
π―Skills4
A skill for generating images and videos via Higgsfield AI through 30+ models including Nano Banana 2, Veo 3.1, Kling 3.0, Seedance 2.0, Flux 2, and GPT Image 2, supporting text-to-image, image-to-image, image-to-video, and a Marketing Studio for branded ad content with curated avatars and imported products.
A skill for generating brand-quality product images through Higgsfield AI with 10 specialized photography modes including product shot, lifestyle scene, virtual model try-on, hero banner, social carousel, and ad creative pack, using mode-specific prompt enhancement on the gpt_image_2 model.
A skill for training a Soul Character on Higgsfield AI -- a personalized face model built from 5-20 photos that enables identity-faithful image and video generation. The trained Soul ID can be chained with higgsfield-generate for consistent face representation across outputs.
A skill for generating marketplace-ready product image cards through the Higgsfield CLI, including compliant main images, secondary product images, infographics, lifestyle shots, and A+ style content modules for e-commerce listings.