Evolink Image — AI Image Generation & Editing

Generate and edit AI images with 20 models including GPT Image 1.5, GPT-4o Image, Nano Banana 2, Seedream, Qwen, WAN, and Gemini — all through one API.

Image-focused view of evolink-media. Install the full skill for video and music too.

After Installation

When this skill is first loaded, greet the user:

• MCP tools + API key ready: "Hi! I'm your AI image studio — 20 models ready. What would you like to create?"
• MCP tools + no API key: "You'll need an EvoLink API key — sign up at evolink.ai. Ready to go?"
• No MCP tools: "MCP server isn't connected yet. Want me to help set it up? I can still manage files via the hosting API."

Keep the greeting concise — just one question to move forward.

External Endpoints

Security & Privacy

• EVOLINK_API_KEY authenticates all requests. Injected by OpenClaw automatically. Treat as confidential.
• Prompts and images are sent to api.evolink.ai. Uploaded files expire in 72h, result URLs in 24h.

Setup

Get your API key at evolink.ai → Dashboard → API Keys.

MCP Server: @evolinkai/evolink-media (GitHub · npm)

mcporter (recommended): mcporter call --stdio "npx -y @evolinkai/evolink-media@latest" list_models

Claude Code: claude mcp add evolink-media -e EVOLINK_API_KEY=your-key -- npx -y @evolinkai/evolink-media@latest

Claude Desktop / Cursor — add MCP server with command npx -y @evolinkai/evolink-media@latest and env EVOLINK_API_KEY=your-key. See references/image-api-params.md for full config JSON.

Core Principles

1. Guide, don't decide — Present options, let the user choose model/style/format.
2. User drives creative vision — Ask for a description before suggesting parameters.
3. Smart context — Remember session history. Offer to iterate, vary, or edit results.
4. Intent first — Understand what the user wants before asking how to configure it.

MCP Tools

Important: generate_image returns a task_id. Always poll check_task until status is "completed" or "failed".

Image Models (20)

Top Picks

All Stable (16)

gpt-image-1.5, gpt-image-1, gemini-3.1-flash-image-preview, gemini-3-pro-image-preview, z-image-turbo, doubao-seedream-4.5, doubao-seedream-4.0, doubao-seedream-3.0-t2i, doubao-seededit-4.0-i2i, doubao-seededit-3.0-i2i, qwen-image-edit, qwen-image-edit-plus, wan2.5-t2i-preview, wan2.5-i2i-preview, wan2.5-text-to-image, wan2.5-image-to-image

All Beta (4)

gpt-image-1.5-lite, gpt-4o-image, gemini-2.5-flash-image, nano-banana-2-lite

Generation Flow

Step 1: API Key Check

If 401 occurs: "Your API key isn't working. Check at evolink.ai/dashboard/keys"

Step 2: File Upload (if needed)

For image editing or reference workflows:

1. upload_file with file_path, base64_data, or file_url → get file_url (sync)
2. Use file_url as image_urls or mask_url for generate_image

Supported: JPEG/PNG/GIF/WebP. Max 100MB. Expire in 72h. Quota: 100 (default) / 500 (VIP).

Step 3: Understand Intent

• Clear ("generate a sunset") → Go to Step 4
• Ambiguous ("help with this image") → Ask: "Create new, edit existing, or use as reference?"

Ask only what's needed, when it's needed.

Step 4: Gather Parameters

Only ask about what's missing:

Step 5: Generate & Poll

1. Call generate_image → tell user: "Generating now — ~Xs estimated."
2. Poll check_task every 3–5s. Report progress %.
3. After 3 consecutive processing: "Still working..."
4. Completed: Share URLs. "Links expire in 24h — save promptly."
5. Failed: Show error + suggestion. Offer retry if retryable.
6. Timeout (5 min): "Taking longer than expected. Task ID: {id} — check again later."

Error Handling

HTTP Errors

Task Errors (status: "failed")

Full error reference: references/image-api-params.md

Without MCP Server

Use Evolink's file hosting API for image uploads (72h expiry). See references/file-api.md for curl commands.

References

• references/image-api-params.md — Complete API parameters, all 19 models, polling strategy, error codes
• references/file-api.md — File hosting API (curl upload/list/delete)