SkyReels V1

SkyReels V1

Playground

Try it on WavespeedAI!

SkyReels V1 is an open-source, human-centric video foundation model fine-tuned from HunyuanVideo on ~10M high-quality film and TV clips to deliver realistic human motion and scene synthesis. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

SkyReels V1 — wavespeed-ai/SkyReels-V1

SkyReels V1 is an image-to-video model that animates a single reference image into a short, cinematic clip guided by a text prompt. Upload an image to anchor the subject and composition, then describe the motion, camera language, atmosphere, and visual style you want. The model is well-suited for nature shots, cinematic macro moments, and smooth “living photo” style animations, with seed control for reproducible variations.

Key capabilities

  • Image-to-video generation anchored to a reference image
  • Prompt-driven motion, atmosphere, and camera intent
  • Works well for cinematic “living photo” animation and natural motion
  • Seed control for reproducible outputs

Use cases

  • Animate nature photography (birds, insects, plants, weather, light rays)
  • Cinematic macro shots (wings fluttering, pollen drifting, dew shimmering)
  • Turning a still image into a short b-roll clip for edits and trailers
  • Rapid iteration: generate multiple takes by changing prompt or seed
  • Stylized scene animation with consistent composition

Pricing

OutputPrice per run
Image-to-Video (per generation)$0.20

Inputs

  • prompt (required): what happens in the video (action + scene + camera)
  • image (required): reference image (subject/composition anchor)

Parameters

  • prompt: describe subject, motion, environment, camera, and style
  • image: input image (upload or URL)
  • seed: random seed (-1 for random; fixed value for reproducible results)

Prompting guide (I2V)

For stronger results, write prompts like a director’s brief:

  • Subject: who/what is on screen
  • Action: what moves over time (flutter, drift, sway, shimmer)
  • Scene: where it happens + time/lighting
  • Camera: macro close-up, slow push-in, gentle pan (optional)
  • Constraints: keep composition consistent with the reference image

Example prompts

  • Amazon rainforest at dawn, sun rays piercing the canopy, a hummingbird hovering by an orchid, wings vibrating rapidly, macro lens, shallow depth of field, drifting pollen and dust motes, slow cinematic push-in, natural motion.
  • A close-up of a flower with dew drops sparkling, gentle breeze moving petals, soft morning light, subtle camera pan, realistic motion, cinematic b-roll.

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/SkyReels-V1" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{}'

# 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-The positive prompt for the generation.
imagestringYes-URL of the image input.
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.