SkillAgentSearch skills...

higgsfield-generate

Generate images/videos/3D assets/audio via Higgsfield AI. Defaults: GPT Image 2.6 for images, animated GIFs and SVG, Seedance 2.5 for video, Nano Banana 2 for cartoon characters, Marketing Studio for ads, Seed Audio 1.0 for audio.

Install / Use

npx skills add higgsfield-ai/skills --skill higgsfield-generate

Installs into whichever agent you are using.

About this skill
šŸ“„

SKILL.md

Installable skill definition

Quality Score

93/100

Supported Platforms

Universal

Our assessment of higgsfield-generate

higgsfield-generate scores 93/100 on our quality scale, 257th of 950 AI & Machine Learning skills we index (top 28%).

Its SKILL.md is 24 KB long, well organised into 19 sections with 6 code examples: a thorough specification that gives an agent plenty to work with.

With 1,120 GitHub stars, it is one of the more widely adopted skills in the catalogue.

Substance
30/30
Structure
20/20
Description
15/15
Adoption
13/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated about 2 months ago, so higgsfield-generate is actively maintained.
  • Our last check on 2026-10-26 found the source still online.
  • It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

Review

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands (1 minor note below). An AI review judged it risky: Step 0 instructs the agent to install the CLI by piping a remote script into a shell: `curl -fsSL https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh | sh`.

  • noteInstalls by piping a downloaded script into a shellline 37
    curl -fsSL https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh | sh

AI review: risky

  • Step 0 instructs the agent to install the CLI by piping a remote script into a shell: `curl -fsSL https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh | sh`
  • Because this is a SKILL.md file, the agent would follow the command, and piping a downloaded script directly to `sh` bypasses package-manager verification
  • No malicious behavior such as credential theft or destructive commands was found, but the remote-script install pattern weakens execution safeguards

AI review by kimi-k2.7-code on 2026-10-04. Automated pattern scan on 2026-10-04. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

higgsfield-generate compared with similar skills

All 4 of these similar skills score higher than higgsfield-generate; compare them before choosing.

SkillScoreStarsUpdatedFormat
higgsfield-generate (this skill)by higgsfield-ai931.1k2mo agoSKILL.md
claude-memby thedotmack100117.6ktodayCLAUDE.md
taste-skillby Leonxlnx100116.8k8d agoCLAUDE.md
Understand-Anythingby Egonex-AI10092.8k1d agoCLAUDE.md
headroomby headroomlabs-ai10079.8ktodayCLAUDE.md

Frequently asked questions

How do I install higgsfield-generate?
Run npx skills add higgsfield-ai/skills --skill higgsfield-generate. The install tabs above show the steps for each supported agent.
Which AI agents does higgsfield-generate work with?
It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
Is higgsfield-generate safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands (1 minor note below). An AI review judged it risky: Step 0 instructs the agent to install the CLI by piping a remote script into a shell: curl -fsSL https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh | sh. It is MIT-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is higgsfield-generate still maintained?
The repository was last updated about 2 months ago, so higgsfield-generate is actively maintained.

version: 0.13.0 name: higgsfield-generate description: | Generate images/videos/3D assets/audio via Higgsfield AI. Defaults: GPT Image 2.5 for image/design/text, Seedance 2.5 for video, Nano Banana 2 for cartoon characters, Marketing Studio for ads, Seed Audio 1.0 for audio. Use when: "generate an image", "make a video", "animate this photo", "image-to-video", "edit/stylize/remix this image", "reframe this video", "edit this video from a sketch", "create a 3D model/GLB", "create a sound effect", "make music", "text-to-audio", "create an ad", "make a UGC video", "unboxing", "presenter video", "import product from URL", or "analyze video virality". Supports generic generation, workflows, Marketing Studio, and Virality Predictor. Chain with higgsfield-soul-id for face/identity consistency. NOT for: Soul training, brand systems/brandbooks (use higgsfield-brandkit), photoshoots, cards, YouTube thumbnails (use higgsfield-youtube-thumbnail), explainers (use higgsfield-video-explainer), playable games/assets (use higgsfield-websites), or TTS. argument-hint: "[prompt-or-analysis-request] [--model <name>] [--image|--video <path-or-id>]" allowed-tools: Bash

Higgsfield Generate

Submit jobs to any Higgsfield model. Wraps the higgsfield CLI. Covers generic image/video/3D/audio generation, Marketing Studio (branded ads, avatars, products, hooks, settings), and, secondarily, Virality Predictor video scoring.

Step 0 — Bootstrap

Before any other command:

  1. If higgsfield is not on $PATH, install it:
    curl -fsSL https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh | sh
    
  2. If higgsfield account status fails with Session expired / Not authenticated, ask the user to run higgsfield auth login (interactive) and wait for confirmation.

