by ristponex
🎨 Flux image generation skill — LoRA support, NSFW capable. Claude Code & 15+ platforms.
# Add to your Claude Code skills
git clone https://github.com/ristponex/flux-image-skillThis project provides a CLI tool (flux-image) for generating images using Flux (Black Forest Labs) models via the Atlas Cloud API.
flux-image "your prompt here"
flux-image "prompt" --model schnell
flux-image "prompt" --nsfw
flux-image "prompt" --lora
flux-image "edit instructions" --image ./source.png --mask ./mask.png --strength 0.75
flux-image "prompt" --model kontext
--model dev (default) — High quality, $0.012/image--model schnell — Ultra fast, $0.003/image--model kontext — Context-aware--lora flag — Switches to LoRA variant--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 (default: 1)--seed N — Random seed--output path — Custom output path--nsfw — Disable safety checkerImages are saved to ./output/ directory by default.
An AI Agent Skill for generating images using Flux (Black Forest Labs) models via Atlas Cloud API.
Works with 15+ AI coding agents including Claude Code, Cursor, OpenAI Codex, GitHub Copilot, Gemini CLI, Windsurf, OpenCode, Kiro, and more.
Flux is Black Forest Labs' cutting-edge image generation model family, offering some of the most affordable and highest-quality text-to-image generation available. This skill integrates Flux directly into your AI coding workflow with support for multiple model variants, LoRA fine-tuning, and unrestricted NSFW generation.
| Model | ID | Starting Price per Image | Description |
|-------|-----|--------------------------|-------------|
| Flux Dev | black-forest-labs/flux-dev | from $0.012/image | High-quality, balanced speed and detail |
| Flux Schnell | black-forest-labs/flux-schnell | from $0.003/image | Ultra-fast generation, great for prototyping |
| Flux Dev LoRA | black-forest-labs/flux-dev-lora | from $0.032/image | Dev model with LoRA fine-tuning support |
| Flux Kontext Dev | | from $0.020/image | Context-aware generation |
| Flux Kontext Dev LoRA | | from $0.032/image | Kontext with LoRA support |
No comments yet. Be the first to share your thoughts!
Requires ATLAS_CLOUD_API_KEY in .env file.
black-forest-labs/flux-kontext-devblack-forest-labs/flux-kontext-dev-loraPrices shown are starting prices. Higher resolution or additional features may cost more.
| 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 |
| 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 |
| Parameter | Type | Default | Description |
|-----------|------|---------|-------------|
| lora_url | string | — | URL to the LoRA weights file |
| lora_scale | number | 1.0 | Scale factor for LoRA influence |
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 |
Flux Dev LoRA and Kontext Dev LoRA support custom fine-tuned models, enabling:
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.
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 |
# 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
flux-image --help
flux-image "A serene Japanese garden with cherry blossoms"
flux-image "Futuristic robot portrait" --model schnell
flux-image "Photorealistic landscape of the Swiss Alps at golden hour" --model dev --steps 35 --guidance 4.0
flux-image "Artistic figure study, Renaissance style" --nsfw
flux-image "Portrait in custom style" --lora --steps 30
flux-image "Replace with a golden retriever" --image ./photo.png --mask ./mask.png --strength 0.8
flux-image "Cute robot character" --count 4
flux-image "A product on a clean white background" --model kontext
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
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
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.
## 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
flux-image CLI./output directorySet your Atlas Cloud API key in the .env file or as an environment variable:
export ATLAS_CLOUD_API_KEY=your_api_key_here
| 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 |
/generateImage with model ID and parameters/result/{request_id} until status is completed or failed