flux-image

Generate images with FLUX models via the inference.sh CLI.

688|95|Updated Jan 31, 2026
One-click install
npx skills add https://github.com/inference-sh/skills --skill flux-image-inference-sh
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: flux-image
Source: https://github.com/inference-sh/skills/tree/main/tools/image/flux-image
Command: npx skills add https://github.com/inference-sh/skills --skill flux-image-inference-sh

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill enables users to generate high-quality images using various FLUX models, including text-to-image and image-to-image transformations, directly from the command line.

Core Features & Use Cases

  • Text-to-Image Generation: Create images from detailed text prompts.
  • Image-to-Image Transformation: Modify existing images based on prompts.
  • LoRA Fine-tuning & Custom Styles: Apply custom styles and fine-tuned models for unique artistic outputs.
  • Multiple FLUX Models: Access different FLUX model versions optimized for speed, quality, or cost.

Quick Start

Generate an image of a futuristic city at night using the falai/flux-dev-lora model.

Frequently Asked Questions about flux-image

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate images from text prompts using FLUX models?

Text-to-image generation with FLUX models is done via the inference.sh CLI by providing a detailed text prompt. You can use models like falai/flux-dev-lora to create high-quality images directly from the command line.

Can I apply LoRA custom styles to an existing image?

Yes, you can modify existing images using the image-to-image transformation feature. This supports LoRA fine-tuning to apply custom artistic styles to your base image based on a text prompt.

What FLUX model variants are available for image generation?

The skill integrates with multiple FLUX model variants, including falai/flux-dev-lora and falai/flux-2-klein-lora. These models are optimized for diverse generation needs like speed, quality, or cost.

Do I need any external dependencies to run FLUX image generation?

No external dependencies are required. The skill operates entirely through the inference.sh CLI and includes its own scripts and references to handle the image generation process.

What is the difference between text-to-image and image-to-image in FLUX?

Text-to-image creates an image from a detailed text prompt, while image-to-image modifies an existing image based on a prompt. Both methods support LoRA fine-tuning for applying custom styles.

When should I use LoRA fine-tuning for AI art generation?

Use LoRA fine-tuning when you need unique artistic outputs or custom styles. It allows you to apply specialized fine-tuned models to your text-to-image or image-to-image generation workflows.