Browse ModelsWavespeed AIOpen Video Image To Video LoRA

Open Video Image To Video LoRA

Open Video Image To Video LoRA

Playground

Try it on WavespeedAI!

OpenVideo Image to Video LoRA is a fast AI image-to-video generation model that creates short cinematic clips with native audio from a single reference image, with optional preset control and per-LoRA strength settings for style, motion, and look-and-feel. Supports 480p, 720p, and 1080p output and 3–20 second duration tiers. Ready-to-use REST inference API for cinematic clips, character-consistent videos, stylized motion, product videos, social media content, advertising creatives, and professional LoRA-based image-to-video workflows with simple integration, no coldstarts, and affordable pricing.

Features

OpenVideo — Unlimited Image-to-Video (LoRA tier)

Full creative control — same audio-video pipeline as the base image-to-video endpoint, plus a curated LoRA stack you can preset or override per request. Unlimited generation freedom for style, motion and look-and-feel.


Extra Inputs (on top of the base endpoint)

FieldRequiredDefaultNotes
presetnotunedoriginal (light styling) or tuned (recommended stack).
lorasno{}Per-LoRA strength overrides merged on top of the preset (e.g. {"omninft": 0.5, "better_motion": 0.3}). Unknown keys dropped.

Available LoRA keys

sulphur, sulphur_v1, vbvr, dreamly, synth, plora, singularity, omninft, omninft_bf16, better_motion, physics_v2, hardcut, transition.

Pricing

ResolutionPer 5sPer secondMax length
480p$0.15$0.03 / s20 s
720p$0.25$0.05 / s20 s
1080p$0.35$0.07 / s20 s
  • Minimum charge: 5 seconds.
  • Maximum billed duration: 20 seconds.

Notes

  • preset = tuned is the default and works well for most prompts. Use original for closer-to-input outputs.
  • Each active LoRA adds ~0.5-0.8 s at 480p / 5s. 13-LoRA worst case ≈ +30% vs no-LoRAs.
  • Pass loras: {"omninft": 0} to fully turn off a preset’s LoRA without changing the rest.
  • You retain full control over output content — by using this endpoint you confirm you have the right to generate the requested content under your jurisdiction.

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/open-video/image-to-video-lora" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "preset": "tuned",
    "loras": [],
    "resolution": "480p",
    "duration": 5,
    "seed": -1
}'

# 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-Reference image for the first frame (JPG/PNG recommended).
promptstringYes-Positive prompt describing the desired motion / scene.
presetstringNotunedtuned, originalLoRA preset bundle. `original` = light styling. `tuned` = the recommended general-purpose stack. Overridden per-LoRA via `loras`.
lorasarrayNomax undefined itemsOptional list of LoRA strength overrides merged on top of the preset, e.g. `[{"path": "sulphur", "scale": 0.3}, {"path": "omninft", "scale": 0.5}]`.
loras[].pathstringYes-Path to the LoRA model
loras[].scalefloatYes-0.0 ~ 4.0Scale of the LoRA model
resolutionstringNo480p480p, 720p, 1080pOutput resolution tier.
durationintegerNo53 ~ 20Output duration in seconds (3-20).
seedintegerNo-1-1 ~ 2147483647Random seed. -1 for a random seed.

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.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.