—
LTX 2.3 Trainer V2 — Video to Video
Train a LoRA that learns a video-to-video transformation from paired before/after clips, steered at inference by a reference (control) video.
Input
Add your inputs and customize the generation settings.
Result & Pricing
Training results and model downloads will appear here.
Your trained model will appear here
Training results and model downloads will appear here.
Model pricing (tax excluded) per training step
| Specification | Webot INR |
|---|---|
| Rate | ₹0.71 |
Calculate credits in the input panel for your selected settings.
Prices, estimates and credit deductions exclude tax. Any applicable tax is charged only when you buy plans or credits.
Minimum billed training steps: 0. Prices are converted to INR. Credits use your current plan rate.
- Prices shown are estimates, not final charges. Final billing details will be available in Reports after generation is complete.
API
WEBOT API · Video to Video
Generate from your server with your WEBOT account credits.
Use your 120-character WEBOT customer key (a–z, A–Z, 0–9). Send
Authorization: Bearer YOUR_KEY. Keys are secrets: call from a server, never from public frontend code. Results come from verified webhooks and remain saved if your stream disconnects.1. Configure your server
WEBOT_BASE_URL=https://webot.online
WEBOT_API_KEY=<your-server-side-WEBOT-key>This base URL is resolved from verified domain mappings and your direct creator reseller. Forwarded Host headers are not trusted. New custom reseller domains need DNS, TLS and platform verification before activation.
2. Quote, then generate
| Method | Endpoint | Purpose |
|---|---|---|
| POST | https://webot.online/api/v1/models/ltx23_trainer_v2_v2v/quote | Validate input and calculate credits (no deduction). |
| POST | https://webot.online/api/v1/models/ltx23_trainer_v2_v2v/requests | Reserve quoted credits and queue an asynchronous job. |
| GET | https://webot.online/api/v1/models/ltx23_trainer_v2_v2v/requests/{request_id}/result | Read your saved result: 202 pending, 200 terminal. |
| GET | https://webot.online/api/v1/models/ltx23_trainer_v2_v2v/requests/{request_id}/events | Authenticated SSE: generation / terminal events. |
Send JSON {"input":{…}} to quote. Send the same input plus integer quoted_credits to generate, with Authorization: Bearer … and Idempotency-Key. Use a unique 16–128 character key per new job; persist it and reuse the same key and input on any uncertain response. Never retry with a new key: that creates a second chargeable job.
Credits are reserved only after validation and a durable request is saved. A changed quote or insufficient balance returns 409. Credits exclude purchase taxes. The quoted amount is an initial reservation. After generation, the final charge replaces it using confirmed usage. Any verified unused allocation becomes available automatically; additional usage may require more credits. Missing billing stays pending, including for failed jobs.
3. Input example
Save this as input.json. Replace sample prompts, files and media URLs with your own. Schemas do not guarantee provider acceptance of the content.
{
"training_data_url": "https://example.com/source.png",
"rank": 32,
"split_input_into_scenes": true,
"frame_rate": 24,
"validation_frame_rate": 24,
"validation_resolution": "high",
"number_of_steps": 3000,
"stg_scale": 1,
"validation_negative_prompt": "blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio, incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts.",
"trigger_phrase": "",
"reference_temporal_scale_factor": 1,
"reference_downscale_factor": 1,
"auto_scale_input": false,
"first_frame_conditioning_p": 0.1,
"validation_aspect_ratio": "1:1",
"aspect_ratio": "1:1",
"split_input_duration_threshold": 30,
"debug_dataset": false,
"validation": [],
"resolution": "medium",
"validation_number_of_frames": 89,
"learning_rate": 0.0002,
"number_of_frames": 89
}4. Language examples
# Save the model's example input as input.json, then replace prompts/media URLs.
# Requires curl and jq. Store NONCE once for this job; reuse it on any retry.
export NONCE="$(openssl rand -hex 16)"
BASE="${WEBOT_BASE_URL%/}"
jq -n --slurpfile input input.json '{input:$input[0]}' > quote-body.json
curl --fail-with-body -sS "$BASE/api/v1/models/ltx23_trainer_v2_v2v/quote" \
-H "Authorization: Bearer $WEBOT_API_KEY" -H 'Content-Type: application/json' \
--data-binary @quote-body.json > quote.json
CREDITS=$(jq -er '.quote.credits_consumed' quote.json)
jq --argjson credits "$CREDITS" '. + {quoted_credits:$credits}' quote-body.json > request-body.json
