Agent Skills

flux-best-practices

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.

Install

npx skills add https://github.com/calesthio/openmontage --skill flux-best-practices
SKILL.md

FLUX 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.md in 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.md is the loadable entry point and the authority. It does not override or extend the repository-root AGENTS.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

  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

Related

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.

Related skills

ai-image-generationgenmedia-labs713KGenerate and edit images on RunComfy via the `runcomfy` CLI — a smart router across the full image-model catalog: FLUX 2 (Klein 9B/4B, Pro, Dev, Flash, Turbo, Max), Google Nano Banana 2 / Pro, OpenAI GPT Image 2, ByteDance Seedream 5 / 4-5 / 4-0 and Dreamina 4-0, Alibaba Qwen Image and Z-Image Turbo, Wan 2-7. Covers both text-to-image (t2i) and image-to-image / edit (i2i) endpoints — the skill picks the right model for the user's actual intent (typography precision, photoreal portraits, sub-secoai-image-generation101-skills547KGenerate AI images with GPT-Image-2, FLUX, Gemini, Grok, Seedream, Reve and 50+ models via inference.sh CLI. Models: GPT-Image-2, FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini 3 Pro Image, Grok Imagine, Seedream 4.5, Reve, ImagineArt. Capabilities: text-to-image, image-to-image, inpainting, LoRA, image editing, upscaling, text rendering. Use for: AI art, product mockups, concept art, social media graphics, marketing visuals, illustrations. Triggers: flux, image generation, ai image, text to image, stnano-banana-2prime-skills424KGenerate images with Google Nano Banana 2 (Gemini-family flash-tier text-to-image) on RunComfy — bundled with the model's documented prompting patterns so the skill gets sharper output than naive prompting against the same model. Documents Nano Banana 2's strengths (rapid iteration, in-image typography rendering, predictable framing, optional web-grounded context), the resolution-tier pricing, the safety-tolerance dial, and when to route to Nano Banana Pro / GPT Image 2 / Flux 2 / Seedream insteimage-editprime-skills424KEdit images on RunComfy — this skill is a smart router that matches the user's intent to the right edit model in the RunComfy catalog. Picks Nano Banana Edit (batch up to 20, identity-preserving default), OpenAI GPT Image 2 Edit (multilingual in-image text rewrite, multi-ref composition, layout precision), Flux Kontext Pro (single-ref high-fidelity local edit), or Z-Image Turbo Inpaint (mask-driven precise region edit). Bundles each model's documented prompting patterns so the skill gets sharper

Search skills and MCP servers

Fuzzy search across 23,137 skills and servers