skills.rest
velamints2
velamints2COMMUNITY
Explore all skills by this author →
GitHub

best-image-generation

Generate and edit AI images via the EvoLink API with polling.

Updated Mar 4, 2026
Search Tags:#ai#image-generation#prompt#image-editing#reference-images#evolink
One-click install
npx skills add https://github.com/velamints2/clawbot-lab --skill best-image-generation
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: best-image-generation
Source: https://github.com/velamints2/clawbot-lab/tree/main/skills/best-image-generation
Command: npx skills add https://github.com/velamints2/clawbot-lab --skill best-image-generation

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Automates the creation and editing of high-quality AI images through the EvoLink API, reducing time and cost per image.

Core Features & Use Cases

  • Text-to-image generation using the gemini-3-pro-image-preview model.
  • Image-to-image editing with reference URLs to modify or refine visuals.
  • End-to-end workflow: submit task, poll for status, and download the final image.

Quick Start

Provide a prompt and optional image URLs to generate or edit an image using EvoLink's API.

Frequently Asked Questions about best-image-generation

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

FAQPage Schema
How do I generate high-quality AI images from text prompts?▼

To generate high-quality AI images from text prompts, you provide a text prompt and optional parameters like size and quality. The system submits the task, polls for completion status, and downloads the final image asset.

Can I edit an existing image using a reference URL?▼

Yes, you can edit an existing image by providing its URL. The image-to-image editing feature uses reference URLs to modify or iteratively refine your visuals based on the new prompt instructions.

Do I need an API key to use text-to-image generation?▼

Yes, you need an EVOLINK_API_KEY to authenticate requests for text-to-image generation. This key allows the system to submit tasks and poll the API for your final image results.

What is the best way to iteratively refine design assets with AI?▼

The best way to iteratively refine design assets is using image-to-image editing. You provide a reference URL for your current visual, submit new prompt instructions, and download the updated asset after polling completes.

Does the image generation process wait synchronously for results?▼

No, the image generation process uses a polling-based workflow. After submitting the task, the system polls the API status until the generation finishes, then downloads the final image.

Related Skills

Explore More Design & Creative Skills→
RealEmmettSRealEmmettS

image-gen

Generate and edit images via Nano Banana 2, MAI-Image-2.5, and Reve APIs.

Community
Advanced
riba2534riba2534
1.3k

feishu-cli-export

Export Feishu cloud documents and wiki pages to local Markdown files.

Community
Intermediate
qq5855144qq5855144
23

minimax-text-to-image

Generate images from text prompts using the MiniSearch API.

Community
Advanced
zhuangbiaoweizhuangbiaowei
2

stable-diffusion-image-generation

Generate images from text prompts using Stable Diffusion models via HuggingFace Diffusers.

Community
Advanced