Browse ModelsWavespeed AICinematic Video Generator

Cinematic Video Generator

Cinematic Video Generator

Playground

Try it on WavespeedAI!

WaveSpeed Cinematic Video Generator creates Hollywood-grade videos from text prompts and optional reference images with native audio, director-level camera control, and real-world physics. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.

Features

Cinematic Video Generator

Cinematic Video Generator produces film-quality video content with stunning visual fidelity and cinematic motion. Whether generating from text alone or guided by reference images, this model delivers Hollywood-grade results with dramatic lighting, professional composition, and smooth, natural movement — ideal for high-end creative productions.


Why Choose This?

  • Film-quality output Produces videos with cinematic lighting, professional color grading, and Hollywood-grade visual fidelity.

  • Dual-mode generation Text-to-Video (T2V) with prompt only, or Image-to-Video (I2V) by adding reference images — one model, two workflows.

  • Reference image support Guide generation with up to 4 reference images for consistent style, characters, or scenes.

  • Dramatic motion Natural, cinematic camera movements and subject motion that feel professionally directed.

  • Flexible aspect ratios Support for 16:9, 9:16, 4:3, and 3:4 formats for various delivery platforms.

  • Prompt Enhancer Built-in tool to automatically improve your scene descriptions.


Parameters

ParameterRequiredDescription
promptYesDetailed description of the cinematic scene
imagesNoReference images for style/character guidance (max: 4)
aspect_ratioNoOutput format: 16:9 (default), 9:16, 4:3, 3:4
durationNoVideo length: 5 (default), 10, 15 seconds

How to Use

  1. Write your prompt — describe the scene with cinematic detail (lighting, mood, camera movement, action).
  2. Add reference images (optional) — upload up to 4 images to guide style, characters, or setting.
  3. Select aspect ratio — 16:9 for widescreen, 9:16 for vertical, 4:3 or 3:4 for classic formats.
  4. Set duration — choose 5, 10, or 15 seconds.
  5. Use Prompt Enhancer (optional) — click to refine your description.
  6. Run — submit and download your cinematic video.

Pricing

DurationCost
5 s$0.80
10 s$1.60
15 s$2.40

Billing Rules

  • Rate: $0.80 per 5 seconds
  • Duration options: 5, 10, or 15 seconds

Best Use Cases

  • Film & Production — Generate cinematic footage for professional video projects.
  • Commercials & Ads — Create high-end promotional content with Hollywood aesthetics.
  • Music Videos — Produce visually stunning sequences with dramatic flair.
  • Concept Visualization — Pitch film and TV concepts with production-quality previews.
  • Social Media Premium — Stand out with film-quality short-form content.

Pro Tips

  • Write prompts like a film director — include lighting (e.g., “dramatic rim lighting”), camera angles, and mood.
  • Reference images help maintain consistency across multiple generations.
  • Use 16:9 for cinematic widescreen; 9:16 for premium vertical content.
  • Include specific visual details for best results (e.g., “orange tabby cat wearing a tiny suit and tie”).
  • Describe character expressions and actions for more engaging scenes.

Notes

  • Prompt only = Text-to-Video (T2V); Prompt + images = Image-to-Video (I2V).
  • Prompt is the only required field.
  • Maximum 4 reference images can be uploaded.
  • Duration options: 5, 10, or 15 seconds.

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/wavespeed-ai/cinematic-video-generator" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "aspect_ratio": "16:9",
    "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
promptstringYes-Describe the scene, action, camera movement, and mood for the video.
imagesarrayNo[]-Optional reference images (up to 4) to guide the visual style, characters, or scene composition.
aspect_ratiostringNo16:916:9, 9:16, 4:3, 3:4The aspect ratio of the generated video.
durationintegerNo55, 10, 15The duration of the generated video in seconds.

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.outputsobjectArray 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.