← 返回 Skills 市场
higgsfield

Higgsfield Generate

作者 Yerzat Dulat · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
50
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install higgsfield-generate
功能描述
Generate images and videos via Higgsfield AI through 30+ models including Nano Banana 2, Soul V2, Veo 3.1, Kling 3.0, Seedance 2.0, Flux 2, GPT Image 2, plus...
使用说明 (SKILL.md)

Higgsfield Generate

Submit jobs to any Higgsfield model. Wraps the higgsfield CLI. Covers generic image/video gen and Marketing Studio (branded ads, avatars, products).

Step 0 — Bootstrap

Before any other command, make sure the CLI is installed and authenticated:

  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, opens a browser) and wait for them to confirm before continuing.

Skip both checks if higgsfield account status already prints account info.

UX Rules

  1. Be concise. No raw IDs, no JSON dumps in chat. Print result URL when ready.
  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. Just submit unless the user asks.
  6. Pass --wait to generate create so the command blocks until done and prints the result URL itself. Avoid the two-step createwait pattern.

Workflow — generic generation

  1. Pick a model. Practical defaults from production use:

    Image:

    • 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)
    • Aesthetic UGC / fashion editorial / lifestyle character → Soul 2.0
    • Cinematic still frame → Soul Cinema
    • Highly characterful creative persona (text-only, distinctive) → Soul Cast
    • Locations / environments / no-people scenes → Soul Location (best in class)
    • Vector illustrations OR face edit + complex scene swap → Seedream 4.5
    • Soul Character (reference id from higgsfield-soul-id) → Soul 2.0 for stills, Soul Cinema for cinematic
    • Fast and cheap iteration → Z Image
    • Character or cartoon-style work → Nano Banana 2; step up to Nano Banana Pro on hard cases
    • Default for everything else → GPT Image 2. Graphic design, UI, banners, typography, and high-fidelity general generation.

    Video:

    • All advertising / commercial / branded ad video → Marketing Studio (see Marketing Studio below)
    • Default all-purpose serious video (multi-shot, consistent identity, motion-heavy) → Seedance 2.0. SOTA.
    • Single-plane scene without strong dynamics, cheaper than Seedance 2.0 → Kling 3.0
    • Cheap clean shot without cuts → Seedance 1.5 Pro
    • Cinema-grade highest fidelity → Cinema Studio Video 3.0
    • Cheap with strong physics, no audio needed → Minimax Hailuo
    • Fast batch / volume → Veo 3.1 Lite

    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 roles (image, start_image, end_image, video, audio) — see references/media-inputs.md.

  3. Validate quickly. If unsure of params, run higgsfield model get \x3Cjst> --json once and pass only what's needed. 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 \x3Cjst> --prompt "..." [media flags] [param flags] --wait. Blocks until terminal status and prints the result URL on stdout. Tunables: --wait-timeout 20m (default 10m), --wait-interval 5s (default 3s).

  5. Deliver. Send the URL plus a one-line summary (model, duration if video).

To inspect or rerun later, higgsfield generate list --json and higgsfield generate get \x3Cid> --json work for retrospection. higgsfield generate wait \x3Cid> is still available if you ever need to rejoin a job started without --wait.

Media flags

Flag Use for Models that accept it
--image \x3Cpath-or-id> reference image most image models, seedance_2_0, veo3, marketing_studio_video
--start-image \x3Cpath-or-id> first frame for image-to-video transitions kling3_0, kling2_6, veo3_1, seedance_2_0, marketing_studio_video
--end-image \x3Cpath-or-id> last frame for transitions kling3_0, seedance_2_0, marketing_studio_video
--video \x3Cpath-or-id> reference video seedance_2_0
--audio \x3Cpath-or-id> reference audio (lipsync, soundtrack match) seedance_2_0 (use this, NOT --generate-audio)

Each flag accepts either a local file path (auto-uploaded) or a UUID (upload id from higgsfield upload create, or a previous job id). Each model declares its own role set via MEDIA_ROLES. See references/media-inputs.md for the full table.

Common params

Flags pass through to model schema. Use higgsfield model get \x3Cjst> to discover.

higgsfield generate create gpt_image_2 --prompt "neon city at dusk" --aspect_ratio 16:9 --resolution 2k --wait
higgsfield generate create nano_banana_2 --prompt "anime character concept, expressive pose" --image ./ref.png --wait
higgsfield generate create seedance_2_0 --prompt "camera dollies in" --start-image ./first.png --duration 8 --wait
higgsfield generate create text2image_soul_v2 --prompt "..." --soul-id \x3Csoul_ref_id> --wait

For machine-readable output (chained pipelines, agent context), add --json. With --wait --json you get the final job object array. Without --wait, you get the job IDs.

Stdin prompt: echo "..." | higgsfield generate create z_image --wait.

Marketing Studio

Branded image/video gen: avatars + products + ad-style modes. Use models marketing_studio_video and marketing_studio_image.

Concepts

  • Avatar — presenter face. Curated preset (browse higgsfield marketing-studio avatars list) or custom (uploaded photos via higgsfield marketing-studio avatars create).
  • Product — brand item with title + reference images. Imported from URL (higgsfield marketing-studio products fetch --url ...) or created from uploaded images (higgsfield marketing-studio products create).
  • Webproduct — App Store / web page version. Auto-routes when fetching App Store URLs.

UX rules (additional)

  • One question per phase. Don't ask product+avatar+mode upfront.

