The Dusk (Higgsfield Open-Source Drama Episode) — prompt skill for stories & short dramas

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 88 s muted, grainy school drama: a pale boy's quiet warning and a guarded girl's wary silence.

What it does

A muted, grainy schoolyard moment under grey skies: a pale boy's quiet warning and a guarded girl's steady, wary silence. Higgsfield published it from its @merumeru account as an open project: the page shows the finished film (1 min 28 s) 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: 861 generations, 242,708 Higgsfield credits, 18.4 GB of assets; models by share of generations: Seedance 2.0 53.7%, Seedance 2.5 34.8%, Seedream 5.0 Pro 2.6%, Higgsfield Soul V2 2.6%, GPT Image 2.0 2.4%. 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, Seedance 2.5, Seedream 5.0 Pro, GPT Image 2.0) or on Higgsfield.

Use when

Not for

Install

Not published as a standalone skill yet. Source: https://higgsfield.ai/@merumeru/projects/dusk

Models it drives: seedance_2, seedance_2_5, seedream_5_pro, gpt_image_2

Example output

https://static.higgsfield.ai/og/v4/project/60ea55a4-7275-4e39-951a-c23a99bf1d09-1726mjg.jpg — Higgsfield's own share card for the The Dusk project page (key art and title); linked, not re-hosted. (credit: Higgsfield, https://higgsfield.ai/@merumeru/projects/dusk)

More stories & short dramas 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.