logo
RunComfy
  • ComfyUI
  • Trainer
  • Models
  • MCPNew
  • Pricing
  • Seedance 2.5Hot
  • Seedream 5.5New

Workflows by Model

HotMiniMax H3Video with audio from text, images or referencesHotQwen Image 2.1Create images and edit photos with referencesWanVideo from text or images, motion transferFLUXImage generation, editing and character variationsLTXVideo with synced audio from text or imagesQwen Image EditPhoto editing with text and image referencesKrea 2Image creation, style transfer and reference editsZ-ImageFast portraits and concepts from text

Popular & New Workflows

NewMiniMax H3 Character Swap V1.5Swap video characters, keep the original audioNewP-H3-Image Reference EditEdit a photo guided by a reference imageHotMiniMax H3 Image-to-VideoOne image to cinematic video with synced audioHotLTX 2.5 Image-to-VideoOne frame to sharp video with synced audioHotMiniMax H3 Character Swap (SAM3)Swap video characters while following the motionQwen Image 2.1 Multi-Image EditingPrecise scenes from up to 10 reference imagesFLUX Klein Face SwapNatural, lifelike face swapsSeedVR2 Video UpscalerSharp, smooth video upscaling
View More Workflows

Train a Model

NewMOSS-Image BaseImage generation, newly supportedNewFLUX.3 KleinImage generation, newly supportedHotKrea 2The most-trained image modelHotKrea 2 TurboFew-step image generationHotQwen Image 2.1Image generation and editingZ-Image TurboFast portraits and concept imagesMiniMax H3Video with synchronized audio

Train & Deploy

Getting StartedYour first training job with Ostris AI ToolkitDatasetsUpload and manage training datasetsInferenceRun your trained models in a playground or via APIDeploymentsServe your trained models as dedicated endpoints
Train More Models

Image Models

NewGPT Image 2.65% OFF · Detailed text to image, GIF and SVG, up to 4KNewSeedream 5.510% OFF · Text to image up to 2K, with transparent PNGsHotSeedream 5.0 Pro41% OFF · Reference edits with multilingual textHotSeedream 4.520% OFF · Photoreal edits with brand consistencyHotWan 2.6 ImageInstruction-based image editingFLUX.2Precise, photorealistic image editsNano Banana Pro77% OFF · Precise 2K to 4K visuals from sketchesQwen Image EditLoRA-based, structure-aware image editing

Video Models

NewSeedance 2.5 Flash34% OFF · Text, image, or reference to videoNewKling 4.010% OFF · Animate a still into a 3 to 30s clipHotWan 3.0 Prime13% OFF · Fast clips from reference videosHotSeedance 2.536% OFF · Longer, more consistent cinematic videoHotWan 3.0Clips from image, video and audio referencesHotMiniMax H3Animate a first frame into a 5 to 15s clipWan 2.510% OFF · Fluid motion with native audioFLUX 3 MaxClips from text, a still, or keyframes
View More Models

API

Serverless (ComfyUI)Deploy ComfyUI workflows as serverless endpoints.Serverless (LoRA)Deploy LoRAs as serverless endpoints.Model APIRun hosted models on-demand with no deployment.Trainer APITrain, manage, and retrieve LoRAs via API.CLIRun RunComfy models from your terminal.
MODELS
Explore
All Models
LIBRARY
Generations
MODEL APIS
API Docs
API Keys
ACCOUNT
Usage

PixVerse V6 AI Video Generator for 1080p Workflows on Models and API | RunComfy

pixverse/pixverse-v6/image-to-video

PixVerse V6 turns task-specific prompts and source media into directed video with 1-15 second timing, resolution controls, and optional native audio.

Starting image that anchors the generated shot.
Describe the subject motion, camera behavior, lighting, and scene progression.
Output quality tier shown as video resolution.
Requested output duration in seconds, from 1 through 15.
Generate an optional native audio track with the video.
Enable a multi-shot sequence within the generated video.
Seed used to reproduce or vary a generation.
Idle
Every generated second costs $0.024 at 360p, $0.034 at 540p, $0.044 at 720p, and $0.089 at 1080p without audio. With audio, the rates are $0.034, $0.044, $0.059, and $0.114 per second.

