Floyo
Floyo
Workflows
API
Pricing
Floyo
Floyo
Workflows
API
Pricing
Last updated
2026-08-18

Run hundreds of ComfyUI nodes and workflows in your browser.

ComfyUI and My Files on Floyo

A collection of custom nodes for ComfyUI designed specifically for enhancing video projects, including tools for film grain, color matching, and video enhancement. This repository offers a comprehensive workflow for video creation, editing, and automation, making it a valuable resource for creators using AI in their projects.

  • Includes the AI Video Builder, allowing users to manage scene-by-scene production seamlessly.
  • Provides tools for face repair, video enhancement, and cinematic effects, enhancing the quality of outputs.
  • Features a variety of utilities for audio, image processing, and dataset creation, streamlining the creative process.

Context

This repository contains a set of custom nodes for ComfyUI tailored to improve video production workflows. Its primary goal is to facilitate various aspects of AI-driven video creation, from initial planning to final output, making it easier for users to generate high-quality content.

Key Features & Benefits

The AI Video Builder serves as the centerpiece of this toolset, enabling users to construct video projects based on audio cues, scripts, or manually timed scenes. Additional nodes provide functionalities such as face enhancement, video upscaling, and cinematic effects, which significantly improve the visual quality and coherence of video productions.

Advanced Functionalities

Among its advanced capabilities, the toolset includes a Face Fix node set that intelligently tracks and repairs faces in videos, ensuring high-quality results. It also features a Video Enhance node set that restores original video resolution while applying guided enhancements, and a VoxCPM2 Voice Clone/TTS tool that allows for text-to-speech generation, voice cloning, and audio editing, expanding the creative possibilities for users.

Practical Benefits

This collection enhances workflow efficiency by providing a streamlined interface for project management, allowing creators to preview, edit, and assemble their videos in one place. The integration of various tools for video and audio enhances the overall quality and reduces the time spent on post-processing tasks, making it easier to produce professional-grade content.

Credits/Acknowledgments

Created by VRGameDevGirl, this repository is licensed under the GNU Affero General Public License v3.0 (AGPL-3.0), which allows for commercial use under specific conditions. Users are encouraged to join the community for support and to explore video tutorials that demonstrate the capabilities of these workflows.

