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.
ว่าง
$0.1ต่อครั้ง·~10 / $1
A slow push-in shot toward the entrance of an ancient stone temple at dawn. Thick morning fog clings to the carved columns and stone steps. Moss covers the lower walls. A single monk in orange robes walks up the steps from the left and disappears through the doorway. The camera continues its slow forward movement as birds begin to call in the distance and soft light warms the stone facade.
A low-angle ground shot of a lone wolf walking through a snow-covered pine forest at dusk. Its breath forms small clouds in the freezing air. Snow falls steadily, settling on its dark fur. The camera tracks slowly alongside at ground level as the wolf pauses, turns its head toward the camera, then continues forward. The forest is silent except for the crunch of snow underfoot.
A top-down overhead shot of a chef's hands carefully plating a dish on a dark ceramic plate. Tweezers place a single herb leaf onto a sauce swirl. Steam rises gently from the main component. The camera slowly zooms in as a final drizzle of golden oil catches the light. The kitchen background is softly blurred, warm ambient light from above.
A wide static shot of a remote cabin in the mountains at night. Warm amber light glows from two small windows. Snow falls heavily around the structure. A thick pine forest surrounds the cabin on three sides. Smoke rises slowly from the chimney and dissolves into the dark sky above. The scene is completely still except for the falling snow and the faint flicker of light inside.
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 generates synchronized video and audio from text prompts in a single pass, bringing together the core building blocks of modern video generation with open weights and practical execution.
Improved quality Enhanced audio and visual quality compared to LTX-2, with better prompt adherence and more coherent outputs.
Synchronized audio-video Generates video with matching audio in a single model pass, no separate audio production needed.
DiT-based architecture Built on Diffusion Transformer technology for high-fidelity, 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 |
|---|---|---|
| loras | No | List of LoRA models to apply (max 3, each with path and scale) |
| prompt | Yes | Text description of the video scene, motion, and audio |
| 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 | $1.00 |
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/wavespeed-ai/ltx-2.3/text-to-video-lora with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Ltx 2.3 Text To Video Lora below.
set -euo pipefail
: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"
REQUEST_BODY=$(cat <<'JSON'
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"resolution": "720p",
"aspect_ratio": "16:9",
"duration": 5,
"seed": -1
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/ltx-2.3/text-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/text-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 ${apiKey}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"resolution": "720p",
"aspect_ratio": "16:9",
"duration": 5,
"seed": -1
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
`https://api.wavespeed.ai/api/v3/predictions/${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",
"resolution": "720p",
"aspect_ratio": "16:9",
"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/text-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 Text 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-text-to-video-lora.
Ltx 2.3 Text 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`, `aspect_ratio`, `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-text-to-video-lora.
Median end-to-end generation time on WaveSpeedAI is around 40 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.