting — Senior AI Solutions Architect, Cloudflare Replicate
Bria
The licensed, IP-safe visual AI platform for editing and control — background removal, generative fill, structured prompts, and video tools built for production.
Cloudflare Replicate
The inference platform for thousands of open and proprietary models — one API to run, fine-tune, and ship them at scale.
Guest List
12 on the list
❛ᴗ❛
ᵔᴥᵔ
^⎵^
Restricted Access
Must be on the list to view event activity & see list details