Higgsfield

Every image and video model

Category: AI
Primary Subcategory: Pending

Integration details

Description

Create images, videos, branded content, and websites with Higgsfield in ChatGPT. Start with an idea or reference image, choose a creative model or preset, and refine your results through conversation. With Higgsfield, you can: • Generate images and videos from text or reference images. Create portraits, illustrations, cinematic scenes, or bring a still photo to life. • Browse image and video presets, or apply a named preset such as @Higgsfield /main-character or /brand-monument to a reference image. • Create product photoshoots, brand identities, packaging mockups, social graphics, YouTube thumbnails, and Instagram covers. • Use Ad Multiplier to create independent variations of an existing video ad. Change selected people, products, clothing, objects, backgrounds, or text while preserving untargeted elements. • Make AI-generated UGC-style content, including product showcases, unboxings, tutorials, and fashion try-ons. Create website and app promos with a virtual presenter and real screenshots. • Produce faceless videos, narrated explainers, and episodes with a consistent AI presenter. Write complete YouTube scripts, generate spoken narration, and add subtitles. • Edit footage and create motion graphics with animated text, layouts, transitions, and effects. Receive rendered videos and editable project files for supported workflows. • Build and deploy websites, web apps, and browser games. Create visual assets, refine the design, and update your hosted project through chat. Describe what you want to make, review the results in chat, and build on your previous creations. Connect your Higgsfield account to get started.

Integration type: Plugin
Verification status: Not applicable
Platform: ChatGPT
Category: AI
Primary Subcategory: Pending
Secondary Subcategories: None listed
Brand: Higgsfield
Access: Account required
First tracked: 2026-06-23
Tool count: 18
Geography: US

ChatGPT Plugin Discovery Score

ChatGPT Plugin discovery is coming soon

ChatGPT can surface a Plugin when it matches a user's request.Your Plugin Discovery Score measures how often yours appears.

No spam. Unsubscribe any time.

ChatGPT recommends Airtable when a user asks it to update a CRM. — ChatGPT surfaces Airtable because it matches the user's request.

Primary Subcategory

Competitive lineup

No Primary Subcategory assigned yetOnce Higgsfield has a Primary Subcategory, the Plugins and Connectors it competes with will appear here with their scores.