UX Rules

  1. Be concise. No raw IDs, no JSON dumps in chat. Print the media URL for generated assets, or the text summary for Virality Predictor.
  2. No internal jargon. Don't narrate "calling higgsfield cost", "polling job".
  3. Detect the user's language from the first message and reply in it. Technical args (--aspect_ratio 16:9) stay English.
  4. Don't batch-ask. Pick a sane default model and ask one thing at a time only if genuinely missing.
  5. Don't pre-estimate cost or optimize for cheaper models unless the user asks. Prefer the quality default first.
  6. Pass --wait to generate create so the command blocks until done and prints the result URL itself. Avoid the two-step create → wait pattern.

Discovery guardrail

When looking for a Higgsfield feature/model, do not rely only on semantic search or CLI --help. First run an unfiltered model list, then inspect likely job_set_type names. If the user says a model exists but search returns no results, trust that signal and verify with the full model list before answering.

Workflows are separate from models. Discover them with higgsfield workflow list and inspect params with higgsfield workflow get <workflow_name>.

Virality Predictor is exposed as:

  • Customer-facing name: Virality Predictor
  • Technical job_set_type: brain_activity
  • Category/output: text report. This is video-in/text-out analysis, not a text/chat generation model.
  • Input: uploaded video
  • Purpose: finished-video hook, attention, retention, and virality analysis

If the user says "analyze this video", "score this ad", "evaluate the hook", or similar, route to brain_activity even though it appears under text/analysis models. Classify by task intent and required input, not by output category alone.

Workflow — generic generation

  1. Pick a model. Start with the core defaults:

    • GPT Image 2.5 → default image model for high-fidelity general generation, graphic design, UI, banners, typography, and on-image text.
    • Seedance 2.5 (seedance_2_5) → SOTA default video model for serious motion, cinematic clips, multi-shot work, and image-to-video. Supports 4–30s output up to 1080p; use Seedance 2.0 when native 4K is required.
    • Nano Banana 2 (nano_banana_flash) → cartoon and illustrated characters.
    • Marketing Studio → default for ads, UGC, product demos, unboxing, TV spots, presenter videos, and brand/product workflows.
    • Seed Audio 1.0 → default audio model for text-to-audio, voice, sound effects, ambience, foley, and music-like audio unless the user names Sonilo/Mirelo.

    Only the models below are picked without being asked. Any other model is used only when the user names it or explicitly asks for what it offers (cheaper, faster, a specific look); see references/model-catalog.md. A model the user names stays in use for follow-ups on the same work.

    Image:

    • Complete brand identity, logo system, palette, typography, brandbook, packaging system, signage, or coordinated branded asset suite → use higgsfield-brandkit instead.
    • YouTube thumbnail, Shorts cover, or Instagram video cover → use higgsfield-youtube-thumbnail instead.
    • Brand product visual (Pinterest pin, lifestyle, hero banner, ad pack, virtual try-on) → use higgsfield-product-photoshoot instead. NOT this skill.
    • Branded ad image with avatar + product (Marketing Studio shape) → Marketing Studio Image (see Marketing Studio below)
    • Soul Character (reference id from higgsfield-soul-id) → Soul 2.0 for stills, Soul Cinema (soul_cinematic) for cinematic
    • New original person — UGC, editorial, fashion, lifestyle → Soul 2.0
    • Cinematic still frame → Soul Cinema (soul_cinematic)
    • Character sheet, one-shot face from reference photos, or face edit on a real photo → Seedream 5.0 Pro (seedream_v5_pro)
    • Locations / environments / no-people scenes → Soul Location
    • Logo, icon, vector-like illustration, brand mark, controlled-palette graphic → Recraft V4.1 (recraft_v4_1, often with --model_type vector)
    • Cartoon or illustrated characters, heavily textured photos → Nano Banana 2 (nano_banana_flash). The id nano_banana_2 is an alias for Nano Banana Pro, not Nano Banana 2
    • Default for everything else → GPT Image 2.5. Graphic design, UI, banners, typography, product concepts, editing, and high-fidelity general generation.
    • User asks for cheaper or faster → Nano Banana 2 Lite (nano_banana_2_lite) for reference edits, Z Image for drafts.

