Generate text-to-video clips with Wan 2.7 through the RunComfy CLI.
npx skills add https://github.com/brillianodhiya/VisionScript --skill wan-2-7-brillianodhiya
Please help me install this Agent Skill. Skill: wan-2-7 Source: https://github.com/brillianodhiya/VisionScript/tree/main/.agents/skills/wan-2-7 Command: npx skills add https://github.com/brillianodhiya/VisionScript --skill wan-2-7-brillianodhiya
runcomfy run wan-ai/wan-2-7/text-to-video with a documented schema covering prompt, duration (2-15s), resolution (720p/1080p), and five aspect ratios. - Audio-Driven Lip-Sync: Accepts a user-supplied audio_url (WAV/MP3, 3-30s, ≤15MB) to drive lip-sync, enabling spokesperson ads and multi-language dub variants. - Model Routing Guidance: Includes a decision table for when to use HappyHorse 1.0, Seedance 2.0 Pro, Kling Video O1, or LTX 2 instead. - Use Case: A marketer needs a 12-second vertical lip-synced spokesperson clip with their own voiceover track; the Skill builds the correct JSON input with audio_url, aspect_ratio: 9:16, and duration: 12 and runs it through the CLI. ## Quick Start Ask the AI to generate a video with Wan 2.7 from your prompt, optionally providing an audio URL for lip-sync and specifying duration, resolution, and aspect ratio.High-intent search queries and answers about installing and using this skill.
Run `runcomfy run wan-ai/wan-2-7/text-to-video` with a JSON input containing your prompt and an output directory. Defaults are 5 seconds, 1080p, and 16:9, with prompt expansion enabled.
Pass an `audio_url` field pointing to a WAV or MP3 file that is 3-30 seconds long and under 15MB. Wan 2.7 uses that track to drive lip-sync; omitting it auto-generates background music instead.
Wan 2.7 fits lip-sync with supplied audio, multi-reference motion control, and smooth transitions. Seedance 2.0 Pro handles in-pass voice generation and multi-modal cinematic refs, while Kling Video O1 targets motion editing on existing footage.
Duration is capped at 15 seconds per call (2-15 whole seconds), resolution tops out at 1080p with no native 4K, and only five aspect ratios are supported: 16:9, 9:16, 1:1, 4:3, and 3:4.
Audio files must be WAV or MP3 format, between 3 and 30 seconds, and no larger than 15MB. Files outside these specs are rejected, so match the audio length to your clip duration.
Set `enable_prompt_expansion` to false in the JSON input. This prevents the model from auto-rewriting short prompts, which is useful for brand-strict ad copy that must be rendered verbatim.
runcomfy-comGenerate text-to-video clips with optional audio-driven lip-sync via RunComfy.
prime-skillsExtend existing video clips with Veo continuation endpoints.
agentspace-soTranslate user prompts into HappyHorse 1.0 text-to-video API payloads for RunComfy.
Pixazo-AIGenerates videos from text, images, and references via the Seedance API on Pixazo.