Tools

18 tools agents can invoke

Produce a complete channel episode carried by one consistent AI presenter, locked to an accepted image or video avatar, from a supplied script or topic. Includes host casting, spoken clips, supporting visuals, authored motion and a measured final edit. Use for a finished AI-hosted episode, not a standalone avatar clip, a faceless narrated video, a product UGC ad, script-only writing, adding a narrator to existing footage, or publishing an existing video.
ai-host-video
Create ordered independent edits from one supplied 4-30 second video with Ad Multiplier while preserving motion, timing, audio, and untargeted text. Activate for "ad multiplier", "multiply my video or ad", or several edits of one clip that replace, add, remove, or change people, products, objects, clothing, backgrounds, attributes, or targeted text. Do not use for ordinary generation, Marketing Studio presets, simple edits, out-of-range sources, or Cartesian asset combinations.
ad-multiplier
Use only when the user asks to produce a finished multi-scene narrator-led video and explicitly requests a faceless channel, YouTube automation, narrated explainer/story/education, documentary, Picture Story, narrated stills, frame-by-frame story, storybook or myth retelling, or kids song video. Topic alone is never enough: a generic video of/about something, including a historical topic, uses ordinary video generation. Do not use for browsing or listing faceless presets: call get_faceless_channel_presets directly without loading this skill. Also exclude planning or ideas, single clips, silent animation, image-to-video, footage edits, ads, product demos, UGC, or any video with a visible on-camera presenter or talking head. This workflow requires a consistent non-photoreal style, reusable assets, narrator voiceover, and burned subtitles.
faceless-video
Execute a named Higgsfield image or video preset invoked as @Higgsfield /preset-name, such as /main-character, /brand-monument or /reel-cover, browse Viral or Marketing Studio galleries with /effects, /product or /motion, or use a named generation model with /MODEL_NAME. Resolve preset names against the catalog before executing; infer intent for unknown commands. Activate for a request to execute or browse presets; a quoted command to translate, an explanation of a URL, or an explicitly negated preset is not an invocation.
higgsfield
Specify native motion for Higgsedit compositions: frame choreography, raw property tracks, token text entrances, shared timelines, sampled curves, steps and bounded counters. Use when designing how frames or text animate. For project assembly, footage editing and rendering, use video-editing.
motion-craft
Use only when the user explicitly names the narrator skill or requests one of three production-ready deliverables: (1) numbered takes fitted to fixed video windows, (2) one continuous long-form story read in a locked voice with explicit measurement and retries for timbre or internal pauses, or (3) an existing video plus a consenting person's photo that must become an on-screen narrator in that same video. Never activate for voice cloning or imitation, voice browsing or listing, ordinary TTS or "read this aloud", an unconstrained audiobook or voiceover, music, SFX, singing, generic dubbing, a voiceover that is only one component of a newly generated ad or video, or a UGC workflow whose locked video model generates native speech (`generate_audio:true`). After a valid activation, collect missing text/media, voice_id, or voice_type; own pacing, speech-duration gates, presenter compositing, retries, and ready delivery; never time-stretch.
narrator
Create finished product photography and product-led brand stills: studio packshots, Shopify or catalog images, lifestyle scenes, product-with-person closeups, Pinterest pins, hero banners, social carousels, static ad packs, virtual-model try-ons, conceptual CGI imagery, and restyles. Use for product photoshoots, packshots, e-commerce imagery, and product campaign stills. Do not use for Amazon-compliance sets, thumbnails, video ads, portraits, or UGC.
product-photoshoot
Activate only when the requested deliverable is a video with captions permanently burned into its pixels, or a faceless workflow explicitly needs caption burning on its finished cut. Use Whisper timing from the video's own audio and return the re-rendered captioned video. Do not activate merely because captions or subtitles are mentioned. Exclude transcription, caption review, translation, authoring, SRT/VTT/sidecar/selectable/live/soft tracks, title cards, and any request that does not modify video pixels. When this gate matches, load this skill immediately, before searching for input files or calling any MCP tool.
subtitles
Produce finished YouTube or Instagram thumbnails, video covers, previews, and high-impact still-image packaging through concept selection, identity-safe casting, 4K rendering, revisions, and durable text export. Activate for an explicit thumbnail, cover, preview image, vertical social cover, before/after cover, or viral-style video packaging request. Do not activate for a generic image, a complete faceless video, channel planning, title ideation without an image, a video edit, or a title card inside video footage.
thumbnail-generation