Introduction To PixVerse V6

PixVerse's PixVerse V6 coordinates text-to-video, image-to-video, transitions, reference-guided creation, and extension. Trading manual frame-by-frame iteration for guided generation, PixVerse V6 helps filmmakers, designers, and product teams build film production, campaign design, and visual development. For developers, PixVerse V6 on RunComfy can be used both in the browser and via an HTTP API, so you don't need to host or scale the model yourself.

Ideal for: Film Previsualization | Campaign Video | Product Storytelling

PixVerse / PixVerse V6#


PixVerse V6 turns text, images, paired frames, references, and source video into controlled clips. It supports clips up to 15 seconds, four resolution tiers through 1080p, and optional native audio, giving creative teams a single route from rough motion tests to polished short-form output.


The broader PixVerse V6 family covers text-to-video, image-to-video, transitions, reference-guided creation, and video extension. PixVerse V6 is designed for filmmakers, designers, agencies, and product teams that need controllable visual development without maintaining video-generation infrastructure.


Highlights#


  • Flexible starting points: Use the task-specific form to begin with text or an image while related PixVerse V6 modes handle transitions and references.

  • Production framing: Choose resolutions from 360p to 1080p and set duration from 1 to 15 seconds.

  • Audio option: Add a generated soundtrack when picture and sound should be explored together.

  • Repeatable iteration: Reuse a seed while refining prompts, framing, motion, and timing with PixVerse V6.

  • Cinematic direction: Describe lens behavior, blocking, atmosphere, pacing, and subject motion instead of relying on a generic style label.

Parameters#


ParameterRequiredTypeDefaultRange / OptionsDescription
image*Yes (*)stringhttps://playgrounds-storage-public.runcomfy.net/tools/7444/media-files/input.webpURIStarting image that anchors the generated shot.
prompt*Yes (*)stringA lone cyclist crosses a rain-swept bridge at blue hour as the camera tracks alongside, reflected city lights shimmering below, cinematic lighting, natural motion.Free inputDescribe the subject motion, camera behavior, lighting, and scene progression.
resolutionNostring720p360p, 540p, 720p, 1080pOutput quality tier shown as video resolution.
durationNointeger51-15Requested output duration in seconds, from 1 through 15.
generate_audio_switchNobooleanfalseFree inputGenerate an optional native audio track with the video.
generate_multi_clip_switchNobooleanfalseFree inputEnable a multi-shot sequence within the generated video.
seedNointeger0Free inputSeed used to reproduce or vary a generation.

Pricing#


Billing is per generated second.


ResolutionWithout audioWith audio
360p$0.024/s$0.034/s
540p$0.034/s$0.044/s
720p$0.044/s$0.059/s
1080p$0.089/s$0.114/s

How to Use#


  • Open PixVerse V6 and choose the task form that matches your source material.

  • Add the required prompt and upload the starting image when the current mode needs one.

  • Write the visible subject, action, camera path, environment, and lighting in concrete terms.

  • Select an aspect ratio when offered, then choose a resolution and duration.

  • Turn audio on only when you want sound generated with the clip.

  • Keep the default seed for exploration, or record a seed for controlled revisions.

  • Generate a draft, review motion continuity and composition, then adjust one instruction at a time.

  • Move the validated request to the HTTP API when your application needs repeatable generation.

Prompt & Reference Tips#


  • Direct the camera: Phrases such as slow dolly-in, locked tripod, overhead orbit, or handheld follow give PixVerse V6 a clearer movement target.

  • Separate motions: State what the subject does and what the camera does so the model does not merge both actions.

  • Preserve composition: For image-led work, start with clean edges, readable silhouettes, and enough space for the intended movement.

  • Plan the beat: Match the amount of action to the selected duration; one clear event often reads better than several competing events.

  • Name the atmosphere: Add time of day, key light, weather, color temperature, and material response where they matter.

  • Iterate deliberately: Hold the seed while testing a prompt change, then vary it after the direction is stable.

How PixVerse V6 compares to other models#


  • Task coverage: Based on publicly available information, PixVerse V6 combines several video workflows under one model family, while some alternatives focus on a narrower input type.

  • Duration control: The 1-15 second range makes PixVerse V6 suitable for both quick motion studies and complete short shots.

