Agent skill

Flux Image Best Practices

by black-forest-labs in black-forest-labs/skills

Comprehensive guide for BFL FLUX image generation models. An agent skill from black-forest-labs/skills.

MITAuto-check passedMedia & Creative

Install Flux Image Best Practices

skills CLI
$ npx skills add black-forest-labs/skills --skill flux-image-best-practices -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install black-forest-labs/skills flux-image-best-practices --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/black-forest-labs/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/flux-image-best-practices .claude/skills/flux-image-best-practices && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
flux-image-best-practices
GitHub stars
128
Used in
1 other repo
Token cost
~983 tokens
SKILL.md length
264 words
Files
15
Skills in repo
10
Repo updated
First seen
Licence
MIT

At a glance

Comprehensive guide for BFL FLUX image generation models. An agent skill from black-forest-labs/skills.

  • Works in 6 steps: NO negative prompts - FLUX does not… → Be specific - Vague prompts produce… → Use natural language - Prose/narrative… → …
  • Tasks that involve Image generation
  • SKILL.md covers When to Use, Quick Reference, Related and Rules Reference, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Flux Image Best Practices is an agent skill from black-forest-labs/skills. Comprehensive guide for BFL FLUX image generation models. Covers prompting, T2I, I2I, structured JSON, hex colors, typography, multi-reference editing, and model-specific best practices for FLUX.2 and FLUX.1 families.

Its SKILL.md is about 980 tokens, which your agent loads only when the skill is triggered. The skill folder holds 15 other files (for example `AGENTS.md`, `metadata.json` and `rules/_sections.md`).

It sits in Media & Creative, covering Image generation and Typography. The repository describes itself as: Official agent skills from Black Forest Labs for FLUX image and video generation — prompting guides and API integration patterns for Claude Code, Codex, and any… The licence is MIT.

When your agent uses it

  • Tasks that involve Image generation
  • Tasks that involve Typography

Example prompts

  • “/flux-image-best-practices”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. NO negative prompts - FLUX does not support negative prompts; describe what you want
  2. Be specific - Vague prompts produce mediocre results
  3. Use natural language - Prose/narrative style works best
  4. Specify lighting - Lighting has the biggest impact on quality
  5. Quote text - Use "quoted text" for typography rendering
  6. Hex colors - Use #RRGGBB format with color description

What it can do on your machine

Read from SKILL.md and the folder at commit 8907d51. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Flux Image Best Practices loads about 983 tokens when it runs. Until then it costs about 61 tokens; SKILL.md has 264 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~61
When it runs · the whole SKILL.md, loaded when a task matches
~983

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from black-forest-labs/skills at commit 8907d51, republished under its MIT licence (© black-forest-labs). 264 words, ~983 tokens.

Download SKILL.mdSave it as .claude/skills/flux-image-best-practices/SKILL.md (or your agent's skills folder). This skill also uses 14 other files; get the full folder from GitHub.
name
flux-image-best-practices
description
Comprehensive guide for BFL FLUX image generation models. Covers prompting, T2I, I2I, structured JSON, hex colors, typography, multi-reference editing, and model-specific best practices for FLUX.2 and FLUX.1 families.
metadata.author
Black Forest Labs
metadata.version
1.0.0
metadata.tags
flux, bfl, image-generation, prompting, t2i, i2i

FLUX Best Practices

Use this skill when generating prompts for any BFL FLUX model to ensure optimal image quality and accurate prompt interpretation.

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 CaseRecommended ModelNotes
Fastest generationFLUX.2 [klein]4B or 9B, sub-second
Highest qualityFLUX.2 [max]Best detail, grounding search
Production balancedFLUX.2 [pro]Quality + speed
Typography/textFLUX.2 [flex]Best text rendering
Local/developmentFLUX.2 [dev]Open weights
Image editingFLUX.2 [pro/max]Pass image URL directly to input_image
InpaintingFLUX.1 FillObject removal/completion
Context editingFLUX.1 KontextOlder model, prefer FLUX.2
Critical Rules
  1. NO negative prompts - FLUX does not support negative prompts; describe what you want
  2. Be specific - Vague prompts produce mediocre results
  3. Use natural language - Prose/narrative style works best
  4. Specify lighting - Lighting has the biggest impact on quality
  5. Quote text - Use "quoted text" for typography rendering
  6. Hex colors - Use #RRGGBB format with color description

For API integration (endpoints, polling, webhooks), see the bfl-api skill.

