Konnektor Higgsfield AI

Wofür er sich eignet

• Werbemittel für eine Kampagne erzeugen, ohne für jedes Motiv ein Fotoshooting zu buchen
• Kurzvideos für soziale Netzwerke aus vorhandenem Material bauen
• Produktbilder freistellen, erweitern und in mehreren Seitenverhältnissen ausspielen
• Sprachaufnahmen für Erklärvideos erzeugen, auch mehrsprachig
• Eine Figur oder ein Gesicht über eine ganze Bildserie hinweg gleich aussehen lassen

Tools (73)

• animation_actions: Read-only catalog of the 3D rig animation library (678 actions: locomotion, gestures, dancing, combat, daily actions).
• apps_describe: Get an app's action contract: with `action`, the full input/output schema + execution mode for that one action; without it, a summary of every action.
• apps_invoke: Run one described action on a Marketplace app AS the current user.
• apps_search: Search Higgsfield Marketplace apps callable through MCP.
• balance: Get the user's available credits and current subscription plan.
• cancel_trial_auto_renewal: Cancel the auto-renewal of the Higgsfield MCP free trial.
• confirm_billing_purchase: INTERNAL - invoked ONLY by the plans widget on an explicit user Confirm click.
• confirm_trial_cancel: INTERNAL - invoked ONLY by the cancel-trial confirmation widget on an explicit user click of 'Cancel auto-renewal'.
• create_voice: Open the Create Voice Apps UI.
• create_voice_from_confirmed_audio: Backend-only creation of a cloned voice from an already confirmed audio upload.
• dubbing: Dub a video into another language: translate the spoken audio, synthesize it in the target language, and lip-sync the result back onto the video.
• generate_3d: Generate a 3D GLB mesh.
• generate_audio: Generate one speech/voice request (text-to-speech) and render it in the generation widget.
• generate_audio_batch: Submit 1-12 independent audio generations in parallel without opening a widget.
• generate_image: Generate one image request and render its result(s) in the generation widget.
• generate_image_batch: Submit 1-12 independent image generations in parallel without opening a widget.
• generate_video: Generate one video request and render its result(s) in the generation widget.
• generate_video_batch: Submit 1-12 independent video generations in parallel without opening a widget.
• get_explainer_presets: Show the explainer video style presets (CMS-managed catalog).
• get_workflow_bundle_file: Read a safe text file or directory from a workflow's resource folder.
• get_workflow_instructions: Faceless video generation, AI-narrated video, narrated animated explainer video, narrated / personal / philosophical story video, YouTube/Instagram thumbnail or video cover, UGC-style ad for a website / SaaS / store / product page from its…
• job_display: Show one specific previous generation in the single-result UI widget by job ID.
• job_status: Check the status and results of an async job.
• jobs_wait: Long-poll 1-12 generation jobs together without opening a widget.
• list_voices: List available voices for speech and voice tools.
• list_workspaces: List every workspace the user can access (their private workspace plus any shared/team workspaces).
• media_confirm: Confirm file uploads after using media_upload's upload_url method.
• media_import_url: Import an HTTPS image, video, or audio URL into Higgsfield storage and return a confirmed media_id.
• media_upload: Upload media for use in generation, or general files (documents, archives, code) for sharing.
• media_upload_widget: Open the Higgsfield upload widget for a user-provided local image, video, or audio file.
• models_explore: Find generation models.
• motion_control: Animate an existing character image with the motion and camera movement from a reference video using Kling 3.0 Motion Control.
• outpaint_image: Expand or uncrop an existing image by outpainting beyond the original frame while preserving the source content.
• personal_clipper_create: Turn YouTube videos into ready-to-share clips.
• personal_clipper_jobs: Show recent clipping jobs.
• personal_clipper_status: Check clip creation progress.
• presets_show: Show available Higgsfield presets for image-to-video generation.
• reframe: Expand or reframe an existing video to a new aspect ratio while preserving the source content.
• remove_background: Remove or cut out the background from an existing image or video.
