Route inputs to avatar-generation models via the RunComfy CLI.
npx skills add https://github.com/doany-ai/skills --skill ai-avatar-video-doany-ai
Please help me install this Agent Skill. Skill: ai-avatar-video Source: https://github.com/doany-ai/skills/tree/main/ai-avatar-video Command: npx skills add https://github.com/doany-ai/skills --skill ai-avatar-video-doany-ai
This Skill lets you create engaging AI avatar videos from a single portrait and audio or scripted prompts, automating the most common animation workflows without manual rigging.
Install the RunComfy CLI and run a sample avatar video with a portrait and audio using ai-avatar-video.
High-intent search queries and answers about installing and using this skill.
To create an AI avatar video, provide a portrait image and an audio file to trigger the OmniHuman model for lip-sync animation. The Skill routes your inputs automatically and uses the RunComfy CLI to generate and download the final video.
The best way to generate lip-sync animation from a single portrait is using the Wan 2-7 open-weights model. This Skill routes your portrait and audio inputs to the appropriate model to automate the animation workflow without manual rigging.
Yes, you can animate a stylized full-body character by routing your inputs to the Wan-2-2 Animate model. The Skill supports both photoreal portraits and stylized characters for versatile avatar video generation.
You do not need an audio file to generate a cinematic avatar scene. You can use scripted text prompts with the Seedance v2 Pro model for cinematic scenes, or HappyHorse for script-to-video generation, bypassing the audio requirement.
The Skill chooses the AI model based on your inputs: it checks whether an audio file is provided and whether the subject is photoreal or stylized. It then routes the request to OmniHuman, Wan 2-7, Wan-2-2 Animate, HappyHorse, or Seedance accordingly.
You need to install the RunComfy CLI to run AI avatar video workflows. The Skill invokes the CLI with the appropriate model ID and payload, then downloads the generated avatar video results to your specified output directory.
runcomfy-comRoute still images to RunComfy image-to-video models for animated video output.
fianchettogianniGenerate marketing videos with AI footage, avatars, and programmatic templates.
doany-aiRoute image-to-video requests to RunComfy models by intent.
prime-skillsSynchronize facial mouth movements with audio to produce lip-synced video.
