FLUX Best Practices
FreeOptimize your prompts for BFL FLUX image generation.
Free · Opens the source repo
What FLUX Best Practices does
The FLUX Best Practices skill is designed to assist users in generating high-quality prompts specifically for BFL FLUX image generation models, including FLUX.1 and FLUX.2 families. This skill provides a comprehensive guide that covers essential aspects of prompt creation, ensuring that users can effectively utilize the capabilities of these models to achieve the desired outcomes in their image generation tasks. By following the structured guidelines and best practices outlined in this skill, users can enhance the accuracy and quality of their generated images.
This skill is particularly useful for developers and designers who are engaged in text-to-image (T2I) and image-to-image (I2I) editing tasks. It includes detailed instructions on how to construct prompts using a specific formula that incorporates subject, action, style, context, lighting, and technical specifications. The skill also emphasizes the importance of being specific and using natural language, which can significantly impact the results produced by the FLUX models. Additionally, it provides insights into model selection based on use cases, helping users choose the most appropriate model for their needs.
Users will find detailed rules and guidelines for various aspects of prompt creation, including typography, color specification, and multi-reference editing. The skill includes references to individual rule files that delve deeper into each topic, offering a rich resource for anyone looking to master prompt generation with FLUX. The emphasis on structured JSON for complex scene generation and the importance of lighting in image quality are also highlighted, making this skill a valuable asset for anyone working with BFL FLUX models.
When to use it
Use this skill when creating prompts for FLUX.1 and FLUX.2 models, especially for T2I and I2I tasks.
When not to use it
This skill is not suitable for users looking for general image generation techniques outside the FLUX model families.
What you can build with it
Creating T2I Prompts
Use this skill to generate effective text-to-image prompts that leverage the capabilities of FLUX.2 models.
Editing Images with I2I
Utilize the guidelines for image-to-image editing tasks, ensuring high-quality results with FLUX.2 models.
Structured Scene Generation
Employ structured JSON prompts for complex scene compositions, enhancing the detail and accuracy of generated images.
How to install FLUX Best Practices
View source1. Install with the skills CLI
npx skills add calesthio/openmontage/flux-best-practices --agent claude-code2. Or install it manually
Download the skill folder and drop it into ~/.claude/skills/ for all projects, or .claude/skills/ to scope it to one repo. Restart Claude Code so it picks up the new skill.
Anthropic's agentic coding CLI, and the reference implementation of Agent Skills. Drop a skill folder into ~/.claude/skills and Claude Code loads it automatically whenever a task matches the skill's description. Claude Code docs
Inside SKILL.md
Written by calesthioFLUX Best Practices
Use this skill when generating prompts for any BFL FLUX model to ensure optimal image quality and accurate prompt interpretation.
Extended reference:
AGENTS.mdin this directory is the long-form upstream FLUX guide (vendored from Black Forest Labs). It is supplementary reference material scoped to this skill only —SKILL.mdis the loadable entry point and the authority. It does not override or extend the repository-rootAGENTS.md/AGENT_GUIDE.md.
When to Use
- Creating prompts for FLUX.2 or FLUX.1 models
- Text-to-image (T2I) generation
- Image-to-image (I2I) editing with FLUX.2 models
- Structured scene generation with JSON
- Typography and text rendering
- Multi-reference style transfer
- Color-accurate brand generations
Quick Reference
Prompt Structure Formula
[Subject] + [Action/Pose] + [Style/Medium] + [Context/Setting] + [Lighting] + [Camera/Technical]
Model Selection
| Use Case | Recommended Model | Notes |
|---|---|---|
| Fastest generation | FLUX.2 [klein] | 4B or 9B, sub-second |
| Highest quality | FLUX.2 [max] | Best detail, grounding search |
| Production balanced | FLUX.2 [pro] | Quality + speed |
| Typography/text | FLUX.2 [flex] | Best text rendering |
| Local/development | FLUX.2 [dev] | Open weights |
| Image editing | FLUX.2 [pro/max] | Pass image URL directly to input_image |
| Inpainting | FLUX.1 Fill | Object removal/completion |
| Context editing | FLUX.1 Kontext | Older model, prefer FLUX.2 |
Critical Rules
- NO negative prompts - FLUX does not support negative prompts; describe what you want
- Be specific - Vague prompts produce mediocre results
- Use natural language - Prose/narrative style works best
- Specify lighting - Lighting has the biggest impact on quality
- Quote text - Use "quoted text" for typography rendering
- Hex colors - Use #RRGGBB format with color description
Related
For API integration (endpoints, polling, webhooks), see the bfl-api skill.
Rules Reference
Read individual rule files for detailed guidance:
- rules/core-principles.md - Universal FLUX prompting principles
- rules/flux2-models.md - FLUX.2 family: klein, max, pro, flex, dev
- rules/flux1-models.md - FLUX.1 family: older generation of FLUX.2 models - pro, Kontext, Fill
- rules/t2i-prompting.md - Text-to-image prompting patterns
- rules/i2i-prompting.md - Image-to-image editing with FLUX.2
- rules/json-structured-prompting.md - Complex scene composition
- rules/hex-color-prompting.md - Precise color specification
- rules/typography-text.md - Text rendering and typography
- rules/multi-reference-editing.md - Multi-image references
- rules/negative-prompt-alternatives.md - Positive alternatives
- rules/model-selection-guide.md - Choosing the right model
Example Prompt
A weathered fisherman in his 70s with deep wrinkles and a salt-and-pepper beard,
wearing a navy cable-knit sweater, standing at the helm of his wooden boat.
Golden hour sunlight from the left creates dramatic rim lighting on his profile.
Shot on Hasselblad with 85mm lens at f/2.8, shallow depth of field with harbor
lights creating soft bokeh in the background. Kodak Portra 400 color science.
Frequently asked questions about FLUX Best Practices
Similar skills
Arize Prompt Optimization
Enhance LLM prompts using data-driven insights.
Prompt Optimizer
Transform vague ideas into precise LLM prompts.
Prompt Engineering Patterns
Enhance LLM prompts for better performance and reliability.
Senior Prompt Engineer
Optimize LLM performance and design advanced AI systems.
Prompt Engineer Toolkit
Transform marketing prompts into tested production assets.
Senior Prompt Engineer
Optimize prompts and evaluate LLM outputs efficiently.