FLUX Best Practices
0This skill ensures optimal prompt generation for BFL FLUX models, enhancing image quality and accuracy. It's designed for users creating prompts for text-to-image and image-to-image tasks.
000Updated 2mo ago
AI Image Generation
Quick InstallView Source
$ npx skills add https://github.com/black-forest-labs/skills --skill flux-best-practicesOverview
About This Skill
FLUX Best Practices is an official skill from Black Forest Labs that provides comprehensive prompting guidelines for all FLUX models, including FLUX.2 variants (klein, pro, flex, max, dev) and FLUX.1. The skill covers core principles, model-specific techniques, text-to-image and image-to-image prompting patterns, JSON structured prompting, hex color specification, typography rendering, and multi-reference image editing. It teaches FLUX-specific conventions such as avoiding negative prompts (which FLUX doesn't support), using quoted text for typography, specifying lighting for quality impact, and selecting the right model for your use case. Users benefit from detailed prompt structure templates and practical guidance on maximizing image quality and accuracy across different generation tasks.
How to Use
Install the skill using the command provided.
Use Cases
Creating prompts for FLUX.2 or FLUX.1 models
Text-to-image (T2I) generation
Image-to-image (I2I) editing with FLUX.2 models
Color-accurate brand generations
Tags
Setup & Installation
Quick Install
Terminal
$ npx skills add https://github.com/black-forest-labs/skills --skill flux-best-practicesAlternative Install (Git Clone)
git clone https://github.com/black-forest-labs/skillsRequirements
- Claude Code or compatible AI agent
Quick Start Guide
1
Install the Skill
Copy the install command above and run it in your terminal.
2
Open Your AI Agent
Launch Claude Code, Cursor, or your preferred AI coding agent.
3
Try It Out
Use the prompt template or examples below to test the skill.
4
Customize
Adapt the skill to your specific use case and workflow.
Usage Examples
Prompt Template
Generate a FLUX-optimized prompt for [TASK: text-to-image or image-to-image] with the following details: [SUBJECT], [STYLE], [DETAILS], [COLORS], and [ADDITIONAL PARAMETERS like resolution or aspect ratio]. Ensure the prompt maximizes FLUX's strengths in coherence, detail, and artistic interpretation. Avoid generic terms like 'high quality' or 'realistic'—focus on specific descriptors. Use the following structure: 'A [SUBJECT] in [STYLE], [DETAILS], with [COLORS], [ADDITIONAL PARAMETERS].'
Example Output
### FLUX-Optimized Prompt for Your Request: **Task:** Text-to-image **Subject:** A cyberpunk street scene at night **Style:** Neon noir, cinematic lighting **Details:** Rain-soaked asphalt reflecting neon signs, distant figure in a trench coat, holographic advertisements, steam rising from a street vendor **Colors:** Vibrant neon blues, deep purples, and electric pinks **Additional Parameters:** 768x1024 resolution, ultra-detailed textures **Generated Prompt:** *A cyberpunk street at night in neon noir style, rain-soaked asphalt with reflections of neon signs, a lone figure in a trench coat walking away, holographic advertisements flickering in the distance, steam rising from a street vendor’s stall, vibrant neon blues and deep purples dominating the palette, electric pinks highlighting key details, ultra-detailed textures, cinematic lighting with high contrast, 768x1024 resolution.* ### Why This Works for FLUX: - **Specificity:** Avoids vague terms; every element is detailed. - **Lighting & Atmosphere:** Emphasizes cinematic and moody lighting. - **Resolution:** Explicitly includes resolution for FLUX’s architecture. - **Style Anchors:** Uses "neon noir" to guide the model’s interpretation.
Find the right skills for your stack
Take a free 3-minute scan and get personalized AI skill recommendations.
Take free scan