skills.rest
armoin2018
armoin2018COMMUNITY
Explore all skills by this author →
WebsiteGitHub

OpenAI DALL-E 3 & Sora Image & Video Generation

Generate images and videos from text prompts using OpenAI models.

4|Updated Jan 2, 2026
Search Tags:#openai#image-generation#video-generation#cost-tracking#sora#dall-e-3
One-click install
npx skills add https://github.com/armoin2018/ai-command-center --skill openai-dall-e-3-sora-image-video-generation
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: OpenAI DALL-E 3 & Sora Image & Video Generation
Source: https://github.com/armoin2018/ai-command-center/tree/main/plugins/aicc-openai/skills/ailey-media-openai
Command: npx skills add https://github.com/armoin2018/ai-command-center --skill openai-dall-e-3-sora-image-video-generation

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Photographers and teams often struggle to generate, edit, and manage AI-produced visuals from prompts, while needing consistent quality, efficient variation workflows, and cost tracking across OpenAI models.

Core Features & Use Cases

  • DALL-E 3: high-fidelity image generation in standard or HD with multiple sizes (1024x1024, 1024x1792, 1792x1024)
  • DALL-E 2: image editing (inpainting) and variations
  • Sora: real-time-to-video generation (Tier 4+ access) with configurable duration and resolutions
  • Account tier detection, cost tracking, and history logging for governance and budgeting
  • CLI and TypeScript API for seamless integration into existing workflows

Quick Start

Provide a text prompt to generate photorealistic images or cinematic videos and save the outputs.

Frequently Asked Questions about OpenAI DALL-E 3 & Sora Image & Video Generation

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

FAQPage Schema
How do I generate cinematic videos from text prompts using Sora?▼

Generate DALL-E 3 images in multiple sizes by providing a text prompt, specifying standard or HD fidelity, and selecting 1024x1024, 1024x1792, or 1792x1024 dimensions. The skill outputs high-fidelity photorealistic image files.

Can I edit existing images and create variations with DALL-E 2?▼

Yes, you can edit existing images and create variations using DALL-E 2. The skill supports inpainting workflows, allowing you to modify specific image areas and generate alternative outputs from an original source image.

How do I track OpenAI API costs and usage for image and video generation?▼

You track OpenAI API costs and usage through the skill's built-in account tier detection and cost tracking. It maintains a local generation history with per-request metadata, enabling accurate budgeting and governance.

Does this image generation skill expose a CLI and TypeScript API?▼

Sora video generation requires Tier 4 or higher account access. The skill automatically detects your account tier to determine model availability, ensuring you have the correct permissions before attempting to output video files.

Related Skills

Explore More Design & Creative Skills→
Mesh-LLMMesh-LLM
3.1k

connect-agents

Connect agent tools and OpenAI clients to a mesh-llm node.

Official
Intermediate
dioerdendioerden

session-logs

Search and analyze past session conversations in JSONL files using jq and regex.

Community
Intermediate
tjade273tjade273

Word Document Handler

Create, edit, and analyze Word .docx documents with docx-js and OOXML.

Community
Advanced
xingBaGanxingBaGan

seedance-2-0

Generate cinematic video clips with Seedance 2.0 from text, images, or references.

Community
Advanced