Rules Reference

Read individual rule files for detailed guidance:

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.

© black-forest-labs, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 14 other files in skills/flux-image-best-practices of black-forest-labs/skills.

  • SKILL.md
  • AGENTS.md
  • metadata.json
  • rules/_sections.md
  • rules/core-principles.md
  • rules/flux1-models.md
  • rules/flux2-models.md
  • rules/hex-color-prompting.md
  • rules/i2i-prompting.md
  • rules/json-structured-prompting.md
  • rules/model-selection-guide.md
  • rules/multi-reference-editing.md
  • rules/negative-prompt-alternatives.md
  • rules/t2i-prompting.md
  • rules/typography-text.md

Open the folder on GitHubat commit 8907d51

Used in 1 other repository

We found 2 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in black-forest-labs/skills, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Flux Image Best Practices next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Flux Image Best Practices compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Flux Image Best Practices this skillblack-forest-labs/skills1281 repos~983Automated safety check: PassMIT
Minimal Zine Poster GeneratorLiamGvchi/gc-minimal-zine-poster7.3k—~2.9kAutomated safety check: PassMIT
Image Prompt ReverseLunarXuan/image-prompt-reverse467—~678Automated safety check: PassGPL-3.0
Scene Distillation Zine PosterZeejay0/gathered-scenes-zine-skill5.4k—~7.5kAutomated safety check: PassCustom licence
Oriental Editorial Posterdacnay816y62-hub/fantasy-dongfang-jianyuehaibao121—~9.6kAutomated safety check: PassNone
Torn Paper Collage Posteragentara/skills603—~1.3kAutomated safety check: PassMIT

Similar skills

  • Minimal Zine Poster Generator

    LiamGvchi/gc-minimal-zine-poster

    Creates or analyzes quiet, paper-texture zine posters with big negative space, one color accent and experimental type, returning an image prompt and the generated poster.

    7.3k GitHub stars~2.9k tokensUpdated 1 mo ago
    Media & CreativeAuto-check passed
  • Image Prompt Reverse

    LunarXuan/image-prompt-reverse

    Analyze user-provided reference images and reverse-engineer high-fidelity AI image-generation prompts.

    467 GitHub stars~678 tokensUpdated 1 mo ago
    Media & CreativeAuto-check passed
  • Scene Distillation Zine Poster

    Zeejay0/gathered-scenes-zine-skill

    Turns a supplied photo into a minimal zine-style poster with a clear artistic idea, empty space, saturated color and authored typography.

    5.4k GitHub stars~7.5k tokensUpdated 1 mo ago
    Media & CreativeAuto-check passed
  • Oriental Editorial Poster

    dacnay816y62-hub/fantasy-dongfang-jianyuehaibao

    Create finished Chinese cultural, fantasy, and minimalist text-material editorial posters or publication covers with mandatory Image 2 style image generation.

    121 GitHub stars~9.6k tokensUpdated 1 mo ago
    Media & CreativeAuto-check passed
  • Create AI image-generation prompts and image-generation workflows for torn-paper editorial collage style posters with layered ripped paper, rough typography, stamps, tape, stickers, cutout subjects…

    603 GitHub stars~1.3k tokensUpdated 12 days ago
    Media & CreativeAuto-check passed
  • Prompt To Design

    hassancs91/claude-image-generation

    Generate a polished PNG graphic from a text prompt and an aspect ratio.

    102 GitHub stars~3.2k tokensUpdated 1 mo ago
    Media & CreativeAuto-check passed

More from black-forest-labs/skills

All 10 skills in this repo
  • Flux 3 Archival Formats

    black-forest-labs/skills

    A skill your agent uses when a FLUX 3 video needs a period or archival look.

