Node Catalog

Explore the available nodes to build your workflows.

Context

Brand context, briefs, and reference assets.

Brand Context

• Summary: Defines brand name and project brief to anchor downstream AI.
• Inputs: None (manual entry).
• Outputs: Context string with brand name and brief.
• Usage: Fill in brand name and brief, then connect to Prompt Optimizer, Text Generator, Brand Assets, Trend Watcher, or Create Brand Brief.

Create Brand Brief

• Summary: Generates a structured brand brief with selectable sections.
• Inputs: Brand Name + Website URL, or connected brand images.
• Outputs: Full brief markdown and per-section text outputs.
• Usage: Select sections, add optional instructions, then run. Each section appears in its own preview card.

Reference Image

• Summary: Uploads and stores up to 20 reference images for models.
• Inputs: None (upload or drag and drop).
• Outputs: Image list and primary image URL.
• Usage: Upload references and connect to Image Generator, Image Editor, Brand Assets, Image Details, or Pro Video Composer parameters.

Inputs

Foundational prompts and user inputs.

Prompt

• Summary: Writes the base instruction text for your workflow.
• Inputs: None.
• Outputs: Prompt text for downstream nodes.
• Usage: Write a clear instruction and connect it to Image, Video, or Text generation nodes.

Intelligence

Research, optimization, and strategy generation.

Prompt Optimizer

• Summary: Refines rough ideas into model-ready prompts.
• Inputs: Rough idea and/or upstream context.
• Outputs: Optimized prompt variations.
• Usage: Enter a rough idea, choose variations, then run. Connect output to Image Gen or Video Gen.

Trend Watcher

• Summary: Researches live trends and returns platform-ready concepts.
• Inputs: Topic or connected context.
• Outputs: Concept list and raw research.
• Usage: Select platform, audience, and goal, then run. Feed results into Split Prompt or Text Generator.

Brand Assets Generator

• Summary: Builds a queue of branded marketing images.
• Inputs: Brand context, website URL, or reference images.
• Outputs: Asset URLs plus research/visual analysis notes.
• Usage: Set brand name/website and configure campaign goal + production queue in properties.

Split Prompt

• Summary: Splits one prompt into multiple distinct variations.
• Inputs: Any upstream text/context or a local prompt.
• Outputs: List of variations for parallel generation.
• Usage: Choose a variation count, run, then connect each output to Image or Video generators.

Text Generator

• Summary: Produces long-form or multi-variation text with optional images.
• Inputs: Prompt text, optional context or images.
• Outputs: Generated text and variations.
• Usage: Provide a task prompt, then connect results to Human Review or Preview.

Review

Human-in-the-loop approvals.

Human Review

• Summary: Pauses the workflow so a person can approve one option.
• Inputs: Upstream image, video, or text variants.
• Outputs: Approved item passed downstream.
• Usage: Connect generated variants, run the workflow, then click the approved option to continue.

Audio

Voice and speech generation.

Audio Generator

• Summary: Turns scripts into speech with selectable voices.
• Inputs: Prompt text for the voice script.
• Outputs: Audio URL for downstream nodes.
• Usage: Write a script, choose a voice/model, then connect to Lip Sync for talking videos.

Notes

Non-executing documentation nodes.

Sticky Note

• Summary: Adds comments and annotations directly on the canvas.
• Inputs: None.
• Outputs: None (visual-only).
• Usage: Use for documentation, handoffs, or team notes. Resize and recolor as needed.

Video

Video generation and manipulation.

Pro Video Composer (Kling V3)

• Summary: Advanced Kling V3 hub with modular parameter nodes.
• Inputs: Optional parameter nodes for prompt, images, audio, camera.
• Outputs: Generated video URL.
• Usage: Add the hub, then add parameter nodes and connect them to control the generation.

Video Generator

• Summary: Generates video from text or an input image.
• Inputs: Prompt text; optional reference image.
• Outputs: Video URL and asset URLs.
• Usage: Set duration/resolution in properties, connect prompt and optional image, then run.

Video Merger

• Summary: Merges two or more videos into a single sequence.
• Inputs: At least two video URLs.
• Outputs: Merged video URL.
• Usage: Connect multiple videos, reorder in-node if needed, then run.

Lip Sync (LatentSync)

• Summary: Creates a talking video from face media and audio.
• Inputs: One audio + one face image or video.
• Outputs: Generated talking video URL.
• Usage: Connect Audio Generator output and a face image/video, choose mode, then run.

Image

Image generation, editing, and analysis.

AI Model Generator

• Summary: Creates virtual influencer or character portraits.
• Inputs: None (configure demographics and style).
• Outputs: Image URLs and generated prompt text.
• Usage: Choose gender, ethnicity, age, style, and setting, then run.

Image Generator

• Summary: Generates one or multiple images from text and references.
• Inputs: Prompt text and/or reference images.
• Outputs: Primary image URL plus image list.
• Usage: Connect a Prompt or Reference node, choose runs/aspect ratio, then run.

Logo / Poster

• Summary: Generates logo or poster designs with layout controls.
• Inputs: Prompt text; optional reference images.
• Outputs: Image URL.
• Usage: Describe the brand and layout, set size/style in properties, then run.

Image Editor

• Summary: Inpaints or edits an image using a drawn mask.
• Inputs: One input image and a mask drawn in-node.
• Outputs: Edited image URL.
• Usage: Connect an image, draw the mask, write a prompt, then run.

Image Details

• Summary: Extracts colors, aesthetics, environment, and mood.
• Inputs: One image plus selected detail categories.
• Outputs: Structured detail text and variations.
• Usage: Select the details to extract, then run. Each detail appears in its own preview card.