Higgsfield Models

What the source does

• FilesystemNone observedNo reads or writes in the source
• NetworkNone observedNo outbound calls in the source
• ShellNone observedNo commands run in the source
• DependenciesPinnedNothing floats
• SecretsNone foundNo keys in source

Five audit layers

Gates applied: no behavioural pass.

Audit 0.4.1 · source sha 9e3a2f685c72 · 28 Oct 2026Report an issue or request a re-scan

• PublisherOSideMedia GitHub userOwner of the repository this skill is read from
• Source folderOSideMedia/higgsfield-ai-prompt-skill/skills/higgsfield-modelsThe exact folder we audited
• LicenceMITAs the repository states it
• Commit pinned for this verdict9e3a2f685c72A new audit runs when the source changes
• Repository statusNot archivedLast push 3 days ago
• Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

Its description: Use when the user asks which model to use, wants to compare models, or needs guidance on selecting between Kling, Wan (incl. Wan 3.0), Seedance (incl. 2.5), Veo 3, Minimax Hailuo / MiniMax H3, FLUX 3 Video, Gemini Omni…

---
name: higgsfield-models
description: >
  Use when the user asks which model to use, wants to compare models,
  or needs guidance on selecting between Kling, Wan (incl. Wan 3.0),
  Seedance (incl. 2.5), Veo 3, Minimax Hailuo / MiniMax H3, FLUX 3 Video,
  Gemini Omni Flash, Soul, Nano Banana, GPT Image 2.5, or other Higgsfield
  engines — including which lane edits existing footage (video_edit, Kling
  3.0 Omni Edit, FLUX 3 Video Edit, Genjutsu, Ad Multiplier) and which
  models make one clip longer than 15s.
user-invocable: true
metadata:
  references:
    - MODELS-DEEP-REFERENCE.md
  tags: [higgsfield, models, Kling, Sora, Wan, Seedance, Veo, Soul, NanoBanana, GPT-Image-2.5, FLUX-3, Genjutsu, edit-lanes, long-take]
  version: 3.3.3
  updated: 2026-09-26
  parent: higgsfield

---

# Higgsfield Model Selection Guide

<!-- CONTENTS — generated by scripts/build_index.py; do not hand-edit -->
**Contents**

- [Quick Decision Flowchart](#quick-decision-flowchart)
- [Video Models — Comparison](#video-models--comparison)
- [Decision Flowchart](#decision-flowchart)
- [Image Models — Quick Selection](#image-models--quick-selection)
- [Budget Tiers](#budget-tiers)
- [Unique Feature Matrix](#unique-feature-matrix)
- [Key Model Notes](#key-model-notes)
- [Cinema Studio 3.0 (Business/Team Plan)](#cinema-studio-30-businessteam-plan)
- [Related skills](#related-skills)

<!-- /CONTENTS -->

Choosing the right model is the single biggest factor in output quality after the prompt.
This file handles most selection questions. For deep per-model documentation (prompting
specifics, parameters, edge cases, API details) → read `MODELS-DEEP-REFERENCE.md`.
The canonical comparison tables, the **Edit-Lane Chooser**, the **Long-Take Chooser**, and
the **Motion Transfer** table live in `../../model-guide.md` — this file agrees with them.

Star ratings are written only from real generations. A `—` in a star column means **not
yet field-rated**; platform facts for those rows are `[OFFICIAL — platform, snapshot 2026-09-26]`.

---

## Quick Decision Flowchart

Fast lookup — for detailed comparisons see the full tables below.

| Need | Recommended Model | Tier |
|------|-------------------|------|
| Top-tier cinematic video + audio | Kling 3.0 | Premium |
| Epic scale / spectacle | Seedance 2.0 or Minimax Hailuo 2.3 (Sora 2 is retired — OpenAI shut its API down 2026-09-24) | Premium |
| Nature / landscapes | Veo 3.1 | Premium |
| Artistic / stylized video | Wan 2.6 | Mid |
| One clip longer than 15s | Seedance 2.5 · Wan 3.0 / Prime · FLUX 3 Video (to 20s) → `model-guide.md` § Long-Take Chooser | — |
| Edit / extend / multiply existing footage | → `model-guide.md` § Edit-Lane Chooser | — |
| Motion transfer from a reference video | Kling 3.0 Motion Control or Genjutsu → `model-guide.md` § Motion Transfer | — |
| Fast video iteration | Seedance 2.0 Fast / Mini | Mid |
| VFX / fluid motion | Minimax Hailuo 2.3 | Mid |
| Budget-friendly video | Kling 3.0 Turbo — the catalog's budget Kling (Kling 2.5 Turbo / Higgsfield DoP Lite: not in the API catalog, 2026-09-26 — verify in the live UI) | Mid |
| Fashion / aesthetic images | Soul 2.0 | Free |
| Photorealistic sharp images | Nano Banana Pro | Low |
| AI actor generation | Soul Cast | Low |
| Native 4K images | Nano Banana Pro (`resolution` to 4k) — Kling Image 3.0 is not in the API catalog, 2026-09-26 — verify in the live UI | — (NB Pro's listed price is for 1K; verify the 4K price) |
| Transparent-background image | GPT Image 2.5 (`background: transparent`) | — |
| Photo style transformation | Photodump (29 presets) | Low |

