Ltx Video V097 I2V 720p

Ltx Video V097 I2V 720p

Playground

Try it on WaveSpeedAI!

Generate 720p videos from text prompts and images with LTX Video-0.9.7 for consistent, high-quality image-to-video results. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

LTX-Video v0.97 I2V 720p generates short videos from a single reference image plus a text prompt. Upload an image to anchor the subject and composition, then describe motion, camera movement, lighting, and style to animate the scene. This model is well-suited for cinematic image animation, stylized shots (e.g., oil painting, illustration), and smooth camera moves at 720p.

Key capabilities

  • Image-to-video generation anchored to a reference image (720p output)
  • Prompt-driven motion and camera direction (push-in, pan, orbit, tilt)
  • Supports negative_prompt to reduce artifacts (blur, jitter, distortion)
  • Strong for stylized animation (painting/illustration looks) and cinematic lighting beats

Use cases

  • Animate portraits and artworks with subtle motion and cinematic camera moves
  • Turn a single keyframe into a short story beat for trailers and storyboards
  • Create stylized clips (oil painting, anime, illustration) while preserving composition
  • Generate multiple variations by changing seed and prompt details
  • Rapid prototyping of mood, lighting, and camera language before higher-cost runs

Pricing

OutputPrice per run
720p I2V video$0.30

Inputs

  • image (required): reference image (subject/composition anchor)
  • prompt (required): motion + scene direction
  • negative_prompt (optional): what to avoid (blurry, jittery, distorted, etc.)

Parameters

  • prompt: describe subject, action, scene, camera, style
  • negative_prompt: optional “avoid list”
  • image: input image (upload or URL)
  • size: output resolution (1280×720)
  • seed: random seed (set for reproducible results)

Prompting guide (I2V)

Write prompts like a director’s brief:

  • Subject: who/what is on screen
  • Motion: subtle expression changes, breathing, cloth movement, particles
  • Camera: slow push-in, gentle orbit, rack focus, steady pan
  • Lighting/style: chiaroscuro, golden hour, neon, painterly brushwork
  • Constraints: keep identity/composition consistent with the reference

Example prompts

  • A classical oil painting portrait. Slow camera push-in toward the subject’s face, subtle breathing motion, gentle flicker in candlelight, soft volumetric haze, cinematic chiaroscuro lighting.
  • A serene landscape painting. Wind moves the trees slightly, clouds drift slowly, camera pans across the scene, painterly style preserved, smooth motion.
  • A fashion portrait. Hair sways lightly, subject turns their head slightly, camera slow orbit, soft studio lighting, realistic texture.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result

set -euo pipefail

export WAVESPEED_API_KEY="your-api-key"

REQUEST_BODY=$(cat <<'JSON'
{
  "prompt": "A cinematic ocean wave at sunrise, highly detailed",
  "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
  "size": "1280*720"
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/ltx-video-v097/i2v-720p" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}")

TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL=$(printf '%s' "${TASK}" | jq -r '.urls.get // empty')
if [ -z "${RESULT_URL}" ]; then RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"; fi

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}")
  RESULT=$(printf '%s' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    created|processing) sleep 2 ;;
    *) printf 'Unexpected status: %s
' "${STATUS}" >&2; exit 1 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

ParameterTypeRequiredDefaultRangeDescription
promptstringYes-The positive prompt for the generation.
imagestringYes-Image URL for Image-to-Video task.
negative_promptstringNo-The negative prompt for the generation.
sizestringNo1280*720720*1280, 1280*720The size of the generated media in pixels (width*height).
seedintegerNo--The 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.outputsarrayOutput values, usually URL strings; some models return text strings or structured result objects (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
data.modelstringModel ID used for the prediction
data.outputsarray<string | object>Array of generated outputs (empty when status is not completed). Items are usually URL strings, but may be text strings or structured result objects, depending on the model.
data.urlsobjectObject containing related API endpoints
data.urls.getstringURL to poll for the prediction result
data.statusstringStatus: created, processing, completed, or failed
data.created_atstringISO timestamp of when the request was created
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds
© 2026 WaveSpeedAI. All rights reserved.