dLazy Video Generate — 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.

Picks a video model for your prompt from about 20 on dLazy (Jimeng, Kling, Veo, Seedance, Wan, PixVerse) and runs it

What it does

A model router that goes through the dLazy hosted service and its dlazy CLI. The agent picks one of about 20 video models listed in the SKILL.md (Jimeng, Kling V3 and Omni, Veo 3.1, Seedance 2.0/2.5, Wan 2.7, PixVerse C1, Vidu Q2, MiniMax Hailuo, OmniHuman 1.5 avatars, and lip-sync tools such as HeyGen, sync-lipsync 3 and VideoRetalk), checks its flags with dlazy <model> -h, and runs it. Commands can be piped so an image from one step feeds the next. All models are reached through dLazy, not the original providers.

Use when

Install

Models it drives: jimeng, kling_v3, kling_v3_omni, veo_3_1, veo_3_1_fast, seedance_2_0, seedance_2_5, wan_2_7, pixverse_c1, vidu_q2, omnihuman_1_5, minimax-hailuo

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.