Wan 2.7 via dLazy — model skill for cinematic & short films

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.

Text, first/last-frame and reference-to-video with Alibaba's Wan 2.7, 2–15 s clips, through the dLazy CLI.

What it does

Runs Alibaba's Tongyi Wanxiang (Wan) 2.7 video model through the dLazy hosted service with the dlazy wan2.7 CLI command. Components mode takes up to 5 reference images and 5 reference videos; frames mode takes a first and last frame; both accept an optional audio file. Clips run 2–15 s at 720P or 1080P, and prompt rewriting is on by default. The SKILL.md is a flag reference only.

Use when

Install

Models it drives: wan_2_7

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.