    128 GitHub stars~1.4k tokensUpdated 1 mo ago
    Auto-check passed
  • Flux 3 Keyframes Continuation

    black-forest-labs/skills

    A skill your agent uses when a FLUX 3 video must be built from supplied images or video.

    128 GitHub stars~827 tokensUpdated 1 mo ago
    Auto-check passed
  • Bfl API

    black-forest-labs/skills

    BFL FLUX API integration guide covering endpoints, async polling patterns, rate limiting, error handling, webhooks, and regional endpoints with Python and TypeScript code examples.

    128 GitHub starsUsed in 1 repo~2.5k tokens
    Auto-check: notes
  • Flux 3 Product Ads

    black-forest-labs/skills

    A skill your agent uses when building a finished product ad from FLUX 3 - shot design, voiceover, action-to-word sync, evidence-gated copy, deterministic assembly, and QC gates that catch clipped…

    128 GitHub stars~9.8k tokensUpdated 1 mo ago
    Auto-check passed
  • Flux 3 Prompt Doctor

    black-forest-labs/skills

    A skill your agent uses when diagnosing a FLUX 3 brief before generation.

    128 GitHub stars~904 tokensUpdated 1 mo ago
    Auto-check passed
  • Flux 3 Generate

    black-forest-labs/skills

    A skill your agent uses when submitting or polling a FLUX 3 video API job.

    128 GitHub stars~1.1k tokensUpdated 1 mo ago
    Auto-check passed

Questions about Flux Image Best Practices

What does Flux Image Best Practices do?

Comprehensive guide for BFL FLUX image generation models. An agent skill from black-forest-labs/skills. Flux Image Best Practices is an agent skill from black-forest-labs/skills. Comprehensive guide for BFL FLUX image generation models.

When should I use Flux Image Best Practices?

Flux Image Best Practices fits situations like: tasks that involve Image generation; tasks that involve Typography.

How do I install Flux Image Best Practices in Claude Code?

Run `npx skills add black-forest-labs/skills --skill flux-image-best-practices -a claude-code`. Or copy the skill folder (skills/flux-image-best-practices in black-forest-labs/skills) into .claude/skills/flux-image-best-practices in your project. Claude Code loads it when a task matches its description.

How do I install Flux Image Best Practices in Codex?

Run `npx skills add black-forest-labs/skills --skill flux-image-best-practices -a codex`. Or copy the skill folder (skills/flux-image-best-practices in black-forest-labs/skills) into .agents/skills/flux-image-best-practices in your project. Codex loads it when a task matches its description.

Can I use Flux Image Best Practices in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add black-forest-labs/skills --skill flux-image-best-practices -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/flux-image-best-practices, .gemini/skills/flux-image-best-practices, .github/skills/flux-image-best-practices and .opencode/skills/flux-image-best-practices in your project.

What does Flux Image Best Practices need to run?

SKILL.md names no scripts, command-line tools or credentials: Flux Image Best Practices is instructions for the agent only.

Does Flux Image Best Practices access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Flux Image Best Practices safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Flux Image Best Practices use?

Flux Image Best Practices is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Flux Image Best Practices use?

About 983 tokens (SKILL.md is roughly 3.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Flux Image Best Practices?

Skills that share tags, products or a category with Flux Image Best Practices: Minimal Zine Poster Generator (LiamGvchi/gc-minimal-zine-poster, 7.3k stars), Image Prompt Reverse (LunarXuan/image-prompt-reverse, 467 stars), Scene Distillation Zine Poster (Zeejay0/gathered-scenes-zine-skill, 5.4k stars) and Oriental Editorial Poster (dacnay816y62-hub/fantasy-dongfang-jianyuehaibao, 121 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Flux Image Best Practices?

black-forest-labs (a GitHub organization) maintains it in black-forest-labs/skills, which has 128 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on September 9, 2026.

Source: black-forest-labs/skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.