genmedia-labs builds skills that let an AI agent generate video, from a single still image animated into a short cinematic clip to reference-guided generation that combines images, video and audio into one output. Their most popular skills cover Seedance 2.5 and Wan 3.0 Prime on RunComfy, with documented schemas, durations, pricing and the use of named inputs such as "Image 1" or "Video 1" to keep characters and identity consistent.
Skills
3 skills · 27 stars · MIT
Seedance 2 5 Image To Video Animate a single still image into a 4-30 second 720p cinematic clip with optional synchronized na…
Seedance 2 5 Reference To Video Generate reference-guided 1080p video with ByteDance Seedance 2.5 Reference to Video on RunComfy…
Wan 3 0 Prime Reference To Video Build video clips from reference images, reference videos, and reference audio with Wan-AI Wan 3.…