genmedia-labs

Consistent characters, products, and scenes are difficult to maintain across generated video. This skill builds structured Wan 3.0 Prime requests from numbered references.

Choosing the wrong video model wastes time and weakens identity or motion consistency. This skill routes each edit to a suitable RunComfy model with focused prompts.

Keeping characters, products, and visual style consistent across generated video is difficult. This skill builds and runs reference-guided Seedance 2.5 requests through RunComfy.

Static images cannot show motion, camera movement, or synchronized sound. This skill creates directed 720p clips from one image through Seedance 2.5.

Choosing an image-to-video model and its parameters can require repeated testing. This skill routes each request and provides focused RunComfy invocation guidance.

Choosing and prompting video models requires detailed model knowledge. This skill routes each request and prepares focused RunComfy CLI invocations.

Choosing a music model and formatting its inputs can slow production. This skill routes requests and prepares RunComfy CLI commands for generation, inpainting, and extension.

Choosing an image model and its parameters can slow creative work. This skill routes requests to suitable RunComfy models and provides focused prompts and commands.