LTX-2.3 with LoRA support is a DiT-based audio-video foundation model designed to generate synchronized video and audio with custom styles, motion, or likeness training. Improved audio and visual quality with enhanced prompt adherence. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Ожидание
$0.1за запуск·~10 / $1
A medium close-up shot of a male engineer in a white lab coat and safety glasses seated at a workbench in a clean laboratory. He holds a soldering iron in his right hand and carefully applies it to a small electronic component with precise, steady movements. Thin wisps of solder smoke rise from the contact point. Simultaneously, the robotic arm to his left begins to move, its joints rotating smoothly one by one as it repositions toward a new target on the bench. The arm pauses, adjusts its angle with a slight mechanical whir, then holds still. The engineer glances briefly at the arm, then returns his focus to the soldering point. The camera slowly pushes in toward the workbench, framing both the man's hands and the robotic arm in the same shot. Lab ambient hum, faint mechanical servo sounds, and soft solder sizzle fill the audio.
A sleek, modern drone glides smoothly through the dense urban skyline, its camera capturing sweeping aerial views of towering skyscrapers, winding streets, and bustling sidewalks below. The drone moves at a slow, steady pace, as if surveying the city with quiet precision. Its shadow flickers across the pavement, while the sun casts long, dramatic shadows from the buildings. The sky is clear and blue, with occasional wisps of clouds. The scene is cinematic, with a realistic, high-definition visual style, emphasizing motion and scale. Shot from a high-angle perspective, capturing the drone’s trajectory as it weaves between structures.
A cinematic wide shot of a weathered white spacecraft drifting through deep space. Its thrusters fire with a steady blue-white exhaust trail streaming behind the rear engine. The ship slowly rolls into a banking turn, its cross-shaped hull catching the light of a distant star on the left side. Hull panels and surface details catch the light as it rotates. The camera orbits slowly around the vessel from a high angle, revealing the cockpit viewport and the pilot silhouette inside. Stars drift past in the background. The ship accelerates forward, exhaust trail brightening and lengthening as it pulls away. Deep low engine rumble and the hiss of thrusters fill the audio against a silent black void.
LTX-2.3 is a significant update to the LTX-2 model, featuring improved audio and visual quality with enhanced prompt adherence. As a DiT-based (Diffusion Transformer) audio-video foundation model, it animates your input image into a high-fidelity video with synchronized audio generated in a single pass.
Improved quality Enhanced audio and visual quality compared to LTX-2, with better prompt adherence and more coherent outputs.
Image-conditioned video with audio Transforms a static image into a moving video with synchronized audio in a single model pass.
Preserves input composition Maintains the subject, framing, and lighting of your reference image while adding natural motion.
DiT-based architecture Built on Diffusion Transformer technology for detailed, temporally consistent video generation.
Flexible resolution Supports 480p, 720p, and 1080p outputs to balance quality and cost.
Variable duration Generate clips from 5 to 20 seconds.
| Parameter | Required | Description |
|---|---|---|
| image | Yes | Reference image to animate (JPG or PNG) |
| loras | No | List of LoRA models to apply (max 3, each with path and scale) |
| prompt | Yes | Text description of motion, action, and audio cues |
| resolution | No | Output resolution: 480p, 720p (default), or 1080p |
| duration | No | Video length in seconds (5-20) |
| seed | No | Random seed for reproducibility (-1 for random) |
| Resolution | Best For |
|---|---|
| 480p | Fast previews, iteration, lowest cost |
| 720p | Balanced quality and cost (default) |
| 1080p | Final delivery, maximum detail |
| Resolution | 5s | 10s | 15s | 20s |
|---|---|---|---|---|
| 480p | $0.15 | $0.30 | $0.45 | $0.60 |
| 720p | $0.20 | $0.40 | $0.60 | $0.80 |
| 1080p | $0.25 | $0.50 | $0.75 | $1.00 |
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/wavespeed-ai/ltx-2.3/image-to-video-lora with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Ltx 2.3 Image To Video Lora below.
