mcpField
F
flux-image

flux-image

github.com/inference-shCreative & media7891.1k installsUpdated 2w ago
Repository

About flux-image

flux-image is a belt CLI skill for generating and transforming images with FLUX models. It helps creators choose among models for different speed and quality needs, use LoRA styles, and perform image-to-image generation.

Key features

  1. 01Run multiple FLUX model variants
  2. 02Choose models by speed and quality
  3. 03Apply custom LoRA styles
  4. 04Generate images from prompts
  5. 05Transform supplied images

Use cases

  1. 01Create product photography
  2. 02Iterate quickly on visual concepts
  3. 03Generate images in a custom style
  4. 04Transform an existing image

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/inference-sh/skills --skill flux-image

After installing, type/flux-imagein Claude Code to confirm it loaded.

Details

From the project README

Install the belt CLI skill: npx skills add belt-sh/cli

FLUX Image Generation

Generate images with FLUX models via inference.sh CLI.

FLUX Image Generation

Quick Start

Requires inference.sh CLI (belt). Install instructions

belt login

belt app run falai/flux-dev-lora --input '{"prompt": "a futuristic city at night"}'

FLUX Models

ModelApp IDSpeedQualityUse Case
FLUX Dev LoRAfalai/flux-dev-loraMediumHighestProduction, custom styles
FLUX.2 Klein LoRAfalai/flux-2-klein-loraFastestGoodFast iteration, 4B/9B sizes
FLUX Dev (Pruna)pruna/flux-devFastHighOptimized, speed modes
FLUX Dev LoRA (Pruna)pruna/flux-dev-loraFastHighLoRA with optimization
FLUX Klein 4B (Pruna)pruna/flux-2-klein-4bFastestGoodUltra-cheap ($0.0001/img)

Examples

High-Quality Generation
belt app run falai/flux-dev-lora --input '{
  "prompt": "professional product photo of headphones, studio lighting, white background"
}'
Fast Generation (Klein)
belt app run falai/flux-2-klein-lora --input '{"prompt": "abstract art, colorful"}'
With LoRA Custom Styles
belt app sample falai/flux-dev-lora --save input.json

# Edit to add "loras": [{"path": "<lora-url>", "scale": 1.0}] for custom style
belt app run falai/flux-dev-lora --input input.json
Image-to-Image
belt app run falai/flux-dev-lora --input '{
  "prompt": "transform to watercolor style",
  "image": "https://your-image.jpg"
}'

For Other Image Tasks

# Image editing with natural language
belt app run falai/reve --input '{"prompt": "change background to beach"}'

# Upscaling
belt app run falai/topaz-image-upscaler --input '{"image": "https://..."}'

Related Skills

# Full platform skill (all apps)
npx skills add inference-sh/skills@infsh-cli

# Pruna P-Image (fast & economical)
npx skills add inference-sh/skills@p-image

# All image generation models
npx skills add inference-sh/skills@ai-image-generation

# Upscaling
npx skills add inference-sh/skills@image-upscaling

Browse all apps: belt app list

Documentation

Comments

Markdown supported