Workflow — quick ad video

  1. Get product.
    • URL → higgsfield marketing-studio products fetch --url \x3Curl> --wait (polls until import done)
    • Local images → higgsfield upload create \x3Cphoto>... then higgsfield marketing-studio products create --title "..." --image \x3Cid>... Capture product id.
  2. Pick avatar.
    • Default: higgsfield marketing-studio avatars list and pick a preset matching the brand voice.
    • Custom: higgsfield marketing-studio avatars create --name "..." --image \x3Cupload_id>.
  3. Pick mode. Default ugc. Other slugs (canonical from MCP): ugc_how_to, ugc_unboxing, product_showcase, product_review, tv_spot, wild_card, ugc_virtual_try_on, virtual_try_on. See references/marketing-modes.md.
  4. Generate (one-shot).
    higgsfield generate create marketing_studio_video \
      --prompt "..." \
      --avatars '[{"id":"\x3Cavatar_id>","type":"preset"}]' \
      --product_ids '[\x3Cproduct_id>]' \
      --mode ugc \
      --duration 15 \
      --resolution 720p \
      --aspect_ratio 9:16 \
      --wait
    
    Resolution is 480p or 720p. Aspect ratio is one of auto/21:9/16:9/4:3/1:1/3:4/9:16. --generate-audio true is supported here (unlike seedance_2_0). --wait blocks until done; bump --wait-timeout 30m for longer ad runs.
  5. Deliver. URL + one-line summary (mode, duration).

Click-to-Ad shortcut (URL-driven)

When the user gives a product URL and wants a marketing video in one go:

# 1. Trigger fetch (returns the product id and starts background scrape)
higgsfield marketing-studio products fetch --url https://shop.example.com/sneakers --wait

# 2. Generate the marketing video against the same URL — backend reuses the entity
higgsfield generate create marketing_studio_video \
  --url https://shop.example.com/sneakers \
  --mode ugc \
  --duration 15 \
  --aspect_ratio 9:16 \
  --wait

Backend dedupes by URL, so repeated runs reuse the existing entity instead of re-fetching.

Workflow — marketing image

Same as above but use marketing_studio_image model:

higgsfield generate create marketing_studio_image \
  --prompt "..." \
  --aspect_ratio 1:1 \
  --resolution 2k \
  --wait

Errors

  • Missing required params: prompt → user gave no prompt; ask for it.
  • Invalid values: aspect_ratio=99:99 (allowed: ...) → bad enum; pick from allowed.
  • Unknown params: foo → schema doesn't accept that flag; check higgsfield model get \x3Cjst>.
  • Session expiredhiggsfield auth login.

See references/troubleshooting.md for more.

Reference docs

Load on demand:

  • references/model-catalog.md — picking the right model for the task
  • references/prompt-engineering.md — writing prompts that work
  • references/media-inputs.md — image/video reference flows
  • references/troubleshooting.md — common errors and fixes
  • references/marketing-avatars.md — preset vs custom avatars
  • references/marketing-products.md — URL fetch vs manual product create
  • references/marketing-modes.md — every Marketing Studio mode
安全使用建议
Before installing, consider installing the Higgsfield CLI yourself from a verified source instead of allowing an agent-run remote installer. Use the skill only with the Higgsfield account and media files you intend to upload, and ask for cost estimates or confirmations when credit usage matters.
功能分析
Type: OpenClaw Skill Name: higgsfield-generate Version: 1.0.0 The skill bundle provides a comprehensive interface for the Higgsfield AI generation service, but it is classified as suspicious due to high-risk execution patterns in SKILL.md. Specifically, the 'Bootstrap' section instructs the AI agent to install the CLI using a `curl | sh` command from a remote GitHub repository (https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh), which constitutes unverified remote code execution. While the functionality (file uploads, network requests, and CLI interaction) appears aligned with the stated purpose of media generation, the reliance on broad Bash permissions and remote scripts creates a significant attack surface for potential exploitation.
能力评估
Purpose & Capability
The stated purpose matches the instructions: it generates images/videos through Higgsfield models and Marketing Studio. Users should still notice that this involves third-party job submission, uploads, and account actions.
Instruction Scope
Most commands are scoped to the Higgsfield CLI, but the skill tells the agent to submit generation jobs without a cost estimate unless the user asks.
Install Mechanism
There is no install spec, but SKILL.md instructs the agent to run a remote unpinned `curl | sh` installer from GitHub if the CLI is missing.
Credentials
Bash access and local media uploads are purpose-aligned for a CLI-based generation skill, but they can send private files to Higgsfield.
Persistence & Privilege
The skill relies on a Higgsfield CLI login/session and can create uploads, products, avatars, and generation jobs in that account. No hidden background persistence is shown.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install higgsfield-generate
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /higgsfield-generate 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
- Initial release of higgsfield-generate for image and video generation via Higgsfield AI, supporting 30+ models. - Supports a wide range of tasks: text-to-image, image-to-image, image-to-video, reference-based generation, and branded ad creation through Marketing Studio. - Automatic model selection and input handling with concise, user-friendly interaction rules. - Includes dedicated workflows and parameter flags for both generic generation and branded ad content (avatars, products, marketing videos/images). - Ensures easy CLI installation, authentication, and result retrieval, delivering output URLs with brief summaries.
元数据
Slug higgsfield-generate
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

Higgsfield Generate 是什么?

Generate images and videos via Higgsfield AI through 30+ models including Nano Banana 2, Soul V2, Veo 3.1, Kling 3.0, Seedance 2.0, Flux 2, GPT Image 2, plus... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 50 次。

如何安装 Higgsfield Generate?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install higgsfield-generate」即可一键安装,无需额外配置。

Higgsfield Generate 是免费的吗?

是的,Higgsfield Generate 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Higgsfield Generate 支持哪些平台?

Higgsfield Generate 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Higgsfield Generate?

由 Yerzat Dulat(@higgsfield)开发并维护,当前版本 v1.0.0。

💬 留言讨论