curl --fail-with-body -sS "$BASE/api/v1/models/ltx23_trainer_v2_v2v/requests" \
-H "Authorization: Bearer $WEBOT_API_KEY" -H "Idempotency-Key: $NONCE" \
-H 'Content-Type: application/json' --data-binary @request-body.json > job.json
# Subscribe; after a nonterminal disconnect, reconnect this SAME URL.
curl --fail-with-body -N "$(jq -er '.events_url' job.json)" -H "Authorization: Bearer $WEBOT_API_KEY"
# Read saved output after terminal notification (never call provider status/results).
curl --fail-with-body -sS "$(jq -er '.result_url' job.json)" -H "Authorization: Bearer $WEBOT_API_KEY"// Node.js 18+. Save your customized input in input.json.
import { readFileSync } from 'node:fs';
import { randomUUID } from 'node:crypto';
const base = process.env.WEBOT_BASE_URL.replace(/\/$/, '');
const key = process.env.WEBOT_API_KEY;
const input = JSON.parse(readFileSync('input.json', 'utf8'));
const nonce = process.env.WEBOT_JOB_NONCE || randomUUID(); // Persist before submission.
async function post(path, body, nonce) {
const response = await fetch(base + path, {method:'POST', headers:{
Authorization:`Bearer ${key}`, 'Content-Type':'application/json',
...(nonce ? {'Idempotency-Key':nonce} : {})}, body:JSON.stringify(body)});
const json = await response.json();
if (!response.ok) throw new Error(JSON.stringify(json));
return json;
}
const {quote} = await post('/api/v1/models/ltx23_trainer_v2_v2v/quote', {input});
const job = await post('/api/v1/models/ltx23_trainer_v2_v2v/requests', {input, quoted_credits:quote.credits_consumed}, nonce);
console.log(job); // Stable WEBOT request_id, events_url, result_url.
// Stream saved webhook state. Reconnect ONLY the event stream, not the generation.
while (!job.terminal || job.financial_pending) {
const stream = await fetch(job.events_url, {headers:{Authorization:`Bearer ${key}`}});
if (!stream.ok) throw new Error(`Event stream HTTP ${stream.status}`);
let buffer = '';
for await (const chunk of stream.body.pipeThrough(new TextDecoderStream())) {
buffer += chunk;
let end;
while ((end = buffer.indexOf('\n\n')) !== -1) {
const event = buffer.slice(0, end); buffer = buffer.slice(end + 2);
const data = event.split('\n').find(line => line.startsWith('data: '));
if (!data) continue;
const state = JSON.parse(data.slice(6));
if (state.error && !state.status) throw new Error(JSON.stringify(state.error));
if (state.terminal && !state.financial_pending) { console.log(state.output ?? state.error); process.exit(0); }
}
}
await new Promise(resolve => setTimeout(resolve, 1500));
}
console.log(job.output ?? job.error);// Node.js 18+. Save your customized input in input.json.
import { readFileSync } from 'node:fs';
import { randomUUID } from 'node:crypto';
const base = process.env.WEBOT_BASE_URL!.replace(/\/$/, '');
const key = process.env.WEBOT_API_KEY!;
const input = JSON.parse(readFileSync('input.json', 'utf8'));
const nonce = process.env.WEBOT_JOB_NONCE || randomUUID(); // Persist before submission.
async function post(path: string, body: unknown, nonce?: string) {
const response = await fetch(base + path, {method:'POST', headers:{
Authorization:`Bearer ${key}`, 'Content-Type':'application/json',
...(nonce ? {'Idempotency-Key':nonce} : {})}, body:JSON.stringify(body)});
const json = await response.json();
if (!response.ok) throw new Error(JSON.stringify(json));
return json;
}
const {quote} = await post('/api/v1/models/ltx23_trainer_v2_v2v/quote', {input});
const job = await post('/api/v1/models/ltx23_trainer_v2_v2v/requests', {input, quoted_credits:quote.credits_consumed}, nonce);
console.log(job); // Stable WEBOT request_id, events_url, result_url.
