Top Up (Higgsfield Open-Source Cinematic Ad) — prompt skill for ads & UGC

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

Higgsfield's 106 s soda ad breakdown: a drained athlete becomes a robot gladiator who must run dry to win.

What it does

One soda turns a drained athlete into a robot gladiator, but to win he has to lose everything, run dry and power up one last time. Published as a carousel breakdown of the shots. Higgsfield published it from its @adilinthewild account as an open project: the page shows the finished film next to the canvas with every generation behind it, its prompt, model and reference assets, so you can study how each shot was made and remix it. Behind it: 255 generations, 54,809 Higgsfield credits, 8 MB of assets; models by share of generations: Seedance 2.0 80.4%, Soul Cinematic 16.8%. Use it as a reference for structure, shot prompts and character consistency; to make your own version, rebuild the shots with the same models in varg (Seedance 2.0) or on Higgsfield.

Use when

Not for

Install

Not published as a standalone skill yet. Source: https://higgsfield.ai/@adilinthewild/projects/top-up

Models it drives: seedance_2

Example output

https://static.higgsfield.ai/og/v4/project/b9c635b6-4ff7-4f54-9459-04fcc913fc0f-xc3s2g.jpg — Higgsfield's own share card for the Top Up project page (key art and title); linked, not re-hosted. (credit: Higgsfield, https://higgsfield.ai/@adilinthewild/projects/top-up)

More ads & UGC 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.