/higgsfield-canvas

name: higgsfield-canvas
description: "Use when the user mentions Higgsfield Canvas, a node-based or node graph workspace, an infinite board/canvas, chaining generations into a pipeline, or wants to wire prompts → images → videos across models on one surface. Covers what Canvas is, the node categories, the seven models that run inside Canvas, the named canvas patterns (Simple Seedance, Extend Video, Image Edit, StoryBoard With Elements, Long Video fan-out), the build-free / generate-paid cost model, reusable templates, assets-as-nodes, and Shared Canvas live collaboration. Also trigger on 'Higgsfield ComfyUI alternative', 'node workflow', or 'connect nodes to build a scene/campaign'."
user-invocable: true
metadata:
  tags: [higgsfield, canvas, node-based, node-graph, infinite-board, pipeline, workflow, shared-canvas, collaboration, storyboard, fan-out]
  version: 1.0.0
  updated: 2026-06-03
  parent: higgsfield

Higgsfield Canvas — Node-Based Production Workspace

<!-- CONTENTS — generated by scripts/build_index.py; do not hand-edit --> **Contents**

• [1. When to use Canvas](#1-when-to-use-canvas)
• [2. Node categories](#2-node-categories)
• [3. Models that run inside Canvas](#3-models-that-run-inside-canvas)
• [4. Named canvas patterns](#4-named-canvas-patterns)
• [5. Cost model](#5-cost-model)
• [6. Templates and assets-as-nodes](#6-templates-and-assets-as-nodes)
• [7. Shared Canvas — live collaboration](#7-shared-canvas--live-collaboration)
• [8. Cross-surface context](#8-cross-surface-context)
• [9. Source acknowledgment](#9-source-acknowledgment)

<!-- /CONTENTS -->

Canvas is a node-based editor where prompts, references, and generations from any Higgsfield model live on a single infinite board. Instead of running each generation in isolation, you connect nodes — a prompt feeds an image, an image feeds a video, a style branches into variations — so a whole scene or campaign becomes one continuous, re-runnable pipeline.

Canvas is its own top-level surface in the Higgsfield nav bar (alongside Image, Video, Cinema Studio, Marketing Studio). It is model-agnostic: it *hosts* the other models rather than being a mode inside any one of them, so this sub-skill routes model-specific craft back to the relevant sibling sub-skill.

**Why Canvas matters for this skill.** Canvas is another place to *deploy the prompts this skill builds* inside the Higgsfield workflow — instead of taking a finished prompt straight to the Image/Video generator or Cinema Studio, you drop it into a **Prompt node** on the board and wire it into a generator. The prompt-craft is identical (MCSLA scene prompts, Seedance prompt modes, GPT Image 2.0 formats — all still apply); Canvas just changes *where* the prompt is executed and lets one prompt feed a multi-step pipeline. Think of the Prompt node as the on-canvas home for everything the rest of this skill teaches.

Translated from Higgsfield's official Canvas guide (`higgsfield.ai/canvas-intro`) plus the in-product Canvas screenshots and a canvas-workflow walkthrough.

---

1. When to use Canvas

Reach for Canvas when the work is a *pipeline*, not a single shot:

• A multi-shot scene or episode where one reference set drives several shot

prompts.

• An ad campaign that fans one product/brand reference into many variants.
• A storyboard that flows assets → story beats → prompts → image/video

generation in columns.

• Any repeatable pipeline you want to save as a template and re-run with

swapped inputs.

For a single prompt-and-generate, the standard Image/Video tabs are simpler. Canvas earns its keep when steps connect.

2. Node categories

A node is one step in the pipeline with typed input sockets (left) and a typed output socket (right); curved edges carry data from one node's output into the next node's input. The board exposes these node categories:

• **Prompt** — text starting points.
• **Image generator** — produces or edits images.
• **Video generator** — produces video.
• **Voice / audio generator** — produces voice or audio.
• **LLM assistant** — a wired-in language model you can task with prompt

drafting or shaping (e.g. a "cinematographer-prompter" role inside a storyboard). It is a general LLM node you author, not a fixed named assistant. (Separate from **Higgsie**, the in-Canvas chatbot — that's a conversational helper, not part of the prompt-to-generator pipeline this sub-skill covers.)

• **Style / motion** — style-transfer and motion-control steps that branch a

look or movement across downstream nodes.

• **Render output** — final deliverables.
• **References** — **Upload** (drop in your own files) and **Assets** (pull

from your library).

Connections are type-aware: an image output feeds an image input, a prompt feeds a generator, and so on. Fan-out (one node feeding many) is free-form; fan-in is more structured.

3. Models that run inside Canvas

All seven Higgsfield models run as nodes on the same board:

| Model | What it's for | Detail | |---|---|---| | **Soul 2.0** | photoreal images, fashion/editorial, consistent characters | `../higgsfield-soul/SKILL.md` | | **Seedance 2.0** | flagship video, 1080p | `../higgsfield-seedance/SKILL.md` | | **Kling 3.0** | cinematic video, multi-shot continuity, native audio | `../higgsfield-motion/SKILL.md` | | **Wan 2.7** | high-action / dynamic motion | `../../model-guide.md` | | **Veo 3.1** | Google flagship video, native audio | `../../model-guide.md` | | **GPT Image 2.0** | 4K image gen, near-perfect text rendering | `../higgsfield-gpt-image-2/SKILL.md` | | **Nano Banana Pro** | precision image editing and placement | `../../image-models.md` |

Mixing models on one board is the point — generate a character in Soul, edit a product in Nano Banana Pro, animate the result in Seedance, all in one graph.

4. Named canvas patterns

The in-product canvases ship as recognizable layouts. Use them as starting shapes:

• **Simple Seedance 2.0** — one image + one prompt → one video.