// Stream saved webhook state. Reconnect ONLY the event stream, not the generation.
while (!job.terminal || job.financial_pending) {
const stream = await fetch(job.events_url, {headers:{Authorization:`Bearer ${key}`}});
if (!stream.ok) throw new Error(`Event stream HTTP ${stream.status}`);
let buffer = '';
for await (const chunk of stream.body.pipeThrough(new TextDecoderStream())) {
buffer += chunk;
let end;
while ((end = buffer.indexOf('\n\n')) !== -1) {
const event = buffer.slice(0, end); buffer = buffer.slice(end + 2);
const data = event.split('\n').find(line => line.startsWith('data: '));
if (!data) continue;
const state = JSON.parse(data.slice(6));
if (state.error && !state.status) throw new Error(JSON.stringify(state.error));
if (state.terminal && !state.financial_pending) { console.log(state.output ?? state.error); process.exit(0); }
}
}
await new Promise(resolve => setTimeout(resolve, 1500));
}
console.log(job.output ?? job.error);# Python 3.9+, pip install requests
import json, os, time, uuid, requests
base = os.environ['WEBOT_BASE_URL'].rstrip('/')
headers = {'Authorization': 'Bearer ' + os.environ['WEBOT_API_KEY']}
with open('input.json', encoding='utf-8') as file:
input_data = json.load(file)
nonce = os.environ.get('WEBOT_JOB_NONCE') or str(uuid.uuid4()) # Persist before submitting.
def post(path, body, extra=None):
response = requests.post(base + path, headers={**headers, **(extra or {})}, json=body, timeout=180)
response.raise_for_status()
return response.json()
quote = post('/api/v1/models/ltx23_trainer_v2_v2v/quote', {'input': input_data})['quote']
job = post('/api/v1/models/ltx23_trainer_v2_v2v/requests', {'input': input_data, 'quoted_credits': quote['credits_consumed']}, {'Idempotency-Key': nonce})
state = job
while not state['terminal'] or state.get('financial_pending', False):
# Reconnect while nonterminal; this reads WEBOT's database, never a provider status API.
with requests.get(job['events_url'], headers=headers, stream=True, timeout=(10, 40)) as stream:
stream.raise_for_status()
for line in stream.iter_lines(decode_unicode=True):
if line and line.startswith('data: '):
state = json.loads(line[6:])
if 'status' not in state: raise RuntimeError(state)
if state['terminal'] and not state.get('financial_pending', False): break
if not state['terminal'] or state.get('financial_pending', False): time.sleep(1.5)
print(state['output'] if state['status'] == 'completed' else state['error'])<?php // PHP 8.1+ with cURL
$base = rtrim(getenv('WEBOT_BASE_URL'), '/');
$input = json_decode(file_get_contents('input.json'), false, 64, JSON_THROW_ON_ERROR);
$nonce = getenv('WEBOT_JOB_NONCE') ?: bin2hex(random_bytes(16)); // Persist this before submission.
function post(string $path, array $body, ?string $nonce = null): array {
global $base;
$headers = ['Authorization: Bearer '.getenv('WEBOT_API_KEY'), 'Content-Type: application/json'];
if ($nonce) $headers[] = 'Idempotency-Key: '.$nonce;
$ch = curl_init($base.$path);
curl_setopt_array($ch, [CURLOPT_RETURNTRANSFER=>true, CURLOPT_POST=>true,
CURLOPT_TIMEOUT=>180, CURLOPT_HTTPHEADER=>$headers,
CURLOPT_POSTFIELDS=>json_encode($body, JSON_THROW_ON_ERROR)]);
$raw = curl_exec($ch); $status = curl_getinfo($ch, CURLINFO_HTTP_CODE); curl_close($ch);
if ($raw === false || $status < 200 || $status >= 300) throw new RuntimeException('WEBOT HTTP '.$status);
return json_decode($raw, true, 64, JSON_THROW_ON_ERROR);
}
$quote = post('/api/v1/models/ltx23_trainer_v2_v2v/quote', ['input'=>$input])['quote'];
$job = post('/api/v1/models/ltx23_trainer_v2_v2v/requests', ['input'=>$input, 'quoted_credits'=>$quote['credits_consumed']], $nonce);
echo json_encode($job, JSON_PRETTY_PRINT); // Connect to events_url with the same Bearer header.// Go 1.20+; save as main.go.
package main
import ("bytes"; "encoding/json"; "fmt"; "io"; "net/http"; "os"; "strings"; "time"; "crypto/rand"; "encoding/hex")
func main() {
base := strings.TrimRight(os.Getenv("WEBOT_BASE_URL"), "/")
raw, err := os.ReadFile("input.json"); if err != nil { panic(err) }
nonce := os.Getenv("WEBOT_JOB_NONCE")
if nonce == "" { b := make([]byte,16); if _,err:=rand.Read(b);err!=nil {panic(err)}; nonce=hex.EncodeToString(b) }
// Persist nonce before the submission; reuse on ambiguous responses.