set -euo pipefail
: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"
REQUEST_BODY=$(cat <<'JSON'
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
"resolution": "720p",
"duration": 5,
"seed": -1
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/ltx-2.3/image-to-video-lora" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d "$REQUEST_BODY")
TASK=$(printf '%s' "$SUBMIT_RESPONSE" | jq 'if has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "$TASK" | jq -r '.id')
if [ -z "$PREDICTION_ID" ] || [ "$PREDICTION_ID" = "null" ]; 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' "$RESPONSE" | jq 'if has("data") then .data else . end')
STATUS=$(printf '%s' "$RESULT" | jq -r '.status')
case "$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
doneconst submitUrl = "https://api.wavespeed.ai/api/v3/wavespeed-ai/ltx-2.3/image-to-video-lora";
const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');
async function requestJson(url, options = {}) {
const response = await fetch(url, options);
if (!response.ok) throw new Error(await response.text());
return response.json();
}
// 1. Submit the prediction.
const body = await requestJson(submitUrl, {
method: "POST",
headers: {
"Authorization": `Bearer ${apiKey}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
"resolution": "720p",
"duration": 5,
"seed": -1
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
`https://api.wavespeed.ai/api/v3/predictions/${task.id}/result`;
// 2. Poll until the prediction finishes.
while (true) {
const resultBody = await requestJson(resultUrl, {
headers: { "Authorization": `Bearer ${apiKey}` },
});
const result = resultBody.data ?? resultBody;
if (result.status === "completed") {
console.log(result.outputs);
break;
}
if (["failed", "cancelled", "timeout"].includes(result.status)) throw new Error(JSON.stringify(result));
if (!["created", "processing"].includes(result.status)) throw new Error("Unexpected status: " + result.status);
await new Promise(resolve => setTimeout(resolve, 2000));
}import json
import os
import time
from urllib.request import Request, urlopen
api_key = os.environ["WAVESPEED_API_KEY"]
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
payload = {
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
"resolution": "720p",
"duration": 5,
"seed": -1
}
def request_json(url, data=None):
request = Request(url, data=data, headers=headers, method="POST" if data else "GET")
with urlopen(request) as response:
return json.load(response)
# 1. Submit the prediction.
body = request_json("https://api.wavespeed.ai/api/v3/wavespeed-ai/ltx-2.3/image-to-video-lora", json.dumps(payload).encode())
task = body.get("data", body)
if not task.get("id"):
raise RuntimeError("Submission response did not contain a prediction id")
result_url = task.get("urls", {}).get("get") or f"https://api.wavespeed.ai/api/v3/predictions/{task['id']}/result"
# 2. Poll until the prediction finishes.
while True:
result_body = request_json(result_url)
result = result_body.get("data", result_body)
status = result.get("status")
if status == "completed":
print(result.get("outputs", []))
break
if status in {"failed", "cancelled", "timeout"}:
raise RuntimeError(result)
if status not in {"created", "processing"}:
raise RuntimeError(f"Unexpected status: {status}")
time.sleep(2)Ltx 2.3 Image To Video Lora is a WaveSpeedAI model for AI inference, exposed as a REST API on WaveSpeedAI. LTX-2.3 with LoRA support is a DiT-based audio-video foundation model designed to generate synchronized video and audio with custom styles, motion, or likeness training. Improved audio and visual quality with enhanced prompt adherence. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.
POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID. Poll the result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. The playground generates production-oriented Python, JavaScript, and cURL examples with timeouts, transient-error handling, and safe GET retries. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/wavespeed-ai/ltx-2.3-image-to-video-lora.
Ltx 2.3 Image To Video Lora starts at $0.10 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.
Key inputs: `prompt`, `image`, `resolution`, `duration`, `seed`, `loras`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/wavespeed-ai/ltx-2.3-image-to-video-lora.
Median end-to-end generation time on WaveSpeedAI is around 63 seconds per request, based on recent successful runs. Queue time varies with global demand; live status is visible in the prediction record.
Commercial usage rights depend on the model's license, set by its provider (WaveSpeedAI). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.