Produce a finished product-only UGC video with off-screen voiceover; a person may appear only as auxiliary hands, cropped body, or POV. Require UGC or casual creator-style intent together with product-only, no creator on camera, no talking head, or product-as-hero framing. Product-only or faceless framing alone does not qualify a generic commercial. Exclude silent or no-narration requests even when labeled UGC; use ordinary video generation instead. Its off-screen voice is native Seedance audio: do not activate narrator or call separate audio-generation tools. Missing product or duration is an intake gap. Do not use for creator-led reviews, unboxings, tutorials, try-ons, SaaS or website walkthroughs, generic ads, scripts, or footage edits.
ugc-product-video
Produce a finished brand-authorized UGC-style talking-head video in which one consenting adult or generated adult creator demonstrates a product or delivers user-supplied copy. Use for explicit UGC, creator-video, TikTok-style product showcase, or review-style requests that can be rendered without fabricated experience or endorsement; a product is optional, while a missing duration is an intake gap. Do not use for testimonials, impersonation, product-only ads without an on-camera speaker, off-screen voiceover, unboxing-led videos, step-by-step tutorials, try-ons, SaaS or website walkthroughs, generic ads, script-only requests, or edits of existing footage.
ugc-review-video
Produce a finished UGC try-on video where one visible creator wears and poses with a garment, footwear item, bag, jewelry piece, or wearable accessory while showing fit and texture. Use when try-on, wearing, OOTD, fit-check, or video-of-me-wearing intent is explicit. Do not load this skill for a text-only script, outline, shot list, or advice, even if it mentions UGC, OOTD, or try-on; those requests need writing, not the video-production workflow. Missing product, duration, or creator input is an intake gap. Do not use for reviews without a try-on, unboxings, tutorials, product-only ads, SaaS walkthroughs, generic ads, or footage edits.
ugc-try-on-video
Produce a UGC tutorial where one visible creator demonstrates realistic step-by-step use of a specific product and every step has a baked "Step N — Heading" label. Use when tutorial, how-to, or step-by-step intent and creator/UGC framing are explicit. Missing product or duration is an intake gap. Do not use for ordinary reviews, unboxings, try-ons, product-only ads, SaaS walkthroughs, generic ads, scripts, or footage edits.
ugc-tutorial-video
Produce a UGC unboxing where one visible creator opens or has just opened a package and the product reveal is the climax. Use when unboxing, haul, PR-drop, first-reaction, opening-the-box, or reveal intent is explicit. Missing product or duration is an intake gap. Do not use for reviews without an unboxing arc, try-ons, tutorials, product-only ads, SaaS walkthroughs, generic ads, scripts, or footage edits.
ugc-unboxing-video
Produce a finished creator-led UGC video about a website, web app, online service, store, or product page, using real captured screenshots while a talking-head creator narrates. Use for SaaS UGC, site tours, app tours, or requests where the supplied page must appear. Do not load this skill for text-only scripts, outlines, or walkthrough plans, even if they mention UGC or SaaS; do not use it merely as a scriptwriting reference. Missing URL or duration is an intake gap. Do not use for product-only ads, unboxings, tutorials, try-ons, website editing, generated UI, scripts, or footage edits.
ugc-website-video
Edit supplied footage or author file-backed motion graphics with Higgsedit. Activate only for a requested edit or graphics deliverable: cuts, trims, soundtrack changes, native layouts, animated text, shaders, overlays or title cards. Do not activate when the user only asks to analyze, summarize, describe, critique or review a video or YouTube link, including scene-by-scene breakdowns. Timeline inspection is supporting work for a requested edit, not a standalone activation trigger. Exclude footage generation, generative restyling, transcription, subtitle translation/review and ordinary speech-caption burning (use subtitles).
video-editing
Activate when the user wants a real, live web product built or edited on Higgsfield: a website, landing page, portfolio, marketing site, web app, internal tool, SaaS front end, or a browser game. Also activate for any edit, redesign, or redeploy of a site created earlier here. Owns the whole build — choosing the product type, creating the site, writing the code in the sandbox, generating its visual assets, and shipping it live at its own subdomain. Collect the missing product type, brand, or scope after activation; their absence is not a reason to skip this skill. Do not use for generating a standalone image, video, or audio clip, for writing copy or code the user will host elsewhere, for reviewing an external URL, or for questions about a site that is not built here.
website-builder
Write a complete YouTube script with a full spoken body in one of six genres: business/finance, tech review, commentary, documentary, true crime or explainer. Includes hook options, timestamps, production cues and a retention map. Use for full scripts, not hook-only requests, ad copy or finished video production; ai-host-video may call this skill for its script-writing stage.
youtube-script

Higgsfield FAQ

How do I improve a ChatGPT Plugin's discoverability?

The levers are the listing surface agents actually read: names, descriptions, keywords, tool metadata, and registry health. Which lever matters depends on where discovery breaks, which is what continuous measurement shows.

Where is this profile measured?

This profile uses the geography attached to the latest public registry snapshot: US. Locale tags are intentionally omitted.