skills.rest
ahostbr
ahostbrCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

ls-gen-image-or-video

Generate AI images or short videos from text prompts with optional reference images.

Updated Aug 5, 2026
Search Tags:#image#marketing assets#video#gemini api#generate#prompt#veo
One-click install
npx skills add https://github.com/ahostbr/liteharness --skill ls-gen-image-or-video
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ls-gen-image-or-video
Source: https://github.com/ahostbr/liteharness/tree/main/liteharness/catalog/skills/ls-gen-image-or-video
Command: npx skills add https://github.com/ahostbr/liteharness --skill ls-gen-image-or-video

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires google-genai, python-dotenv, Pillow, websockets, requests, and includes scripts (resource) components.

What problem does it solve?

It helps you turn a textual concept into production-ready AI image or video assets without manually dealing with multiple tools, formats, and workflows.

Core Features & Use Cases

  • Image generation (with optional references): Create marketing visuals like hero banners, product mockups, social posts, thumbnails, and infographics from text prompts and reference images.
  • Video generation (text-to-video and image-to-video): Produce animated backgrounds, scroll-synced style clips, cinematic product shots, and Veo-based short videos.
  • Interactive parameter collection: Uses an AskUserQuestion-first flow to capture required settings such as aspect ratio, resolution, duration/model, and output location.
  • Post-processing support: Guidance includes background removal for generated images and optional scroll-asset frame extraction after video generation.
  • Fallbacks and multiple backends: Supports Gemini API by default, with routes through Codex Desktop, ChatGPT Desktop CDP, browser fallback, local SD (LiteImage), and an SSE gateway.
  • Use Case: Create a matching pair of assets—one hero image and one short animated hero background—then extract video frames for web scroll playback.

Quick Start

Ask for a marketing hero banner image and include whether you want landscape or portrait, then specify the save location you prefer.

Frequently Asked Questions about ls-gen-image-or-video

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

FAQPage Schema
How do I generate marketing images and videos from text prompts?▼

You can generate AI marketing visuals by providing a text prompt and specifying an aspect ratio. The system uses an interactive flow to collect missing parameters like resolution and save location, then routes the request through the Gemini API or local backends.

Can I use a reference image to generate a short video?▼

Yes, you can use a reference image for image-to-video workflows. The system supports transforming static marketing visuals into short Veo-based video clips, allowing you to create animated backgrounds or cinematic product shots from existing images.

Does this image and video generation tool work with local Stable Diffusion?▼

Yes, the tool supports local Stable Diffusion (LiteImage) as a fallback backend for image generation. If the primary Gemini API route is unavailable, it can route requests through local SD, browser fallbacks, or an SSE gateway to deliver marketing assets.

What is the best way to create scroll-synced video assets for web playback?▼

The best way to create scroll-synced assets is to generate a short video and use the frame extraction post-processing guidance. This extracts individual frames from the generated video, providing the image sequence needed for web scroll animations.

How do I remove the background from an AI generated marketing image?▼

To remove the background from an AI generated marketing image, you follow the mandatory background removal post-processing guidance provided after generation. This ensures your newly created visual assets are production-ready for compositing and design layouts.

What are the limitations of using the Gemini API for video generation?▼

A limitation of using the Gemini API for video generation is that it may require fallback routing through desktop CLIs, browser sessions, or an SSE gateway if the primary service fails. Users must also interactively define duration and model parameters for successful output.

Related Skills

Explore More Design & Creative Skills→
0xHoneyJar0xHoneyJar
1

loa-credentials

Manage API credentials across environment variables, encrypted stores, and dotenv files.

Official
Intermediate
sterlingdonsterlingdon

wechat-sticker-generator

Generate WeChat sticker packs with background removal and export packaging.

Community
Advanced
lgoodcodelgoodcode

image-pipeline

Automate image upload processing, moderation, and CDN delivery with Sharp and Gemini.

Community
Advanced
unclehowellunclehowell

stable-diffusion-image-generation

Generate images from text prompts using Stable Diffusion diffusion models.

Community
Advanced