skills.rest
aden-hive
aden-hiveOFFICIAL
Explore all skills by this author →
Website𝕏@aden_hqGitHub

hive.image-generation

Generate and edit images from text prompts using OpenAI gpt-image-2 through the Hive image service.

11.0k|5.7k|Updated Jan 12, 2026
Search Tags:#image generation#logo design#image editing#openai#text-to-image#Hive#GPT-Image-2
One-click install
npx skills add https://github.com/aden-hive/hive --skill hive-image-generation
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: hive.image-generation
Source: https://github.com/aden-hive/hive/tree/main/core/framework/skills/_default_skills/image-generation
Command: npx skills add https://github.com/aden-hive/hive --skill hive-image-generation

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Creating visual assets like logos, banners, mockups, and product shots normally requires design tools or a separate image API with its own key and billing. This Skill lets an agent generate or edit images directly from a prompt, billed to the user's existing Hive credits with no API key to configure.

Core Features & Use Cases

  • Text-to-image generation: Create logos, illustrations, icons, posters, thumbnails, hero images, and social graphics from a natural-language prompt, with control over size, format (png/jpeg/webp), and batch count.
  • Reference-image editing: Pass up to 10 local paths or URLs to restyle photos, place products on mockups, or keep a character consistent across images.
  • Asynchronous workflow with failure handling: Generation runs in the background via a handle polled with collect_result, with explicit guidance for out-of-credits, moderation, rate-limit, and timeout errors.
  • Use Case: A user asks for a minimalist bee logo; the agent calls image_generate, polls collect_result until the image is ready, then surfaces it in chat with attach_file.

Quick Start

Ask the agent to generate an image, for example: create a simple flat-vector logo of a friendly robot in teal and white, then show me the result.

Frequently Asked Questions about hive.image-generation

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

FAQPage Schema
How do I generate an image from a text prompt with an AI agent?▼

Call image_generate with a concrete prompt describing subject, style, composition, and any text to render. It returns a background handle immediately; poll collect_result with that handle until the finished image path is returned.

How do I edit or restyle an existing image with AI?▼

Pass reference_images to image_generate with up to 10 local file paths or http(s) URLs. The model conditions on them at high fidelity, so you can restyle a product photo, place a logo on a mockup, or keep a character consistent.

Do I need an OpenAI API key for image generation?▼

No API key is required. Requests route through the Hive image service to OpenAI gpt-image-2, and the cost is billed to the user's Hive credits exactly like an LLM call.

Why does image generation return pending instead of an image?▼

Generation runs asynchronously and can take a couple of minutes, so collect_result returns status pending until the job finishes. Keep polling with the same handle; if it stays pending past several minutes, the job likely failed and should be restarted once.

What image sizes and formats are supported?▼

Supported sizes are 1024x1024, 1536x1024 landscape, 1024x1536 portrait, or auto, with png, jpeg, or webp output. Quality is locked to low for cost control, and you can request 1 to 4 images per call.

What errors can image generation return and how do I handle them?▼

Errors arrive in the collect_result payload: 402 means out of Hive credits, 403 means the model is unavailable, 400 means the prompt was moderated and should be rephrased, and 429 means rate limited so retry once after waiting.

Related Skills

Explore More Design & Creative Skills→
byteplus-sabyteplus-sa
8

polym-autocase-image-gen

Automate ChatGPT-image-2 generation through the AutoCase playground in Chrome.

Official
Advanced
augustoheissaugustoheiss

agency-carousel-growth-engine

Generate and publish 6-slide TikTok and Instagram carousels from website content.

Community
Advanced
jolequesjoleques

nina-geradora-visual-nano-banana-2

Generate image prompts and PNG files for Nano Banana 2 with preflight validation.

Community
Advanced
akhilksap2026akhilksap2026

ai-integrations-openai

Access OpenAI endpoints through the Replit AI Integrations proxy.

Community
Advanced