  • Resolution choices: Four output tiers let teams separate inexpensive drafting from 1080p delivery.

  • Sound workflow: Optional generated audio can reduce the gap between visual ideation and an early audiovisual cut.

More Models to Try#


  • PixVerse V6 Image To Video for animating a composed still.

  • PixVerse V6 Transition for connecting specified opening and closing frames.

  • PixVerse V6 Reference To Video for identity or appearance guidance.

  • PixVerse V6 Extend for continuing an existing clip.

Related Models

flux-3/first-last-frame-to-video/draft

FLUX 3 Draft FLF: Fast start-end frame video previews at 720p

seedance-2.5/image-to-video/4k

Seedance 2.5 4K Image to Video: animate stills into 4K motion

wan-2-2/lora/text-to-image

Generate cinematic visuals with MoE precision and creative control.

kling-video-o3/4K/reference-to-video

Cinematic 4K reference-to-video at $0.419 per second of output.

kling-3.0/standard/text-to-video

Create multi-scene films with synced dialogue and consistent characters.

wan-2-2/fun-control

First-frame restyle locks cinematic look across full AI video.

Frequently Asked Questions

What can PixVerse V6 create?

PixVerse V6 supports text-to-video, image-to-video, transitions, and reference-guided generation, plus video extension. The current form uses an image and prompt, while related modes expose the other workflows. Outputs can run from 1 to 15 seconds at 360p, 540p, 720p, or 1080p.

Who should use PixVerse V6?

PixVerse V6 fits filmmakers, technical artists, designers, agencies, and product teams creating shot concepts, campaign assets, product motion, or social video. It is especially useful when prompt-level direction and repeatable parameters matter.

How do I get better motion from PixVerse V6?

Give PixVerse V6 separate instructions for subject action and camera movement, then add framing, lighting, atmosphere, and pacing. Keep the requested action realistic for the selected 1-15 second duration.

Does PixVerse V6 generate audio?

PixVerse V6 includes a generate_audio_switch option that is off by default. Turning it on requests native audio and changes the per-second rate.

What resolution and duration limits apply to PixVerse V6?

PixVerse V6 exposes 360p, 540p, 720p, and 1080p, with an integer duration from 1 through 15 seconds. Available aspect-ratio control depends on the task form.

Can I reproduce results from PixVerse V6?

PixVerse V6 includes a seed parameter for controlled iteration. The same seed and inputs can improve repeatability, although generated-video systems may still show some variation.

Can developers call PixVerse V6 through the RunComfy API?

Yes. Teams can test PixVerse V6 in the RunComfy model UI and then send the same exposed parameters through the HTTP API. This supports moving a validated request into an application or automation workflow.

How much does PixVerse V6 cost on RunComfy?

PixVerse V6 is billed per generated second. Without audio: 360p $0.024/s, 540p $0.034/s, 720p $0.044/s, and 1080p $0.089/s. With audio: 360p $0.034/s, 540p $0.044/s, 720p $0.059/s, and 1080p $0.114/s. Your total depends on duration.

Follow us
  • LinkedIn
  • Facebook
  • Instagram
  • Twitter
Support
  • Discord
  • Email
  • System Status
  • Affiliate
Video Models
  • Seedance 2.5 Flash Text To Video
  • Seedance 2.5 Flash
  • Seedance 2.5 Flash Reference to Video
  • Wan 3.0
  • MiniMax H3 Fast
  • Wan 2.5
  • View All Models →
Image Models
  • Seedream 5.5
  • Seedream 5.5 Edit
  • Seedream 5.5 Layer Decomposition
  • Wan 2.6 Image to Image
  • Nano Banana Pro
  • Seedream 5.0 Pro
  • View All Models →
Legal
  • Terms of Service
  • Privacy Policy
  • Cookie Policy
RunComfy
Copyright 2026 RunComfy. All Rights Reserved.

RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals. RunComfy also provides AI Models, enabling artists to harness the latest AI tools to create incredible art.

Examples Of PixVerse V6

Video thumbnail
Loading...
Video thumbnail
Loading...
Video thumbnail
Loading...
Video thumbnail
Loading...
Video thumbnail
Loading...
Video thumbnail
Loading...