Inner Nodes

BeatImpactAnalysisNode
BeatSceneDurationNode
ColorMatchToReference
FastFilmGrain
FastLaplacianSharpen
FastSobelSharpen
FastUnsharpSharpen
IndexedImageFromFolder
IndexedImageFromFolder_ForRemakeMode
MiniMaxH3TurboLoRA
SRTLyricsMerger
VRGDGFaceFixComposite
VRGDGFaceFixCompositeLandmarkAligned
VRGDGFaceFixCompositeOpaque
VRGDGFaceFixCopyVideo
VRGDGFaceFixCreateCropVideo
VRGDGFaceFixLTXInputs
VRGDGFaceFixLoadAnchorsMetaBatch
VRGDGFaceFixPrepare
VRGDGFaceFixPrepareShotAware
VRGDGFaceFixPrepareVideoShotAware
VRGDGFaceFixSaveFramesVideo
VRGDGFaceFixStoreAnchors
VRGDGStandaloneVideoEnhancer
VRGDGVideoEnhanceCollectLTXInputs
VRGDGVideoEnhanceLoadAnchorsMetaBatch
VRGDGVideoEnhancePrepare
VRGDGVideoEnhanceRestoreOriginal
VRGDGVideoEnhanceStoreAnchors
VRGDG_ArchiveLlmBatchFolders
VRGDG_AudioCrop
VRGDG_AudioCropTime
VRGDG_AudioDelayByIndex
VRGDG_BoxIT
VRGDG_BuildVideoOutputPath_General
VRGDG_BuildVideoOutputPath_General_SRT
VRGDG_CalculateSetsFromAudio
VRGDG_CalculateSetsFromAudio_Queue
VRGDG_ChatGPTImagesBrowser
VRGDG_CleanAudio
VRGDG_ClearMemoryButtonUI
VRGDG_CombinevideosV2
VRGDG_CombinevideosV3
VRGDG_CombinevideosV5
VRGDG_ConditionalLoadVideos
VRGDG_CreateFinalVideo
VRGDG_CreateFinalVideo_SRT
VRGDG_CreateSilentAudio
VRGDG_CyclingTextPicker
VRGDG_DisplayIndex
VRGDG_DurationIndexFloat
VRGDG_EasyMultiCyclingTextPicker
VRGDG_Extract_Frame_Number
VRGDG_FlowBrowserImageEdit
VRGDG_FlowBrowserSetup
VRGDG_GeneralGGUF
VRGDG_GeneralPromptBatcher
VRGDG_GeneralVLM
VRGDG_GetAudioFilePath
VRGDG_GetFilenamePrefix
VRGDG_GetIndexNumber
VRGDG_GetRunIndexFromJson
VRGDG_GetStems
VRGDG_HumoReminderNode
VRGDG_ImageBatchMultiFromPaths
VRGDG_ImageCompare
VRGDG_ImageIndex0HUMOEDIT
VRGDG_ImageIndexMap
VRGDG_ImagePasteBack
VRGDG_ImageSwitch4
VRGDG_ImageSwitchMultiDynamic
VRGDG_ImageSwitchMultiDynamic002
VRGDG_IndexedPromptChunker
VRGDG_IndexedPromptChunkerV2
VRGDG_IntToFloat
VRGDG_IntToString
VRGDG_Json2String
VRGDG_Krea2AIToolkitInstaller
VRGDG_Krea2LoraStudio
VRGDG_Krea2LoraTrainChunk
VRGDG_Krea2MusubiInstaller
VRGDG_LLM_Multi
VRGDG_LLM_OutputSaver
VRGDG_LLM_PromptBatcher
VRGDG_LTX25MSRReferenceLoader
VRGDG_LTXAudioOnlyLoraTrainChunk
VRGDG_LTXAudioVideoLoraTrainChunk
VRGDG_LTXCFGSchedule
VRGDG_LTXFirstLastEndpointGuide
VRGDG_LTXFirstLastGuide
VRGDG_LTXICIngredientsGrid
VRGDG_LTXLoraTrainChunk
VRGDG_LTXMSRReferenceBuilder
VRGDG_LTXPreviewXYZPlot
VRGDG_LTXScheduledCFGGuider
VRGDG_LTXSigmaAdvancedGuider
VRGDG_LTXSigmaGuideRelease
VRGDG_LTXVLoopingSamplerAdvanced
VRGDG_LUTS
VRGDG_LatestSRTAutoLoader
VRGDG_LlamaCppDoctor
VRGDG_LoadAudioFilePath
VRGDG_LoadAudioSplitDynamic
VRGDG_LoadAudioSplitUpload
VRGDG_LoadAudioSplit_General
VRGDG_LoadAudioSplit_HUMO
VRGDG_LoadAudioSplit_HUMO_Transcribe
VRGDG_LoadAudioSplit_HUMO_TranscribeV2
VRGDG_LoadAudioSplit_HUMO_TranscribeV3
VRGDG_LoadAudioSplit_SRTOnly
VRGDG_LoadAudioSplit_Wan22HumoFMML
VRGDG_LoadAudioWithPath
VRGDG_LoadLatestCombinedJsonText
VRGDG_LoadText
