SandBase is live — $1 in free credits on signupStart free ›

PixVerse modelsvideo generation api

pixverse/swap

Swap by PixVerse - animate still images into dynamic videos with AI. Transform photos into cinematic clips with natural motion, camera movement, and optional audio generation.

Input

PNG, JPEG, WebP, or GIF · 20 MiB maximum

URL of the target image for swapping
URL of the external video to swap
The output resolution (1080p not supported) Allowed values: 360p, 540p, 720p.
Whether to keep the original audio
The keyframe ID to use for face/object mapping. The input video is normalized to 24 FPS before processing, so keyframe 1 = first frame, keyframe 24 = 1 second in, etc. Valid range: 1 to (duration_seconds * 24). Minimum: 1.
The swap mode to use Allowed values: person, object, background.
Random seed for generation
Idle

Example output — click Run to generate your own

API README

PixVerse

PixVerse is the PixVerse route for video subject replacement, turning an existing shot and replacement subject into a production-ready result while keeping the operation distinct from neighboring endpoints. Swap by PixVerse - animate still images into dynamic videos with AI. Transform photos into cinematic clips with natural motion, camera movement, and optional audio generation. The workflow is designed for creators who need the model’s specific transformation to remain visible in the request, so the source, intended change, and finished artifact can be reviewed as one coherent creative decision.

In practical use, this route exposes seed, image, video, swap_mode, resolution, keyframe_id, original_sound_switch to shape the exact deliverable. Those controls let a team preserve the important source constraints, state subject behavior or material treatment precisely, choose supported timing or output characteristics, and reproduce successful settings across alternate takes. The result fits an iterative pipeline: establish the core brief, compare controlled variations, then pass the selected asset into editorial, design, localization, visualization, or publishing work.

Highlights

  • Targeted subject swap. Replace the selected person or object while retaining the surrounding shot.
  • Motion-aware integration. Carry the replacement through the clip so position and movement remain coherent over time.
  • Resolution-aware rendering. Select the documented output tier and duration bracket for the intended delivery.
  • Existing-shot revision. Revise cast or product presence without regenerating the entire scene from text.

Pricing

ConfigurationPrice
Up to 5 seconds · 360p/540p$0.15
Up to 5 seconds · 720p$0.20
Up to 5 seconds · 1080p$0.40
More than 5 seconds · 360p/540p$0.30
More than 5 seconds · 720p$0.40
More than 5 seconds · 1080p$0.80

When to Use

ScenarioWhy it fits
Exact workflow fitChoose this route when the required deliverable is video subject replacement, rather than a related route with different source media.
Directed creative iterationUse it when subject, motion, material, speech, framing, or finish should be expressed explicitly and compared across controlled variants.
Existing-asset continuityUse it when supplied images, video, audio, references, or styles must remain the anchor for the generated result.
Repeatable productionUse it when successful inputs need to be saved and rerun across a campaign, asset set, localization pass, or batch.
Pipeline handoffUse it when the returned artifact will move into editorial, compositing, visualization, review, storage, or publishing.

Prompt Guide

Start with the source or subject, then describe the intended transformation, movement or behavior, camera and composition, and the desired finish. Keep media URLs reachable, use only fields documented for this exact route, and change one major control at a time when comparing results. For source-led tasks, describe what should change as well as what must remain recognizable.

{
  "image": "https://static.sandbase.ai/examples/pixverse/swap/input_image_0.jpg",
  "resolution": "720p"
}

Technical Specs

PropertyValue
Model IDpixverse/swap
Execution modeasync
Required inputsimage
seedinteger
imagestring
videostring
swap_modestring; options: person, object, background; default: person
resolutionstring; options: 360p, 540p, 720p; default: 720p
keyframe_idinteger; minimum: 1; default: 1
original_sound_switchboolean; default: true

Related Models

  • pixverse/extend
  • pixverse/lipsync
  • pixverse/sound-effects
  • pixverse/c1/image-to-video

Related Models

pixverse/c1/image-to-videoC1 is PixVerse's image-to-video AI model. Bring static images to life with fluid animation, consistent character motion, and professional-grade video output.pixverse/c1/reference-to-videoC1 is PixVerse's image-to-video AI model. Bring static images to life with fluid animation, consistent character motion, and professional-grade video output.pixverse/c1/text-to-videoC1 by PixVerse - generate cinematic videos from text descriptions with AI. Create high-quality video content with natural motion, camera control, and optional audio generation.pixverse/c1/transitionC1 Transition is PixVerse's image-to-video AI model. Bring static images to life with fluid animation, consistent character motion, and professional-grade video output.pixverse/extendExtend by PixVerse - AI-powered video editing and transformation. Apply style transfer, motion control, lip-sync, and visual effects to existing videos with natural language instructions.pixverse/extend/fastExtend Fast is PixVerse's video-to-video AI model. Transform, enhance, and edit video content using text prompts - from style changes to object manipulation and scene modification.pixverse/lipsyncLipsync is PixVerse's video-to-video AI model. Transform, enhance, and edit video content using text prompts - from style changes to object manipulation and scene modification.pixverse/sound-effectsSound Effects is PixVerse's video-to-video AI model. Transform, enhance, and edit video content using text prompts - from style changes to object manipulation and scene modification.