Higgsfield Moodboard logo

Higgsfield Moodboard

Community
OSideMedia
higgsfield-moodboard

Use when the user asks about Moodboard, building a moodboard from reference images, curated moodboard presets, Soul Hex color transfer, applying a visual style direction to generations, or named moodboard styles like Y2K studio, Warm ambient, Theatrical light, Swag era, Flash editorial, Street photography, Asian nostalgia, Retro BW, Surreal solarization, etc.

Overview

PublisherOSideMedia
Repositoryhiggsfield-ai-prompt-skill
Skill namehiggsfield-moodboard
Stars
722
Forks
126
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by OSideMedia on GitHub. Read the source before you install it.

Installation

Install the Higgsfield Moodboard AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/OSideMedia/higgsfield-ai-prompt-skill/tree/main/skills/higgsfield-moodboard
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/OSideMedia/higgsfield-ai-prompt-skill.git /tmp/higgsfield-ai-prompt-skill
mkdir -p .claude/skills
cp -r /tmp/higgsfield-ai-prompt-skill/skills/higgsfield-moodboard .claude/skills/higgsfield-moodboard
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Higgsfield Moodboard in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Higgsfield Moodboard on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Higgsfield Moodboard is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Higgsfield Moodboard

What Moodboard Does

Moodboard translates a collection of visual references into a unified style direction that can be applied to any generation. Instead of describing a feeling in text and hoping the model interprets it correctly, you show the platform exactly what you want.

Location: Moodboard tab (marked "New" in nav) → higgsfield.ai/moodboard

Two tabs inside Moodboard:

  • Curated — Higgsfield's own named preset moodboards, ready to use
  • My Moodboards — your custom moodboards built from uploaded references

Curated Moodboard Presets

Named presets built by Higgsfield — apply any of these immediately without uploading reference images. Each represents a complete visual world.

PresetVisual CharacterBest for
GeneralNeutral — no strong stylistic biasDefault when unsure, versatile
Warm ambientWarm, soft, gently lit — cozy and lived-inLifestyle, home, intimate portrait
Y2K studioHypercolor studio backdrop, fairy wings, maximalistY2K aesthetic, fashion, fantasy editorial
Swag eraEarly 2000s hip-hop and streetwear energyUrban fashion, music culture content
Theatrical lightDramatic stage lighting, strong contrast, silhouetteArtistic portrait, performance, dark editorial
Y2K streetUnion Jack tees, street photography, 2000s pop cultureStreet style, youth culture, nostalgia
Flash editorialOn-camera flash, oversaturated, candid — Cobrasnake eraParty, raw editorial, documentary fashion
Old smartphoneLow resolution, slightly washed, nostalgic phone cameraAuthentic, lo-fi, personal content
Street photographyUrban candid, natural light, documentaryStreet style, city life, authentic scenes
Asian nostalgiaJapanese/Korean city streetwear, warm neon, youth cultureAsian fashion, Tokyo/Seoul aesthetic
Retro BWBlack and white, classic tones, timelessArtistic portrait, formal editorial, classic fashion
Surreal solarizationOtherworldly color shifts, solarization effectConceptual/avant-garde, fashion art

How to apply a curated preset:

  1. Go to Moodboard tab
  2. Select Curated
  3. Click any preset
  4. It becomes available in My Moodboards or applies directly to generation

Building a Custom Moodboard

Upload Requirements

Recommended: 20+ photos, one cohesive style Avoid: Mixed styles, inconsistent quality

Two upload options in the Moodboard builder:

  • Upload images — upload from your device
  • Upload from assets — pull from your existing Higgsfield generations/assets

What "one cohesive style" means: All reference images should share the same visual world — similar lighting quality, color temperature, tone, and aesthetic. If half your references are dark and moody and half are bright and airy, the moodboard gets confused and produces a muddled output.

Good reference set (cohesive): Film stills from the same movie, a photographer's series, a curated Pinterest board with a single strong aesthetic, a fashion brand's lookbook.

Bad reference set (mixed): Random images from different genres, mixing a sunset photo with a dark studio portrait with a colorful illustration.

Building the Moodboard

  1. Click Build your moodboard ✦ (yellow button at top)
  2. Upload 20+ reference images via "Upload images" or "Upload from assets"
  3. Higgsfield analyzes the visual properties across all references
  4. Synthesizes dominant: colors, tonal values, lighting character, stylistic patterns
  5. Creates a named moodboard saved under My Moodboards

Applying to Generation

Once built, your moodboard appears in:

  • Soul 2.0 → Moodboard selector in the prompt bar
  • Any generation interface that supports moodboard input

The moodboard acts as a style layer applied on top of your text prompt — you describe the scene, the moodboard handles the look.


Soul Hex — Color Transfer

Soul Hex is Moodboard's dedicated color feature. It extracts and transfers the exact color signature from a reference image.

