Browse ModelsPixversePixverse Pixverse V4.5 I2V

Pixverse Pixverse V4.5 I2V

Pixverse Pixverse V4.5 I2V

Playground

Try it on WavespeedAI!

PixVerse V4.5 I2V creates high-quality videos from text or image prompts, offering multiple resolutions, aspect ratios, and motion modes for versatile cinematic output. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

PixVerse V4.5 Image-to-Video

Bring your images to life with PixVerse V4.5 — a versatile image-to-video model that excels at natural human motion, fashion content, and dynamic scenes. Create professional-quality videos with realistic movement and cinematic flair at an accessible price point.

Looking for faster processing? Try PixVerse V4.5 Fast for optimized generation speed.

Why It Looks Great

  • Natural human motion: Excels at realistic walking, posing, and body movement.
  • Multiple resolutions: Choose from 360p, 540p, 720p, or 1080p based on your needs.
  • Flexible duration: Generate 5-second or 8-second videos.
  • Negative prompt support: Exclude unwanted elements for precise control.
  • Competitive pricing: High-quality generation at budget-friendly rates.
  • Reproducible results: Use the seed parameter to recreate exact outputs.

Parameters

ParameterRequiredDescription
promptYesText description of the motion, action, and scene you want.
imageYesSource image to animate (upload or public URL).
resolutionNoOutput quality: 360p, 540p, 720p, or 1080p. Default: 540p.
durationNoVideo length: 5 or 8 seconds. Default: 5.
negative_promptNoElements to avoid in the generated video.
seedNoRandom seed for reproducibility. Leave empty for random.

How to Use

  1. Write your prompt — describe the motion, actions, and atmosphere you want.
  2. Upload your image — drag and drop or paste a public URL.
  3. Choose resolution — select quality level based on your use case and budget.
  4. Set duration — choose 5 or 8 seconds.
  5. Add negative prompt (optional) — specify elements to exclude.
  6. Set seed (optional) — for reproducible results.
  7. Run — click the button to generate.
  8. Download — preview and save your video.

Pricing

Pricing varies by resolution and duration.

5-Second Videos

ResolutionCost
360p$0.25
540p$0.25
720p$0.35
1080p$0.70

8-Second Videos

ResolutionCost
360p$0.50
540p$0.50
720p$0.70
1080p$1.40

Quick Reference

Duration360p540p720p1080p
5s$0.25$0.25$0.35$0.70
8s$0.50$0.50$0.70$1.40

Best Use Cases

  • Fashion & Runway — Animate models walking, posing, and showcasing clothing.
  • Social Media Content — Create dynamic video content from portrait and lifestyle photos.
  • Marketing & Advertising — Bring product and campaign images to life with motion.
  • Portrait Animation — Add natural movement to headshots and character images.
  • Event & Performance — Animate photos with crowd reactions, stage lighting, and atmosphere.

Example Prompts

  • “The woman in the image strikes a pose, then starts walking confidently on a fashion runway, flashbulbs going off”
  • “Subject turns toward camera with a warm smile, hair gently moving in the breeze”
  • “Model showcases the outfit with a slow spin, studio lighting creating dynamic shadows”
  • “The person laughs naturally, subtle head movement, candid authentic moment”
  • “Confident walk toward camera, urban street background with bokeh lights”

Resolution Guide

ResolutionBest For
360pQuick previews, testing concepts, maximum budget efficiency
540pSocial media, general use, balanced quality and cost
720pHigher quality content, presentations, detailed motion
1080pProfessional deliverables, large displays, premium content

Pro Tips for Best Results

  • For fashion content, describe the walk style: “confident”, “graceful”, “powerful strut”.
  • Include environmental details: “flashbulbs”, “studio lighting”, “crowd reactions”.
  • Use negative prompts to avoid “blur”, “distortion”, “unnatural movement”.
  • Start with 540p to test concepts — it offers great quality at the base price.
  • Describe the emotional tone: “confident”, “playful”, “elegant”, “dramatic”.
  • Keep the same seed when upgrading resolution to maintain consistency.

Notes

  • If using a URL for the image, ensure it is publicly accessible. A preview thumbnail confirms successful loading.
  • Processing time varies based on resolution and duration.
  • Best results come from images with clear subjects and appropriate poses for the intended motion.
  • For complex artistic transformations, consider PixVerse V4.5 Fast which is optimized for dramatic effects.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result


# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/pixverse/pixverse-v4.5-i2v" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "resolution": "540p",
    "duration": 5
}'

# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"

Parameters

Task Submission Parameters

Request Parameters

ParameterTypeRequiredDefaultRangeDescription
imagestringYes-First frame of the video; Supported image formats include.jpg/.jpeg/.png; The image file size cannot exceed 10MB, and the image resolution should not be less than 300*300px, and the aspect ratio of the image should be between 1:2.5 ~ 2.5:1.
promptstringYes-The positive prompt for the generation.
resolutionstringNo540p360p, 540p, 720p, 1080pVideo quality (360p/540p/720p/1080p).
durationintegerNo55, 8Video duration in seconds. 1080p only supports 5 seconds.
negative_promptstringNo-The negative prompt for the generation.
seedintegerNo--1 ~ 2147483647The random seed to use for the generation.

Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
data.idstringUnique identifier for the prediction, Task Id
data.modelstringModel ID used for the prediction
data.outputsarrayArray of URLs to the generated content (empty when status is not completed)
data.urlsobjectObject containing related API endpoints
data.urls.getstringURL to retrieve the prediction result
data.has_nsfw_contentsarrayArray of boolean values indicating NSFW detection for each output
data.statusstringStatus of the task: created, processing, completed, or failed
data.created_atstringISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds

Result Request Parameters

ParameterTypeRequiredDefaultDescription
idstringYes-Task ID

Result Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
dataobjectThe prediction data object containing all details
data.idstringUnique identifier for the prediction, the ID of the prediction to get
data.modelstringModel ID used for the prediction
data.outputsstringArray of URLs to the generated content (empty when status is not completed).
data.urlsobjectObject containing related API endpoints
data.urls.getstringURL to retrieve the prediction result
data.statusstringStatus of the task: created, processing, completed, or failed
data.created_atstringISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds
© 2025 WaveSpeedAI. All rights reserved.