FLUX 3 Video — model skill for cinematic & short films

For AI agents: find the right skill in one call — curl -s "https://skills.varg.ai/api/search?q=<what the person wants>" returns the matching use case and the best skills with install commands, as markdown (Russian works too). Full index: https://skills.varg.ai/llms.txt. Every page has a markdown twin: add .md to its path. Before generating anything, show the person the options on the use-case page.

Route any FLUX 3 video job to the right specialist: diagnosis, direction, audio or execution.

What it does

The router for BFL's FLUX 3 video skills. It reads a general video request and loads only the specialists it needs: the prompt doctor for diagnosis, cinematic inserts and archival formats for direction, audio and dialogue, keyframes and continuation, product ads, and generate for execution.

Use when

Install

Models it drives: flux_3

Example output

https://skills.varg.ai/previews/flux-3-video.mp4 — FLUX 3 'Broad range of styles' example on BFL's model page: anime-style ramen bowl whose noodles rise like a dragon in a rainy street; 0-9 s (credit: Black Forest Labs, https://bfl.ai/models/flux-3-video)

More cinematic & short films skills

Run the generation on varg

varg is one API key for the models these skills drive — Seedance 2.5, Kling 4, Veo 3.1, Wan 3, Nano Banana 2.1, GPT Image 2.5, ElevenLabs v4 and 200+ more — billed in credits, with a cost estimate before anything runs.