665,000+ skills indexed

yangyixxxxCOMMUNITY

Explore all skills by this author →

Verified:GitHub

gptnb-image

Generate images, layered assets, and videos via the gptnb.ai middleware API.

13|2|Updated May 4, 2026

Search Tags:#poster design #image generation #video generation #text-to-video #seedance #gptnb #layered images

One-click install

npx skills add https://github.com/yangyixxxx/gptnb-image --skill gptnb-image

Or copy as Structured Prompt for Agent▼

Please help me install this Agent Skill.
Skill: gptnb-image
Source: https://github.com/yangyixxxx/gptnb-image/tree/main
Command: npx skills add https://github.com/yangyixxxx/gptnb-image --skill gptnb-image

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill eliminates the need for manual design work or multiple disconnected tools to create visual content, letting users generate professional images, layered graphic assets, and short videos on demand via the gptnb.ai middleware service.

Core Features & Use Cases

Image Generation: Supports text-to-image, layered poster generation (splitting designs into transparent PNG layers), and image editing via the gpt-image-2 and gpt-image-2-vip models.
Video Generation: Supports text-to-video, image-to-video, first-to-last frame video, and multi-reference video synthesis with optional synchronized audio via the seedance model series.
Use Case: Marketing teams can quickly generate promotional posters and matching short social media videos for product launches without hiring dedicated designers.

Quick Start

Use the gptnb-image skill to generate a cyberpunk-style city night poster with split transparent layers, or create a 5-second video of a kitten yawning that includes synchronized background audio.

Frequently Asked Questions about gptnb-image

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I generate layered poster images with transparent PNG layers for marketing?▼

Layered poster generation splits a design into transparent PNG layers using the gpt-image-2 model. You provide text prompts and receive separated graphic assets ready for compositional editing in promotional campaigns.

Can I create a short video from text with synchronized background audio?▼

Text-to-video creation with synchronized background audio is supported via the seedance model series. You input a text prompt and receive a short video output with matching generated audio tracks.

What's the best way to animate an existing image into a video?▼

Image-to-video animation is achieved through the seedance model series. You supply a static image as the input reference and generate a dynamic short video clip based on that visual starting point.

Does gptnb-image support multi-reference video synthesis for social media content?▼

Multi-reference video synthesis is supported for social media content creation. You provide multiple reference inputs and the seedance models generate a cohesive video combining those visual elements.

How do I generate a video using first and last frame images?▼

First-to-last frame video generation is supported by the seedance model series. You provide starting and ending frame images to interpolate and generate the intermediate video sequence.

Can I edit generated images without starting over from scratch?▼

Image editing is supported via the gpt-image-2 and gpt-image-2-vip models. You can modify existing generated images or layered graphic assets directly without needing to recreate the visual from a text prompt.

Related Skills

Explore More Design & Creative Skills→

seedance-video

Automate AI video generation from text and images via Ark API.

music-video-production

Convert a recorded song into a synchronized, rights-aware music video production plan.

Gundlapuriswathiii006

remove-image-background

Remove image backgrounds and output transparent PNG files.

fal.ai

Generate images from text prompts via the fal.ai API.