Generate Wan 2.7 videos from text prompts via RunComfy CLI.
npx skills add https://github.com/doany-ai/skills --skill wan-2-7-doany-ai
Please help me install this Agent Skill. Skill: wan-2-7 Source: https://github.com/doany-ai/skills/tree/main/wan-2-7 Command: npx skills add https://github.com/doany-ai/skills --skill wan-2-7-doany-ai
Wan-2-7 simplifies the creation of high-quality text-to-video content by providing a flexible, lip-sync capable model with multi-reference conditioning, enabling creators to produce cinematic video outputs directly within RunComfy.
Provide a prompt and an optional audio_url to generate a Wan 2.7 video through RunComfy.
High-intent search queries and answers about installing and using this skill.
To generate a lip-synced video, provide a text prompt and an optional audio_url to synchronize speech with visuals. The system processes these inputs via the RunComfy CLI to produce a cinematic video file.
Text-to-video generation supports 720p and 1080p resolutions. It includes a 16:9 family of aspect ratios, specifically supporting 16:9, 9:16, 1:1, 4:3, and 3:4 formats.
Prompt expansion is enabled by default to improve cinematic video output quality. You can easily disable this feature if you require the model to strictly follow your literal text prompts.
Multi-reference conditioning provides richer motion control and cinematic quality in video generation. It allows the model to process multiple visual references simultaneously to guide the output.
A generated video clip can be between 2 and 15 seconds long. You can specify the exact duration within this range when configuring your text-to-video generation parameters.
You should use alternative models like HappyHorse 1.0, Seedance 2.0 Pro, Kling, or LTX 2 when a different capability is required. Wan 2.7 is optimized for lip-syncing and multi-reference cinematic outputs.
runcomfy-comRoute text-to-video, image-to-video, and video-extend requests to RunComfy model endpoints.
prime-skillsGenerate text-to-video clips with Wan 2.7 via the RunComfy Model API.
agentspace-soCreate avatar videos from audio or scripts via RunComfy model routing.
doany-aiGenerate text-to-video content with synchronized audio via RunComfy.
