Requires ATLAS_CLOUD_API_KEY in .env file.

Prices shown are starting prices. Higher resolution or additional features may cost more.

Input Parameters

Text-to-Image (Generate Mode)

| Parameter | Type | Default | Description | |-----------|------|---------|-------------| | prompt | string | (required) | Text description of the desired image | | size | string | 1024x1024 | Output image dimensions (e.g., 512x512, 1024x1024, 1280x720) | | num_inference_steps | number | 28 | Number of denoising steps (higher = better quality, slower) | | seed | number | random | Random seed for reproducible results | | guidance_scale | number | 3.5 | How closely to follow the prompt (higher = more faithful) | | num_images | number | 1 | Number of images to generate | | enable_safety_checker | boolean | true | Set to false for NSFW content | | enable_base64_output | boolean | false | Return images as base64 instead of URLs |

Image Editing (Edit Mode)

| Parameter | Type | Default | Description | |-----------|------|---------|-------------| | prompt | string | (required) | Text description of the desired edit | | image | string | (required) | Base64-encoded image or URL of the source image | | mask_image | string | — | Base64-encoded mask or URL (white = edit area, black = preserve) | | strength | number | 0.75 | Edit strength (0.0 = no change, 1.0 = full regeneration) | | size | string | from source | Output image dimensions | | num_inference_steps | number | 28 | Number of denoising steps | | seed | number | random | Random seed for reproducible results | | guidance_scale | number | 3.5 | How closely to follow the prompt | | enable_safety_checker | boolean | true | Set to false for NSFW content |

LoRA Parameters

| Parameter | Type | Default | Description | |-----------|------|---------|-------------| | lora_url | string | — | URL to the LoRA weights file | | lora_scale | number | 1.0 | Scale factor for LoRA influence |

Why Flux?

The Cheapest Image Generation Available

Flux Schnell at $0.003/image is the most affordable high-quality image generation on the market. Even Flux Dev at $0.012/image undercuts most competitors while delivering superior results.

| Model | Price per Image | |-------|----------------| | Flux Schnell | $0.003 | | Flux Dev | $0.012 | | Flux Kontext Dev | $0.020 | | Flux Dev LoRA | $0.032 |

LoRA Fine-Tuning Support

Flux Dev LoRA and Kontext Dev LoRA support custom fine-tuned models, enabling:

• Custom character consistency across multiple generations
• Brand-specific styling for commercial applications
• Specialized domains like medical imaging, architecture, fashion
• Personal likeness generation from trained models
• Artistic style transfer from specific artists or movements

NSFW Generation

Atlas Cloud provides unrestricted access to Flux models with the safety checker disabled:

flux-image "your prompt" --nsfw

Setting --nsfw passes enable_safety_checker: false to the API, allowing generation of adult content, artistic nudity, and other content that would normally be filtered.

Speed vs Quality Tradeoff

• Flux Schnell — 4 steps, ~1 second, great for rapid prototyping and exploration
• Flux Dev — 28 steps, ~5 seconds, production-quality results
• Flux Dev LoRA — 28 steps with custom fine-tuning applied

Choose the right model for your use case:

| Use Case | Recommended Model | |----------|-------------------| | Rapid prototyping | Flux Schnell | | Production images | Flux Dev | | Custom fine-tuned | Flux Dev LoRA | | Context-aware | Flux Kontext Dev |

Installation

Prerequisites

• Bun runtime installed
• An Atlas Cloud API key (get one here)

Setup

# Clone the repository
git clone https://github.com/thoughtincode/flux-image-skill.git
cd flux-image-skill

# Install dependencies
bun install

# Set up your API key
cp .env.example .env
# Edit .env and add your ATLAS_CLOUD_API_KEY

# Link the CLI globally
bun link

Verify Installation

flux-image --help

Usage

Basic Text-to-Image

flux-image "A serene Japanese garden with cherry blossoms"

Ultra-Fast with Schnell

flux-image "Futuristic robot portrait" --model schnell

High-Quality with Dev

flux-image "Photorealistic landscape of the Swiss Alps at golden hour" --model dev --steps 35 --guidance 4.0

NSFW Mode

flux-image "Artistic figure study, Renaissance style" --nsfw

With LoRA

flux-image "Portrait in custom style" --lora --steps 30

Image Editing with Mask

flux-image "Replace with a golden retriever" --image ./photo.png --mask ./mask.png --strength 0.8

Multiple Images

flux-image "Cute robot character" --count 4

Kontext Model

flux-image "A product on a clean white background" --model kontext

Full Parameter Control

flux-image "A cyberpunk street scene at night, neon lights reflecting on wet pavement" \
  --model dev \
  --size 1280x720 \
  --steps 35 \
  --guidance 4.5 \
  --seed 42 \
  --count 2 \
  --output ./cyberpunk.png

CLI Reference

flux-image <prompt> [options]

Arguments:
  prompt                    Text description of the image to generate

Options:
  --model <variant>         Model: dev (default), schnell, lora, kontext, kontext-lora
  --size <WxH>              Image dimensions (default: 1024x1024)
  --steps <n>               Inference steps (default: 28, schnell: 4)
  --guidance <n>            Guidance scale (default: 3.5)
  --count <n>               Number of images to generate (default: 1)
  --seed <n>                Random seed for reproducibility
  --output <path>           Output file path (default: ./output/<timestamp>.png)
  --image <path>            Source image for editing (file path or URL)
  --mask <path>             Mask image for inpainting (file path or URL)
  --strength <n>            Edit strength 0.0-1.0 (default: 0.75)
  --nsfw                    Disable safety checker for NSFW content
  --lora                    Use LoRA model variant (Flux Dev LoRA)
  --help                    Show this help message

Agent Skill Integration

This tool is designed to work as an AI agent skill across all major coding agents. Install it with a single command:

npx skills add flux-image-skill

This works with Claude Code, Cursor, OpenAI Codex, GitHub Copilot, Gemini CLI, Windsurf, OpenCode, Kiro, and any agent that supports skill installation.

Add to your project's CLAUDE.md

## Image Generation with Flux

Use the `flux-image` CLI to generate images:
- Basic: `flux-image "your prompt here"`
- Fast: `flux-image "prompt" --model schnell`
- NSFW: `flux-image "prompt" --nsfw`
- LoRA: `flux-image "prompt" --lora`
- Edit: `flux-image "edit instructions" --image ./source.png --mask ./mask.png`
- Models: dev (default), schnell, lora, kontext

How It Works

1. Your AI agent reads the skill instructions
2. When asked to generate images, the agent invokes the flux-image CLI
3. The CLI sends requests to Atlas Cloud API
4. Images are downloaded and saved to the ./output directory
5. The agent can reference the saved images in subsequent interactions

API Details

Authentication

Set your Atlas Cloud API key in the .env file or as an environment variable:

export ATLAS_CLOUD_API_KEY=your_api_key_here

Endpoints

| Endpoint | Method | Description | |----------|--------|-------------| | https://api.atlascloud.ai/api/v1/model/generateImage | POST | Submit image generation request | | https://api.atlascloud.ai/api/v1/model/result/{request_id} | GET | Poll for generation result |

Request Flow

1. Submit — POST to /generateImage with model ID and parameters
2. Poll — GET /result/{request_id} until status is completed or failed
3. Download — Retrieve generated image(s) from the response URLs