client := &http.Client{Timeout:180*time.Second}
post := func(path string, body any, id string) map[string]any {
data, err := json.Marshal(body); if err != nil {panic(err)}
req, err := http.NewRequest("POST",base+path,bytes.NewReader(data)); if err!=nil {panic(err)}
req.Header.Set("Authorization","Bearer "+os.Getenv("WEBOT_API_KEY")); req.Header.Set("Content-Type","application/json")
if id!="" {req.Header.Set("Idempotency-Key",id)}
res,err:=client.Do(req); if err!=nil {panic(err)}; defer res.Body.Close()
data,err=io.ReadAll(res.Body); if err!=nil {panic(err)}
if res.StatusCode<200||res.StatusCode>=300 {panic(string(data))}
var result map[string]any; if err=json.Unmarshal(data,&result);err!=nil {panic(err)}; return result
}
input:=json.RawMessage(raw)
quote:=post("/api/v1/models/ltx23_trainer_v2_v2v/quote",map[string]any{"input":input},"")["quote"].(map[string]any)
job:=post("/api/v1/models/ltx23_trainer_v2_v2v/requests",map[string]any{"input":input,"quoted_credits":quote["credits_consumed"]},nonce)
fmt.Println(job) // Stream events_url with the same Authorization header.
}// Java 11+, Jackson databind dependency; class Main in Main.java.
import java.net.URI;
import java.net.http.*;
import java.nio.file.*;
import java.time.Duration;
import java.util.UUID;
import com.fasterxml.jackson.databind.*;
import com.fasterxml.jackson.databind.node.ObjectNode;
public class Main {
static final ObjectMapper json = new ObjectMapper();
static final HttpClient client = HttpClient.newHttpClient();
static final String base = System.getenv("WEBOT_BASE_URL").replaceAll("/$", "");
static JsonNode post(String path, JsonNode body, String nonce) throws Exception {
var b = HttpRequest.newBuilder(URI.create(base+path)).timeout(Duration.ofSeconds(180))
.header("Authorization","Bearer "+System.getenv("WEBOT_API_KEY")).header("Content-Type","application/json")
.POST(HttpRequest.BodyPublishers.ofString(json.writeValueAsString(body)));
if(nonce!=null)b.header("Idempotency-Key",nonce);
var r=client.send(b.build(),HttpResponse.BodyHandlers.ofString());
if(r.statusCode()<200||r.statusCode()>=300)throw new IllegalStateException(r.body());
return json.readTree(r.body());
}
public static void main(String[] args) throws Exception {
var input=json.readTree(Files.readString(Path.of("input.json")));
ObjectNode body=json.createObjectNode();body.set("input",input);
var quote=post("/api/v1/models/ltx23_trainer_v2_v2v/quote",body,null).get("quote");
body.put("quoted_credits",quote.get("credits_consumed").asInt());
String nonce=System.getenv("WEBOT_JOB_NONCE");if(nonce==null)nonce=UUID.randomUUID().toString(); // Persist before POST.
var job=post("/api/v1/models/ltx23_trainer_v2_v2v/requests",body,nonce);System.out.println(job);
// Subscribe to job.events_url with Authorization; use BodyHandlers.ofLines().
}
}// .NET 8 console app, top-level statements.
using System.Net.Http;
using System.Text;
using System.Text.Json.Nodes;
var client = new HttpClient { Timeout = TimeSpan.FromSeconds(180) };
var root = Environment.GetEnvironmentVariable("WEBOT_BASE_URL")!.TrimEnd('/');
var key = Environment.GetEnvironmentVariable("WEBOT_API_KEY");
async Task<JsonNode> Post(string path, JsonNode body, string? nonce = null) {
using var req = new HttpRequestMessage(HttpMethod.Post, root + path);
req.Headers.Add("Authorization", "Bearer " + key);
if (nonce != null) req.Headers.Add("Idempotency-Key", nonce);
req.Content = new StringContent(body.ToJsonString(), Encoding.UTF8, "application/json");
using var res = await client.SendAsync(req);
var raw = await res.Content.ReadAsStringAsync();res.EnsureSuccessStatusCode();
return JsonNode.Parse(raw)!;
}
var input = JsonNode.Parse(await File.ReadAllTextAsync("input.json"));
var body = new JsonObject { ["input"] = input };
var quote = await Post("/api/v1/models/ltx23_trainer_v2_v2v/quote", body);
body["quoted_credits"] = quote["quote"]!["credits_consumed"]!.GetValue<int>();
var nonce = Environment.GetEnvironmentVariable("WEBOT_JOB_NONCE") ?? Guid.NewGuid().ToString(); // Persist before submitting.
