crisng95

crisng95 / flowboard

Public

Flowboard — open-source infinite canvas for AI product videos. Drag nodes for model, product, scene, video — connect them, click Generate. Auto-prompts write themselves. Runs locally; powered by Google Flow + Claude CLI.

ai claude-cli google-flow video
49
43
100% credibility
Found Apr 28, 2026 at 49 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

Flowboard is a local infinite-canvas app for building reusable AI media workflows like characters, products, scenes, and videos using graph connections.

How It Works

1
🔍 Discover Flowboard

You find a simple canvas tool that makes creating product videos easier by reusing characters and outfits without retyping prompts every time.

2
🧩 Set up your helpers

Load a small browser add-on and start the local app so everything connects smoothly on your computer.

3
🔗 Link your AI tools

Open your video maker site in the browser and let the app grab your login so generations work privately.

4
🎨 Build your scene

Drag characters, products, and scenes onto an infinite canvas and connect them like building blocks—everything reuses perfectly.

5
✨ Generate with one click

Click generate on an image or video spot, and it pulls details from connected pieces to create fresh variants automatically.

🎉 Your videos are ready

Watch your full campaign of reusable clips come alive, all from one organized canvas you can tweak anytime.

Sign up to see the full architecture

4 more

Sign Up Free

Star Growth

See how this repo grew from 49 to 49 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is flowboard?

Flowboard delivers an infinite canvas for crafting AI product videos locally. Drag nodes for models, products, scenes, or clips, connect them to wire dependencies, click generate—auto-prompts via Claude CLI synthesize fashion-editorial text from upstream refs, feeding Google Flow's Veo i2v models through a Chrome extension proxy. Python FastAPI backend pairs with React canvas for single-user workflows, turning repetitive e-com creative into reusable graphs.

Why is it gaining traction?

Graph nodes make refs one-time uploads with real data flows—compositions spawn variant batches, videos i2v direct from images with scene-smart motion (street glances vs studio tilts). Auto-prompts adapt via local Claude CLI (no cloud keys), and one-click batches handle 4-up variants without prompt copy-paste. Beats generic UIs by persisting campaigns as editable canvases.

Who should use this?

E-com teams producing model-in-garment clips across scenes like Seoul streets or autumn roads. Fashion creators needing consistent identity in Veo videos. Devs hacking AI media prototypes with drag-connect-generate flows.

Verdict

Grab it if you have Google Flow Pro/Ultra—190 tests pass, docs shine, but 49 stars and 1.0% credibility signal early personal tool. Setup hurdles (extension, CLI) limit broad appeal; solid for matching niches.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.