Image Generation via Replicate

Generate images programmatically using Replicate's hosted ML models.

Purpose

Enable Alex to create images for documentation, UI assets, banners, and visual content without manual design tools.

When to Use

Model Selection

Default: flux-schnell for speed. Upgrade to flux-dev for final assets.

Prompt Engineering

Structure

[Subject] [Style] [Details] [Technical specs]

Style Modifiers

Negative Prompts

Always include to avoid common issues:

blurry, low quality, distorted, text, watermark, signature

For icons/logos add:

complex background, photorealistic, detailed textures

API Reference

Authentication

REPLICATE_API_TOKEN=r8_xxxxx

Create Prediction

curl -X POST https://api.replicate.com/v1/predictions \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "version": "<model-version-id>",
    "input": {
      "prompt": "...",
      "negative_prompt": "...",
      "width": 1024,
      "height": 1024,
      "num_outputs": 1
    }
  }'

Poll for Result

curl https://api.replicate.com/v1/predictions/<id> \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN"

Response States

Common Sizes

Output Handling

1. Download the generated URL immediately (expires)
2. Save to workspace with descriptive name
3. Optimize if needed (large files)

Decision Framework

User wants image
    ↓
Is it a quick draft? → flux-schnell
    ↓
Is it final quality? → flux-dev
    ↓
Is it an icon/logo? → Add "minimal, vector style"
    ↓
Is it a photo? → Add "photorealistic, 8k"
    ↓
Generate → Download → Save

Common Mistakes

Troubleshooting