Route face swaps in images and videos to RunComfy model endpoints.
npx skills add https://github.com/runcomfy-com/skills --skill face-swap
Please help me install this Agent Skill. Skill: face-swap Source: https://github.com/runcomfy-com/skills/tree/main/face-swap Command: npx skills add https://github.com/runcomfy-com/skills --skill face-swap
Face-swap helps you substitute one identity’s face into still images or videos by routing to the right RunComfy model endpoints based on whether the input is a photo or a video and whether you need motion preservation.
Use the face-swap skill to swap a face into a video by providing a target identity image and an audio track as inputs to runcomfy.
High-intent search queries and answers about installing and using this skill.
To swap a face into a video with audio-driven motion, you provide a target identity image and an audio track. The skill routes these inputs to the Wan 2-2 Animate model to generate a talking character with the substituted identity.
The best way to preserve motion during an identity swap is using the Kling 2-6 Motion Control Pro route. This transfers the performance from a reference video directly onto your target character image.
Yes, you can perform batch identity-consistent face swaps across still images. The skill uses the Nano Banana 2 Edit model route to ensure strong fidelity and consistent identity substitution throughout the batch.
Yes, multi-reference compositional face swaps are supported. The skill routes your structured JSON inputs to the GPT Image 2 Edit model endpoint to execute precise compositional identity substitutions.
For a single-image face swap with high fidelity, the skill routes your declarative instruction and image to the Flux Kontext Pro model. This endpoint handles precise, high-quality identity substitution in still photos.
Yes, you must provide structured JSON inputs matching the endpoint's expected fields. The skill calls the RunComfy CLI with an allowlisted model API route, requiring correctly structured data for still or video processing.
prime-skillsReplaces faces or characters in images and videos via RunComfy APIs.
shige1014-devSwap a face from a source image into a target video via HeyGen's FaceswapNode workflow.
prime-skillsRoute image editing requests to the appropriate RunComfy model and execute them.
agentspace-soRoute image editing requests to the appropriate RunComfy edit model.
