Node Types

TongFlow provides a rich library of nodes organized into six categories. This reference covers each category and its nodes.

Data Nodes

Data nodes store and display content. They are the starting and ending points of your workflows.

NodeDescriptionUse Case
ImageDisplays imagesView generated or uploaded images
TextContains text contentStore prompts, scripts, or results
VideoPlays video filesPreview generated or uploaded videos
AudioPlays audio filesListen to music, speech, or effects
FileHolds document filesStore PDFs, documents
Model3D model viewerDisplay generated 3D assets

Add Nodes

Add nodes are the entry points for bringing content into your workflow.

NodeDescriptionInput Types
Add ImageUpload or generate imagesJPG, PNG, WebP
Add TextEnter or paste textPlain text
Add VideoUpload video filesMP4, MOV, WebM
Add AudioUpload audio filesMP3, WAV, M4A
Add LinkImport from social mediaTikTok, Douyin, Instagram, Xiaohongshu
Add FileUpload documentsPDF, DOCX, TXT
Add ModelUpload 3D modelsGLB, GLTF

Transform Nodes

Transform nodes are where AI magic happens. They convert one type of content into another.

Text Generation

NodeInput โ†’ OutputDescription
Generate TextText โ†’ TextAI writing and chat
Voice to TextAudio โ†’ TextTranscription
Image to TextImage โ†’ TextDescribe images
Video to TextVideo โ†’ TextDescribe video content
File to TextDocument โ†’ TextExtract text from PDFs

Image Generation

NodeInput โ†’ OutputDescription
Text to ImageText โ†’ ImageGenerate images from descriptions
Image EditImage + Text โ†’ ImageModify images with instructions
Multi-angle EditImage โ†’ ImagesCreate consistent multi-view edits
Upscale ImageImage โ†’ ImageEnhance resolution
Segment ImageImage โ†’ ImageRemove backgrounds

Video Generation

NodeInput โ†’ OutputDescription
Image to VideoImage โ†’ VideoAnimate still images
Text to VideoText โ†’ VideoGenerate videos from descriptions
Speech to VideoAudio + Text โ†’ VideoCreate videos with voice
Upscale VideoVideo โ†’ VideoEnhance video quality
Remove SubtitleVideo โ†’ VideoClean subtitle text from videos
Remove WatermarkVideo โ†’ VideoRemove watermarks

Audio Generation

NodeInput โ†’ OutputDescription
Text to SpeechText โ†’ AudioNatural voice synthesis
Text to MusicText โ†’ AudioGenerate music from descriptions
Clone VoiceAudio + Text โ†’ AudioCopy voice characteristics
Denoise AudioAudio โ†’ AudioRemove background noise
Separate AudioAudio โ†’ Audio(s)Split vocals and instruments

Compose Nodes

Compose nodes combine multiple inputs to create new content.

NodeInputsOutputDescription
Avatar VideoImage + AudioVideoCreate talking head videos
Merge Video AudioVideo + AudioVideoReplace or add audio track
Mix VideoVideo + ImageVideoOverlay effects on video
Concat VideoVideosVideoJoin multiple clips
Image FusionImagesImageBlend multiple images
Add SubtitlesVideo + TextVideoBurn subtitles into video

Batch Nodes

Batch nodes process multiple items or prepare content for batch operations.

NodeDescriptionUse Case
Arrange TextOrganize multiple text itemsPrepare batch prompts
Video InfoExtract video metadataGet duration, resolution, etc.
Drop VideoRemove specific framesEdit video sections
Concat VideoJoin multiple videosCreate compilations

Decompose Nodes

Decompose nodes split content into parts.

NodeInputOutputDescription
Split VideoVideoVideo segmentsDivide by time or scenes

Node Anatomy

Every node shares these common elements:

โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”
โ”‚  Icon    Title    โ‹ฎ Menu   โ”‚  โ† Header
โ”œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ค
โ”‚                             โ”‚
โ”‚       Node Content          โ”‚  โ† Content area
โ”‚    (preview/controls)       โ”‚
โ”‚                             โ”‚
โ”‚ โ—‹                         โ—‹ โ”‚  โ† Handles (input/output)
โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜
  • Header: Icon, title, and options menu
  • Content: Preview or input controls
  • Handles: Connection points (left = input, right = output)

Next Steps