VRGDG_LoadTextAdvanced
VRGDG_LoadVideos
VRGDG_LocalLLM
VRGDG_LoraDatasetCreatorUI
VRGDG_LoraFromPathModelOnly
VRGDG_LyricSegmentDurationMerger
VRGDG_LyricSegmentJsonFixer
VRGDG_LyricSegmentTextCleaner
VRGDG_LyricsEmotionMerger
VRGDG_MakeLUT
VRGDG_ManualLyricsExtractor
VRGDG_ManualLyricsExtractor_SRT
VRGDG_ManualLyricsExtractor_SRT_Advanced
VRGDG_ManualLyricsExtractor_SRT_Advanced_BeatV9
VRGDG_MetaAIBrowserImage
VRGDG_MiniMaxH3AudioDrive
VRGDG_MiniMaxH3LatentUpscaleModelLoader
VRGDG_MiniMaxH3LearnedLatentUpscale
VRGDG_MiniMaxH3ReferenceMediaFromPaths
VRGDG_MiniMaxH3ReplaceUpscaledVideoLatent
VRGDG_MiniMaxH3TurboLoRACompat
VRGDG_ModernFaceCrop
VRGDG_MultiCyclingTextPicker
VRGDG_MultiReferenceConditioning
VRGDG_MultiReferenceConditioningFromPaths
VRGDG_MultiStringConcat
VRGDG_MusicVideoBuilderUI
VRGDG_MusicVideoPromptCreator
VRGDG_MusicVideoPromptCreatorV2
VRGDG_MusicVideoPromptCreatorV3
VRGDG_MusubiTunerInstaller
VRGDG_MuteUnmute4PromptCreatorWF_0
VRGDG_MuteUnmute4PromptCreatorWF_1
VRGDG_MuteUnmute4PromptCreatorWF_2
VRGDG_NanoBananaPro
VRGDG_NoteBox
VRGDG_OptionalMultiLoraModelOnly
VRGDG_OptionalMultiLoraTwoPassStrengths
VRGDG_PadVideoWithLastFrame
VRGDG_Part2WorkflowUI
VRGDG_Part3WorkflowUI
VRGDG_PostRunIndexStepper
VRGDG_PromptCreatorUI
VRGDG_PromptCreatorUI_V2
VRGDG_PromptJsonSubjectPrepender
VRGDG_PromptMapJsonFixer
VRGDG_PromptSpitterWithIndex
VRGDG_PromptSplitter
VRGDG_PromptSplitter2
VRGDG_PromptSplitter4
VRGDG_PromptSplitterForFL
VRGDG_PromptSplitterForFMML
VRGDG_PromptSplitterForManual
VRGDG_PromptSplitterJson
VRGDG_PromptSplitterV2
VRGDG_PromptSplitterWithIndex
VRGDG_PromptSplitter_General
VRGDG_PromptTemplateBuilder
VRGDG_PythonCodeRunner
VRGDG_QueueTriggerFromAudio
VRGDG_Qwen2.5
VRGDG_Qwen3.5
VRGDG_RemakeClipQueue
VRGDG_RunStateLogger_SRT
VRGDG_SaveAudio
VRGDG_SaveAudioFilePath
VRGDG_SaveText
VRGDG_SaveTextAdvanced
VRGDG_SaveTextAdvancedConcat
VRGDG_SetGroupStateMulti
VRGDG_SetMuteStateMulti
VRGDG_ShowAny
VRGDG_ShowImage
VRGDG_ShowText
VRGDG_SmartSplitTextTwo
VRGDG_SpeechEmotionExtractor
VRGDG_SpeedCharacterLoraTraining
VRGDG_SplitPrompt_T2I_I2V
VRGDG_StartImageStoryboard
VRGDG_StoryBoardCreator
VRGDG_StoryGroupJsonFixer
VRGDG_StoryboardBuilderUI
VRGDG_String2Json
VRGDG_StringConcat
VRGDG_SuperGemmaGGUFChat
VRGDG_T2VPromptsFromConcepts
VRGDG_TextBox
VRGDG_ThemeSplitter
VRGDG_TimecodeFromIndex
VRGDG_TimestampedLyricsExtractor
VRGDG_TranscribeText
VRGDG_TriggerCounter
VRGDG_TrimFinalClip
VRGDG_TrimImageBatch
VRGDG_TrimImageBatch_SRTOnly
VRGDG_UnloadGemmaModels
VRGDG_UpdateLatestCombinedJsonPrompts
VRGDG_UpdateLatestCombinedJsonPrompts_zimage
VRGDG_VideoBuilderNodeCanvas
VRGDG_VideoCompareSlider
VRGDG_VideoEditorSessionLoader
VRGDG_VideoEditorUI
VRGDG_VideoFolderGridPlot
VRGDG_VideoSplitter
VRGDG_VoxCPM2Generate
VRGDG_ZImageLoraTrainChunk
VRGDG_ZImageSpeedCharacterLoraTraining
VRGDG_ZImageWorkflowRunnerUI

Run workflows with this node

Community workflows using comfyui-vrgamedevgirl.