Higgsfield is an AI media generation platform for creating short videos, images, and motion effects from text and reference assets. Use this skill for any request that asks to produce, animate, restyle, or stage media via Higgsfield's models (DoP camera-aware video, Soul photoreal image, Speak lip-sync, plus motion/effects models surfaced through Marketing Studio).
Capabilities
- Generate images from a text prompt with an optional aspect ratio, style/model choice, and one or more reference images for likeness, composition, or style transfer.
- Generate videos from a text prompt and/or a starting image. Camera-aware video supports specific shot intents (push-in, orbit, dolly, etc.); motion-effect generation drives stylized animation from a still.
- Apply a named Marketing Studio preset (look, motion effect, or template) to a prompt or reference image to match a current trend or campaign style without hand-tuning parameters.
- Maintain persistent characters: list saved characters and reuse a character reference across generations so the same face/identity appears in new scenes.
- Predict the virality of a generated piece of media before publishing, to choose between candidates.
Asset and job lifecycle
- Upload a reference image or audio asset, then confirm it so it becomes addressable by id in subsequent generation calls. Generations accept these media ids in their reference slots; never paste a public URL into a prompt when the asset is uploadable.
- Generations are asynchronous. After a generate call, poll job status until completion, then fetch the job display to read the final media ids and rendered URLs. A pending status is normal for video; do not retry the generate call while a job is still running.
- List past generations to recover work the user mentions ("the cinematic kitchen video from earlier") without asking for ids. List media to retrieve raw uploads or render outputs by recency or type.
Model and template selection
- Explore the model catalog to discover which models are currently available and what each is tuned for (photoreal stills, camera-aware video, lip-sync, effect transfer). Pick the model that matches the user's described output, not the most expensive option.
- Marketing Studio presets bundle a model + parameters + style guidance into a single named template. Prefer a preset when the user names a trend or a look ("Y2K music video", "product hero shot"); fall back to raw model parameters when they describe a custom intent.
Workspace and account scoping
- All generations, characters, and media belong to a workspace. List workspaces and select the right one before generating when the user mentions a specific brand, client, or project; otherwise the current workspace persists across calls.
- Credit balance, plan tier, and transaction history are available for "do I have enough credits?" or "what did I spend?" questions. Read balance for the instantaneous number, plans-and-credits for the entitlement view, and transactions for spend history. Generations consume credits; refuse to fire a long video render if the balance check shows it will fail.
Output handling
- Generated media is returned as URLs plus internal media ids. Surface the rendered URL to the user and keep the media id internally so follow-up calls (restyle, re-cut, virality scoring, reuse as reference) work without re-uploading.
- When the user says "make another like that" or "use the same character", resolve the prior generation or character by listing recent work first; do not re-prompt them for an id they never saw.