**Pricing tiers:** Free (Soul 2.0; DoP Lite — not in the API catalog, verify in the UI) · Low (0.1–2 credits) · Mid (2–10 credits) · Premium (10+ credits). See the Credit Cost Reference below for exact per-model costs.

---

## Video Models — Comparison

| Model | Realism | Character | Motion | Style | Duration | Audio | Best for |
|-------|---------|-----------|--------|-------|----------|-------|----------|
| Kling 3.0 | ★★★★★ | ★★★★★ | ★★★★★ | ★★★★☆ | 3–15s | ✅ | Cinematic, long, audio, multi-shot |
| Kling 3.0 Omni | ★★★★★ | ★★★★★ | ★★★★★ | ★★★★☆ | 3–15s | ✅ | Video clone, storyboard control — not in the API catalog, 2026-09-26 — verify in the live UI (only its edit model `kling_video_edit` is). Storyboards: Kling 3.0 |
| Kling 3.0 Omni Edit | ★★★★★ | ★★★★★ | — | ★★★★☆ | 3–10s in (UI doctrine) | ✅ | Edit footage at 3.0 quality — `kling_video_edit`, `mode` std / pro / 4k, source video + optional image refs |
| Kling O1 Video (legacy) | ★★★★★ | ★★★★★ | ★★★★☆ | ★★★☆☆ | 5–10s | ❌ | Multi-ref (7), start/end frame — not in the API catalog, 2026-09-26 — verify in the live UI. Start/end frame: Kling 3.0; many refs: Seedance 2.0 / 2.5 |
| Kling O1 Video Edit (legacy) | ★★★★☆ | ★★★★★ | — | ★★★★★ | 3–10s | ❌ | Relight, restyle, swap, remove — UI-only, not in the API catalog |
| Kling 3.0 Motion Control | ★★★★★ | ★★★★☆ | ★★★★★ | ★★★☆☆ | 3–30s | Optional | Motion transfer from reference video |
| Genjutsu — motion transfer | — | — | — | — | — | — | `hf_mult_motion_control`: motion from a reference video onto subjects in reference images; 480p–1080p. Not yet field-rated |
| Genjutsu — replace object | — | — | — | — | — | — | `hf_mult_replace_object`: replace objects in a source video from reference images; 480p–1080p. Not yet field-rated |
| Kling 2.6 (legacy) | ★★★★★ | ★★★★★ | ★★★★☆ | ★★★☆☆ | 5/10s | ✅ | Character drama, realism; native audio via `sound` toggle (default on) |
| Kling 2.5 Turbo | ★★★★☆ | ★★★★☆ | ★★★★☆ | ★★★☆☆ | 5–10s | ❌ | Fast Kling iteration — not in the API catalog, 2026-09-26 — verify in the live UI. Catalog: Kling 3.0 Turbo |
| Sora 2 (retired) | ★★★★☆ | ★★★☆☆ | ★★★★★ | ★★★★☆ | 4–12s | ✅ | **Retired — do not recommend.** OpenAI shut the Sora 2 API down on 2026-09-24; Higgsfield UI availability is unconfirmed. Scale / physics → Seedance 2.0 or Minimax Hailuo 2.3 (`../../model-guide.md`). Was: epic scale, physics, action — UI-only |
| Wan 3.0

Excerpt, first 6,000 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

git clone https://github.com/OSideMedia/higgsfield-ai-prompt-skill
git -C higgsfield-ai-prompt-skill checkout 9e3a2f685c72

Works in

1. 2026-10-28
   ✓SAFE B 89 / 100

   first audit · source 9e3a2f685c72

Questions about Higgsfield Models

• github.com/OSideMedia/higgsfield-ai-prompt-skill/tree/main/skill — the audited source at commit 9e3a2f685c72 and every finding aboveObserved · 28 Oct 2026

Spotted something wrong? Report a correction · Methodology