• resolve_explainer_preset: Resolve a explainer video style preset (from get_explainer_presets) into a style reference media_id: the backend imports the preset's style image into the user's media storage.
• reveal_generation: Confirm the user has rights to the content of an `ip_detected` generation and flip its status to `completed`.
• sandbox_exec: Execute a shell command in a remote Higgsfield cloud Linux sandbox - NOT your local machine or the client's own shell.
• select_workspace: Set or clear the active workspace - the one all subsequent MCP operations bill against and read from (generations, balance, transactions, uploads, custom references).
• shorts_studio_create: Start a Shorts Studio short: restyle one uploaded source video (4s - 120s) into a set of AI-generated short-form clips using a style preset.
• shorts_studio_create_preset: Create a user-owned Shorts Studio style preset from reference media (videos + images).
• shorts_studio_list_presets: Browse Shorts Studio style presets - the visual STYLE a short is restyled toward.
• shorts_studio_list_sessions: List the caller's past Shorts Studio sessions (newest first) to find a session_id to poll with shorts_studio_status.
• shorts_studio_status: Poll one Shorts Studio session.
• show_characters: Soul Characters widget - reusable trained identity models.
• show_generation_by_ids: Render exactly 1-60 requested generation jobs in the full-profile gallery widget, ordered by index and paginated locally in groups of 12.
• show_generations: Browse completed non-Marketing Studio generation history and render one paginated page in the gallery widget.
• show_marketing_studio: When replying to the user, do not say `ms_image` - refer to it as "DTC Ads".
• show_marketing_studio_generations: Browse past completed Marketing Studio generations only.
• show_medias: List your uploaded media files by type.
• show_plans_and_credits: Open the single combined pricing widget for everything billing-related.
• show_reference_elements: Elements widget - reusable characters / environments / props per workspace.
• sync_agents: Sync Agents - imports the user's user-authored Skills and a personality dump from the current host LLM into Higgsfield.
• tiktok_accounts: List the user's connected TikTok accounts.
• tiktok_connect: Start connecting the user's TikTok account.
• tiktok_music_trending: List trending commercially licensed tracks from TikTok's Commercial Music Library for the connected account.
• tiktok_music_tune: Open the tuning editor for one Commercial Music Library track the user already picked (via tiktok_music_trending): trim start/end and set track/original volumes.
• tiktok_prepare_publish: Step 1 of publishing to TikTok.
• tiktok_publish: Step 2 of publishing.
• tiktok_publish_status: Step 3 of publishing.
• tiktok_reconnect: Re-run the TikTok OAuth for an existing connector in `error` status (expired/revoked access).
• transactions: List the user's credit transactions (spend/refund/grant/deduct), newest first.
• upscale_image: Upscale and enhance an existing image.
• upscale_video: Upscale and enhance an existing video.
• video_analysis_create: Start a scene-by-scene analysis of a video.
• video_analysis_jobs: List the user's video analyses in the current workspace, newest first.
• video_analysis_status: Get the status and result of a video analysis.
• virality_predictor: Virality Predictor predicts a video's virality potential, engagement, attention, audience response, retention risk, hook strength, and creative performance with an interactive dashboard.
• voice_change: Replace the spoken voice in a video with a different voice while keeping the original timing and visuals, then re-merge the new audio onto the video.

Beispielanfragen

• “Erzeuge ein Produktbild unserer Verpackung auf einem hellen Steintisch, Hochformat 4 zu 5.”
• “Skaliere dieses Bild auf 4K und stelle den Hintergrund frei.”
• “Mach aus diesem Querformat Video eine Hochformat Fassung für soziale Netzwerke.”
• “Sprich diesen Text als ruhige weibliche Stimme auf Schweizer Hochdeutsch ein.”
• “Wie viele Credits habe ich noch und was hat die letzte Erzeugung gekostet?”

Higgsfield AI ist einer von vielen Konnektoren im AIWerk-Katalog. Jeder Konnektor ist signiert und geprüft. Sie können ihn selbst auf Ihrem Rechner installieren oder von AIWerk betreiben lassen.