skills.rest
Aadi-110i
Aadi-110iCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

flux-image

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

Updated Jul 28, 2026
Search Tags:#image generation#text-to-image#image-to-image#lora#flux#inference.sh#black forest labs
One-click install
npx skills add https://github.com/Aadi-110i/PEP-PROJECT --skill flux-image-aadi-110i
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: flux-image
Source: https://github.com/Aadi-110i/PEP-PROJECT/tree/main/skills/flux-image
Command: npx skills add https://github.com/Aadi-110i/PEP-PROJECT --skill flux-image-aadi-110i

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Creating AI-generated images requires choosing the right model, configuring parameters, and managing API access. This Skill provides direct command-line access to FLUX image generation models from Black Forest Labs through the inference.sh platform, covering text-to-image, image-to-image, and LoRA custom styles. ## Core Features & Use Cases - Multiple FLUX Models: Choose between FLUX Dev LoRA for highest quality, FLUX.2 Klein LoRA for fast iteration, and Pruna-optimized variants for speed and low cost. - Text-to-Image and Image-to-Image: Generate images from prompts or transform existing images with style instructions. - LoRA Custom Styles: Apply custom LoRA weights via a lora_url parameter for branded or stylized outputs. - Use Case: A designer needs product mockups in a consistent visual style. They run FLUX Dev LoRA with a custom LoRA URL to generate studio-quality images matching their brand aesthetic. ## Quick Start Ask the AI to generate an image of a futuristic city at night using the FLUX model via the belt CLI.

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 with FLUX models from the command line?▼

Install the inference.sh belt CLI, run belt login, then execute belt app run falai/flux-dev-lora with a JSON input containing your prompt. The CLI returns the generated image output directly.

Which FLUX model should I use for fast image generation?▼

FLUX.2 Klein LoRA (falai/flux-2-klein-lora) is the fastest option for quick iteration, while FLUX Klein 4B from Pruna offers ultra-low cost at around $0.0001 per image. FLUX Dev LoRA provides the highest quality for production use.

Can FLUX models apply custom LoRA styles to images?▼

Yes, FLUX Dev LoRA and FLUX.2 Klein LoRA support custom LoRA weights. Generate a sample input with belt app sample, add your lora_url to the JSON, and run the app with that input file.

Does FLUX support image-to-image transformation?▼

Yes, pass an image_url along with a prompt describing the desired transformation, such as converting a photo to watercolor style. The model uses the source image as a base for generation.

What are the limitations of FLUX Klein models?▼

Klein models prioritize speed and cost over output quality, making them less suitable for final production assets. For highest fidelity results, use FLUX Dev LoRA instead.

Related Skills

Explore More Design & Creative Skills→
inference-shinference-sh
723

gpt-image

Generate and edit images with OpenAI GPT-Image-2 via the inference.sh CLI.

Official
Basic
SheshiyerSheshiyer
4

image-upscaling

Upscale low-resolution images with multiple AI upscalers via inference.sh CLI.

Community
Intermediate
JackiexiaoJackiexiao

ai-image-generation

Generate AI images across 50+ models using the inference.sh CLI.

Community
Advanced
inference-shinference-sh
688

p-image

Generate and edit images with Pruna P-Image models via inference.sh CLI.

Official
Intermediate