Install any skill in seconds. Free to start, no credit card required.
Get Started Free →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.
.claude/skills/osidemedia-higgsfield-moodboard/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 37% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 33% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 25% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 121% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 56% | 0% |
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:
Named presets built by Higgsfield — apply any of these immediately without uploading reference images. Each represents a complete visual world.
| Preset | Visual Character | Best for | |--------|-----------------|---------| | General | Neutral — no strong stylistic bias | Default when unsure, versatile | | Warm ambient | Warm, soft, gently lit — cozy and lived-in | Lifestyle, home, intimate portrait | | Y2K studio | Hypercolor studio backdrop, fairy wings, maximalist | Y2K aesthetic, fashion, fantasy editorial | | Swag era | Early 2000s hip-hop and streetwear energy | Urban fashion, music culture content | | Theatrical light | Dramatic stage lighting, strong contrast, silhouette | Artistic portrait, performance, dark editorial | | Y2K street | Union Jack tees, street photography, 2000s pop culture | Street style, youth culture, nostalgia | | Flash editorial | On-camera flash, oversaturated, candid — Cobrasnake era | Party, raw editorial, documentary fashion | | Old smartphone | Low resolution, slightly washed, nostalgic phone camera | Authentic, lo-fi, personal content | | Street photography | Urban candid, natural light, documentary | Street style, city life, authentic scenes | | Asian nostalgia | Japanese/Korean city streetwear, warm neon, youth culture | Asian fashion, Tokyo/Seoul aesthetic | | Retro BW | Black and white, classic tones, timeless | Artistic portrait, formal editorial, classic fashion | | Surreal solarization | Otherworldly color shifts, solarization effect | Conceptual/avant-garde, fashion art |
How to apply a curated preset:
Recommended: 20+ photos, one cohesive style Avoid: Mixed styles, inconsistent quality
Two upload options in the Moodboard builder:
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.
Once built, your moodboard appears in:
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 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
Pre-built palettes available directly in Color Transfer:
| Palette | Visual Character | |---------|----------------| | Film colors | Natural, organic, slightly desaturated film stock | | Lime Jam | Cool greens, fresh tones, nature-adjacent | | Candy pink | Warm pinks, peachy highlights | | Nostalgic blue | Desaturated blues, faded, melancholic | | Soft palette | Muted, airy, minimal contrast | | Black gloss | High contrast, deep blacks, graphic |
Good color references to upload:
| What it controls | Tool | |-----------------|------| | Who — face and character consistency | Soul ID | | Color world — palette and grade | Color Transfer / Soul Hex | | Overall aesthetic — lighting, tone, visual language | Moodboard | | Specific visual treatment — preset style | Soul 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 postPer-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.]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 fashionExample — 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 editorialhiggsfield-soul — Soul ID character consistency (combine with Moodboard for full visual lock)higgsfield-style — Visual styles and color gradeshiggsfield-mixed-media — Artistic preset overlayshiggsfield-pipeline — Pipeline B uses Moodboard as a core stagetemplates/ — Annotated genre templates demonstrating style direction| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 22,807 | 11,936 | -48% | 1 | 1 | 0% | 2,669 | 3,663 | +37% | 0 | 0 | — |
case-02 | fail→pass | 20,952 | 13,239 | -37% | 1 | 1 | 0% | 2,705 | 3,596 | +33% | 0 | 0 | — |
case-03 | fail→pass | 38,908 | 6,892 | -82% | 1 | 1 | 0% | 2,288 | 2,856 | +25% | 0 | 0 | — |
case-04 | pass→pass | 10,221 | 4,837 | -53% | 1 | 1 | 0% | 1,391 | 2,665 | +92% | 0 | 0 | — |
case-05 | fail→pass | 8,433 | 5,408 | -36% | 1 | 1 | 0% | 1,206 | 2,660 | +121% | 0 | 0 | — |
case-06 | pass→pass | 48,473 | 4,117 | -92% | 1 | 1 | 0% | 1,379 | 2,466 | +79% | 0 | 0 | — |
case-07 | fail→pass | 11,516 | 6,051 | -47% | 1 | 1 | 0% | 1,637 | 2,550 | +56% | 0 | 0 | — |
case-08 | fail→pass | 12,122 | 4,960 | -59% | 1 | 1 | 0% | 1,456 | 2,557 | +76% | 0 | 0 | — |
case-09 | pass→pass | 11,686 | 4,783 | -59% | 1 | 1 | 0% | 1,504 | 2,587 | +72% | 0 | 0 | — |
case-10 | fail→pass | 11,185 | 5,163 | -54% | 1 | 1 | 0% | 1,306 | 2,537 | +94% | 0 | 0 | — |
case-11 | pass→pass | 15,294 | 10,233 | -33% | 1 | 1 | 0% | 1,931 | 3,293 | +71% | 0 | 0 | — |
case-12 | fail→pass | 16,610 | 3,550 | -79% | 1 | 1 | 0% | 1,000 | 2,295 | +130% | 0 | 0 | — |
case-13 | fail→pass | 10,071 | 2,830 | -72% | 1 | 1 | 0% | 1,161 | 2,232 | +92% | 0 | 0 | — |
case-14 | fail→pass | 17,346 | 3,409 | -80% | 1 | 1 | 0% | 2,183 | 2,290 | +5% | 0 | 0 | — |
case-15 | pass→pass | 20,739 | 24,032 | +16% | 1 | 1 | 0% | 2,843 | 3,995 | +41% | 0 | 0 | — |
case-16 | fail→pass | 15,228 | 12,436 | -18% | 1 | 1 | 0% | 2,156 | 3,662 | +70% | 0 | 0 | — |
case-17 | fail→fail | 14,994 | 6,538 | -56% | 1 | 1 | 0% | 1,796 | 2,773 | +54% | 0 | 0 | — |
case-18 | fail→pass | 11,324 | 4,241 | -63% | 1 | 1 | 0% | 1,405 | 2,329 | +66% | 0 | 0 | — |
case-19 | fail→pass | 21,632 | 3,003 | -86% | 1 | 1 | 0% | 1,210 | 2,239 | +85% | 0 | 0 | — |
case-20 | fail→pass | 11,024 | 11,499 | +4% | 1 | 1 | 0% | 1,275 | 2,610 | +105% | 0 | 0 | — |
case-21 | fail→pass | 14,219 | 7,341 | -48% | 1 | 1 | 0% | 1,835 | 3,044 | +66% | 0 | 0 | — |
case-22 | pass→pass | 19,543 | 7,150 | -63% | 1 | 1 | 0% | 1,506 | 2,847 | +89% | 0 | 0 | — |
case-23 | pass→pass | 14,954 | 10,535 | -30% | 1 | 1 | 0% | 1,958 | 3,257 | +66% | 0 | 0 | — |
case-24 | fail→pass | 13,434 | 7,340 | -45% | 1 | 1 | 0% | 1,710 | 2,628 | +54% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 24 cases were attempted. The headline lift of +67 percentage points is the difference between those two pass rates over the 24 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.