flux-best-practices

Optimize prompts for BFL FLUX image generation models.

1|Updated Jun 23, 2026
One-click install
npx skills add https://github.com/whichguy/hermes-skills-marketplace --skill flux-best-practices-whichguy
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: flux-best-practices
Source: https://github.com/whichguy/hermes-skills-marketplace/tree/main/skills/flux-best-practices
Command: npx skills add https://github.com/whichguy/hermes-skills-marketplace --skill flux-best-practices-whichguy

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill provides best practices and prompts for optimizing BFL FLUX image generation models, ensuring optimal image quality and accurate prompt interpretation.

Core Features & Use Cases

  • Optimization for FLUX Models: Offers guidance for FLUX.2 and FLUX.1 families, including prompting, T2I, I2I, structured JSON, hex colors, typography, and multi-reference editing.
  • Use Case: When generating prompts for BFL FLUX models, this Skill ensures high-quality image generation and accurate prompt fulfillment.

Quick Start

Generate an image with FLUX.2 by running the flux-best-practices skill with the prompt: "A futuristic cityscape at dusk, with skyscrapers and neon lights, rendered in a cyberpunk style."

Frequently Asked Questions about flux-best-practices

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

FAQPage Schema
What are the best practices for writing prompts for FLUX image generation models?

Yes, you can use image-to-image (I2I) workflows with FLUX models. This Skill provides guidance on multi-reference editing and I2I transformations, ensuring optimal image quality when modifying existing inputs through BFL FLUX generation.

How do I ensure accurate color rendering when generating images with FLUX?

FLUX.2 prompting is optimized through structured JSON syntax, precise typography instructions, and multi-reference editing capabilities. These features distinguish it from FLUX.1, allowing for more complex scene composition and stricter adherence to layout requirements.

Do I need to use structured JSON for T2I prompts in FLUX.1?

Using structured JSON for T2I prompts in FLUX.1 is highly recommended to achieve accurate prompt fulfillment. It enforces a clear prompt structure that the model can parse reliably, resulting in better image quality and fewer generation errors.

Why are my FLUX.2 prompts not generating the expected text and typography?

FLUX.2 prompts may fail at typography if the prompt structure lacks explicit text formatting instructions. Applying the model's specific structured JSON prompting techniques ensures the model correctly interprets and renders complex typographic elements.