Location: Soul 2.0 prompt bar → Color Transfer button

Named Color Palettes

Pre-built palettes available directly in Color Transfer:

PaletteVisual Character
Film colorsNatural, organic, slightly desaturated film stock
Lime JamCool greens, fresh tones, nature-adjacent
Candy pinkWarm pinks, peachy highlights
Nostalgic blueDesaturated blues, faded, melancholic
Soft paletteMuted, airy, minimal contrast
Black glossHigh contrast, deep blacks, graphic

Custom Color Reference Upload

  1. Click Upload & Create ✦ in the Soul Hex section
  2. Upload any reference image with the color world you want
  3. Soul Hex extracts the color palette automatically — shows hex swatches
  4. Apply to generations

Good color references to upload:

  • Film still from a movie with the color grade you want
  • Fashion editorial with a strong color world
  • Your brand's visual assets to match brand colors
  • Any image where the color palette is the dominant appeal

Moodboard + Soul ID: The Power Combination

What it controlsTool
Who — face and character consistencySoul ID
Color world — palette and gradeColor Transfer / Soul Hex
Overall aesthetic — lighting, tone, visual languageMoodboard
Specific visual treatment — preset styleSoul 2.0 Style Preset

Workflow for a consistent content series:

Step 1: Create Soul ID character (20+ photos, Character tab)
Step 2: Build Moodboard from style references (20+ cohesive images)
Step 3: Set Color Transfer palette (named or custom upload)
Step 4: Every generation uses:
         → Character slot: Soul ID active
         → Style: appropriate preset
         → Color Transfer: consistent palette
         → Moodboard: your custom moodboard active
Step 5: Only the scene description changes post to post

Platform constraint — preset vs reference image (Soul 2.0) [OFFICIAL — platform CLI, 2026-09-26]: higgsfield model get text2image_soul_v2 rejects style_id combined with image_references and allows at most one image reference. The schema also has a separate custom_reference_id param that this rule does not mention. Which UI control maps to which param — Style preset → style_id? Soul ID character slot → custom_reference_id or image_references? — is unverified. So this workflow's "Soul ID + preset" pairing is not known to break, while "preset + an uploaded reference image" is the pair the CLI forbids if the preset is style_id: if a generation rejects or ignores one of them, drop the preset or the uploaded reference rather than retrying the pair. Detail: ../../image-models.md § Soul 2.0.

Per-post prompt template (with all consistency tools active):

[Soul ID character] is [action] at [specific location].
[One unique visual detail for this post.]
Camera: [movement]. Aspect: 9:16.
[No style description needed — moodboard + preset handle it.]

Moodboard as a Prompt Modifier

When you want to write the moodboard's style into the prompt directly (rather than using the UI), use this structure:

[MOODBOARD: Project Name]
Color palette: [2–3 dominant colors]
Tone: [warm/cool + emotional register]
Film look: [sensor/grain if applicable]
Lighting character: [quality of light]
Cultural reference: [specific aesthetic if using a curated preset]

Example — Y2K Studio:

[MOODBOARD: Summer Campaign]
Color palette: electric blue backdrop, metallic silver, iridescent highlights
Tone: hyper-energized, maximalist, unserious
Film look: early 2000s digital — slightly blown highlights, vivid saturation
Lighting character: hard studio flash, colorful gels
Cultural reference: Y2K maximalism, early internet fashion

Example — Theatrical Light:

[MOODBOARD: Dark Portrait Series]
Color palette: deep black, single amber key light, deep shadow fill
Tone: mysterious, composed, high-drama
Film look: medium format digital, razor-sharp
Lighting character: single hard source, theatrical — all else falls to black
Cultural reference: stage photography, Helmut Newton editorial

Related skills

  • higgsfield-soul — Soul ID character consistency (combine with Moodboard for full visual lock)
  • higgsfield-style — Visual styles and color grades
  • higgsfield-mixed-media — Artistic preset overlays
  • higgsfield-pipeline — Pipeline B uses Moodboard as a core stage
  • templates/ — Annotated genre templates demonstrating style direction

Frequently asked questions

What does the Higgsfield Moodboard AI skill do?

Use when the user asks about Moodboard, building a moodboard from reference images, curated moodboard presets, Soul Hex color transfer, applying a visual style direction to generations, or named moodboard styles like Y2K studio, Warm ambient, Theatrical light, Swag era, Flash editorial, Street photography, Asian nostalgia, Retro BW, Surreal solarization, etc.

Why use Higgsfield Moodboard on TypingMind?

Because you install it once and use it with any model. Higgsfield Moodboard is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Higgsfield Moodboard in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/OSideMedia/higgsfield-ai-prompt-skill/tree/main/skills/higgsfield-moodboard. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Higgsfield Moodboard?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Higgsfield Moodboard?

As many as you like. As long as a model supports skills, you can use Higgsfield Moodboard with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Higgsfield Moodboard AI skill free?

Yes. It is published on GitHub by OSideMedia under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