    Video:

    • Complete narrated explainer from a topic, story, or document → use higgsfield-video-explainer, not generic video generation.
    • All advertising / commercial / branded ad video → Marketing Studio (see Marketing Studio below)
    • Edit existing video from sketch/timestamp, or reframe to another aspect ratio → workflow (draw_to_video or reframe), not a model. See references/workflows.md.
    • Default for everything else → Seedance 2.5 (seedance_2_5): multi-shot, consistent identity, motion-heavy, image-to-video, editing, extension, 4–30s. Modes t2v / omni_reference / video_edit / video_extension; use omni_reference for reference inputs, including start/end frames; t2v accepts no media. Up to 1080p. Do not downgrade because another model's schema looks simpler.
    • User asks for 4K → Seedance 2.0 (seedance_2_0); say why you switched.
    • User asks for cheaper or faster → Kling 3.0 Turbo (kling3_0_turbo), Veo 3.1 Lite, or Seedance 1.5 Pro.
    • Named by the user → use it, e.g. Cinema Studio 4.0 (cinematic_studio_video_4_0), Kling 3.0, Veo 3.1, Gemini Omni Flash (gemini_omni), or Grok Video 1.5 (grok_video_v15: one --start-image or --image, duration 2–15s, up to 1080p without reference media).

    Video analysis:

    • Rate a finished video's hook, virality potential, attention, retention, or distraction risk → Virality Predictor (brain_activity). This is a video analysis model that returns a text score/report, not a generated media asset.

    3D:

    • A 3D asset within a playable game or game-wide asset system → use higgsfield-websites (game product type).
    • Create an actual 3D mesh/model/GLB from one or more object/product reference images → Multi-Image to 3D (multi_image_to_3d). Pass 1–4 images with repeated --image; use --should_texture true when the asset needs texture. If the user only asks for a 3D-rendered picture, use an image model instead.

    Audio:

    • Default for audio generation → Seed Audio 1.0 (seed_audio). Use for text-to-audio, sound effects, ambience, foley, impacts, environmental audio, voice-style generations, and music-like audio. It requires --prompt; use optional --audio-references/--image-references only when the user provides references.
    • Use Sonilo Music (sonilo_music) only when the user explicitly asks for Sonilo or you need that specialist music model. It requires --prompt and --duration, and returns audio.
    • Use Mirelo Text to Audio (mirelo_text_to_audio) only when the user explicitly asks for Mirelo or you need that legacy SFX model. It requires --prompt and --duration, and returns audio.

    For the actual --model ID to pass to higgsfield generate create, run higgsfield model list --json | jq to map display names to IDs. See references/model-catalog.md for the full table.

  2. Pass media inputs straight to flags. Media flags accept a local file path or a UUID. CLI auto-uploads paths and auto-detects job vs upload for UUIDs. No need to pre-upload. Each model declares accepted media roles or *_references params — see references/media-inputs.md.

  3. Validate quickly. If unsure of params, run higgsfield model get <jst> --json once and pass only what's needed. Validate the preferred model before falling back to an older one. Use schema defaults otherwise. The server returns adjustments for non-fatal coercions (e.g. aspect_ratio=99:99 → closest match) and a structured error for invalid declared-param values.

  4. Submit and wait in one shot. higgsfield generate create <jst> [--prompt "..."] [media flags] [param flags] --wait. Blocks until terminal status and prints the result on stdout. Tunables: --wait-timeout 20m (default 10m), --wait-interval 5s (default 3s). Virality Predictor does not need a prompt; pass --video.

  5. Deliver. For generated media and 3D assets, send the primary result URL plus a one-line summary (model, duration if video; GLB/asset URL for 3D). For Virality Predictor, deliver the scores, business interpretation, and the Open report link. Do not surface Virality Predictor .glb, .bin, or region-table internals in normal chat output.

To inspect or rerun later, higgsfield generate list --json and higgsfield generate get <id> --json work for retrospection. higgsfield generate wait <id> is still available if you ever need to rejoin a job started without --wait.

For workflow jobs, use higgsfield generate workflow <workflow_name> ... --wait. Cost syntax is higgsfield generate cost workflow <workflow_name> .... See references/workflows.md.

Media flags

| Flag | Purpose | Models that accept it | |---|---|---| | --image <path-or-id> | reference image | most image models, grok_video_v15, multi_image_to_3d, seedance_2_0, seedance_2_5, veo3, marketing_studio_video | | --start-image <path-or-id> | first frame for image-to-video transitions | grok_video_v15, kling3_0, kling3_0_turbo, kling2_6, veo3_1, seedance_2_0, seedance_2_5, marketing_studio_video | | --end-image <path-or-id> | last frame for transitions | kling3_0, seedance_2_0, seedance_2_5, marketing_studio_video | | --video <path-or-id> | reference or analyzed video | seedance_2_0, seedance_2_5, brain_activity | | --audio <path-or-id> | reference audio (lipsync, soundtrack match) | seedance_2_0, seedance_2_5 (reference input; distinct from generating output audio) |

For reference-array models, the explicit flags are --image-references, --video-references, and --audio-references; --image, --video,

Truncated for display — read the full file on GitHub.

Related Skills

View on GitHub
GitHub Stars1.1k
CategoryAI
Updated2mo ago
Forks216

Languages

Python

Trust signals

100/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

No cautions
higgsfield-generate — Universal Skill: Install & Safety Check | SkillAgent