Seedream 5.0 Pro đã ra mắt | Thử trong Trình tạo ảnh →

LTX 2.3 Spicy LORA Image to Video API

wavespeed-ai /

LTX 2.3 Spicy LoRA Image to Video API turns a reference image and prompt into expressive AI videos using selectable LoRA presets, optional LoRA strength overrides, duration, and resolution controls. Run fast REST inference on WaveSpeedAI with no cold starts and affordable pricing.

lora-support
Đầu vào

Chờ

$0.15cho mỗi lần chạy·~66 / $10

Ví dụXem tất cả

The woman slowly walks through the neon alley while holographic signs flicker around her. She glances sideways, her coat moves naturally, and reflections shimmer on the wet ground. Smooth cinematic tracking shot, realistic motion.

Mô hình liên quan

README

Ltx-2.3-spicy/image-to-video-lora

wavespeed-ai/ltx-2.3-spicy/image-to-video-lora uses the same audio-video generation pipeline as the base image-to-video endpoint, while adding a curated LoRA stack for stronger style, motion, and visual control. You can use the recommended preset or override individual LoRA strengths per request.

Why Choose This?

  • Same base image-to-video workflow Uses the same core audio-video pipeline as the base image-to-video endpoint.

  • Preset-based LoRA control Choose between original for lighter styling or tuned for the recommended LoRA stack.

  • Per-LoRA override support Override individual LoRA strengths on top of the selected preset for more flexible control.

  • Style, motion, and look control Fine-tune visual style, motion behavior, and overall output feel with a curated LoRA set.

  • Unlimited creative flexibility Designed for users who want more direct control over the generation result.

Parameters

This endpoint supports all inputs from the base image-to-video endpoint, plus the following extra fields:

ParameterRequiredDescription
presetNoLoRA preset. original applies lighter styling. tuned applies the recommended LoRA stack. Default: tuned.
lorasNoPer-LoRA strength overrides merged on top of the selected preset. Example: {"omninft": 0.5, "better_motion": 0.3}. Unknown keys are ignored. Default: {}.

Available LoRA Keys

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

How to Use

  1. Prepare your base image-to-video inputs — Use the same required inputs as the base image-to-video endpoint.
  2. Choose a preset (optional) — Use tuned for the recommended LoRA stack or original for a lighter effect.
  3. Set LoRA overrides (optional) — Pass a loras object to adjust individual LoRA strengths.
  4. Submit — Generate the final video result with LoRA-enhanced control.

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

Billing Rules

  • Minimum charge: 5 seconds.
  • Maximum billed duration: 20 seconds.
  • 720p costs 5/3× the 480p price.
  • 1080p costs 7/3× the 480p price.
  • Billing is based on max(5, min(duration, 20)).

Best Use Cases

  • Style-controlled image-to-video generation — Apply stronger visual styling on top of the base image-to-video workflow.
  • Motion tuning — Use motion-focused LoRAs such as better_motion or physics_v2 to guide output behavior.
  • Look-and-feel customization — Combine preset stacks and LoRA overrides to shape the final visual result.
  • Creative experimentation — Try different LoRA combinations for varied output styles and motion characteristics.

Pro Tips

  • Use preset = tuned for the recommended default behavior.
  • Use preset = original when you want results closer to the base input style.
  • Use the loras object to override only the LoRAs you want to adjust.
  • Set a LoRA value to 0 if you want to disable that LoRA while keeping the rest of the preset unchanged.
  • Start with a small number of LoRA overrides before stacking many changes together.

Notes

  • This endpoint includes all base image-to-video inputs and adds preset and loras.
  • Default preset is tuned.
  • Default loras value is {}.
  • Unknown LoRA keys are ignored.
  • Each active LoRA adds approximately 0.5–0.8 seconds of extra runtime at 480p / 5s.
  • In the worst case, using all 13 LoRAs may increase runtime by approximately 30% compared with using no LoRAs.
  • Pass loras: {"omninft": 0} to fully disable that LoRA from the selected preset without changing the rest.
  • By using this endpoint, you confirm that you have the right to generate the requested content under your jurisdiction.
Lưu ý:Trang web này sử dụng các mô hình AI do bên thứ ba cung cấp.

Ltx 2.3 Spicy Image To Video Lora API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/wavespeed-ai/ltx-2.3-spicy/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 Spicy Image To Video Lora below.

HTTP example
set -euo pipefail

: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"

REQUEST_BODY=$(cat <<'JSON'
{
    "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
    "preset": "tuned",
    "resolution": "480p",
    "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-spicy/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
done
Node.js example
const submitUrl = "https://api.wavespeed.ai/api/v3/wavespeed-ai/ltx-2.3-spicy/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 ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
        "preset": "tuned",
        "resolution": "480p",
        "duration": 5,
        "seed": -1
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
  `https://api.wavespeed.ai/api/v3/predictions/${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));
}
Python example
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 = {
    "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
    "preset": "tuned",
    "resolution": "480p",
    "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-spicy/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 Spicy Image To Video Lora API — Frequently asked questions

What is the Ltx 2.3 Spicy Image To Video Lora API?

Ltx 2.3 Spicy Image To Video Lora is a WaveSpeedAI model for AI inference, exposed as a REST API on WaveSpeedAI. LTX 2.3 Spicy LoRA Image to Video API turns a reference image and prompt into expressive AI videos using selectable LoRA presets, optional LoRA strength overrides, duration, and resolution controls. Run fast REST inference on WaveSpeedAI with no cold starts and affordable pricing. You can call it programmatically or try it from the playground above.

How do I call the Ltx 2.3 Spicy Image To Video Lora API?

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-spicy-image-to-video-lora.

How much does Ltx 2.3 Spicy Image To Video Lora cost per run?

Ltx 2.3 Spicy Image To Video Lora starts at $0.15 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.

What inputs does Ltx 2.3 Spicy Image To Video Lora accept?

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-spicy-image-to-video-lora.

How long does Ltx 2.3 Spicy Image To Video Lora take to generate?

Median end-to-end generation time on WaveSpeedAI is around 57 seconds per request, based on recent successful runs. Queue time varies with global demand; live status is visible in the prediction record.

Can I use Ltx 2.3 Spicy Image To Video Lora outputs commercially?

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.

LTX 2.3 Spicy LORA Image to Video API | WaveSpeedAI