var job = await Post("/api/v1/models/ltx23_trainer_v2_v2v/requests", body, nonce);
Console.WriteLine(job); // Subscribe to events_url with the same Bearer header and ResponseHeadersRead.# Ruby 3+, standard library only.
require 'net/http'
require 'json'
require 'securerandom'
base = ENV.fetch('WEBOT_BASE_URL').sub(%r{/$}, '')
post = lambda do |path, body, nonce = nil|
uri = URI(base + path)
req = Net::HTTP::Post.new(uri)
req['Authorization'] = 'Bearer ' + ENV.fetch('WEBOT_API_KEY')
req['Content-Type'] = 'application/json'
req['Idempotency-Key'] = nonce if nonce
req.body = JSON.generate(body)
res = Net::HTTP.start(uri.host, uri.port, use_ssl: true, read_timeout: 180) { |http| http.request(req) }
raise res.body unless res.is_a?(Net::HTTPSuccess)
JSON.parse(res.body)
end
input = JSON.parse(File.read('input.json'))
quote = post.call('/api/v1/models/ltx23_trainer_v2_v2v/quote', {'input' => input})['quote']
nonce = ENV['WEBOT_JOB_NONCE'] || SecureRandom.uuid # Persist this before submission.
job = post.call('/api/v1/models/ltx23_trainer_v2_v2v/requests', {'input' => input, 'quoted_credits' => quote['credits_consumed']}, nonce)
puts JSON.pretty_generate(job) # Subscribe to events_url with the same Authorization header.// Swift 5.9 server-side/CLI only. Do not embed customer keys in shipped apps.
import Foundation
#if canImport(FoundationNetworking)
import FoundationNetworking
#endif
@main struct Main {
static func main() async throws {
let env=ProcessInfo.processInfo.environment
let base=env["WEBOT_BASE_URL"]!.trimmingCharacters(in: CharacterSet(charactersIn:"/"))
let input=try JSONSerialization.jsonObject(with: Data(contentsOf:URL(fileURLWithPath:"input.json")))
func post(_ path:String,_ body:[String:Any],_ nonce:String?=nil) async throws -> [String:Any] {
var req=URLRequest(url:URL(string:base+path)!);req.httpMethod="POST";req.timeoutInterval=180
req.setValue("Bearer "+env["WEBOT_API_KEY"]!,forHTTPHeaderField:"Authorization")
req.setValue("application/json",forHTTPHeaderField:"Content-Type")
if let nonce {req.setValue(nonce,forHTTPHeaderField:"Idempotency-Key")}
req.httpBody=try JSONSerialization.data(withJSONObject:body)
let (data,res)=try await URLSession.shared.data(for:req)
guard let http=res as? HTTPURLResponse,(200..<300).contains(http.statusCode) else {throw NSError(domain:"WEBOT",code:1)}
return try JSONSerialization.jsonObject(with:data) as! [String:Any]
}
let quote=try await post("/api/v1/models/ltx23_trainer_v2_v2v/quote",["input":input])["quote"] as! [String:Any]
let nonce=env["WEBOT_JOB_NONCE"] ?? UUID().uuidString // Persist before submission.
let job=try await post("/api/v1/models/ltx23_trainer_v2_v2v/requests",["input":input,"quoted_credits":quote["credits_consumed"]!],nonce)
print(job) // Subscribe to events_url with the same Authorization header.
}
}// Server-side Kotlin/JVM 17+, Gradle dependencies: OkHttp 4.12, org.json 20240303.
import okhttp3.*
import okhttp3.MediaType.Companion.toMediaType
import okhttp3.RequestBody.Companion.toRequestBody
import org.json.JSONObject
import java.io.File
import java.util.UUID
import java.util.concurrent.TimeUnit
fun main() {
val base=System.getenv("WEBOT_BASE_URL").trimEnd('/')
val client=OkHttpClient.Builder().readTimeout(180,TimeUnit.SECONDS).build()
fun post(path:String,body:JSONObject,nonce:String?=null):JSONObject {
val b=Request.Builder().url(base+path).header("Authorization","Bearer "+System.getenv("WEBOT_API_KEY"))
.post(body.toString().toRequestBody("application/json".toMediaType()))
if(nonce!=null)b.header("Idempotency-Key",nonce)
return client.newCall(b.build()).execute().use {res ->
val raw=res.body!!.string();check(res.isSuccessful){raw};JSONObject(raw)
}
}
val body=JSONObject().put("input",JSONObject(File("input.json").readText()))
val quote=post("/api/v1/models/ltx23_trainer_v2_v2v/quote",body).getJSONObject("quote")
body.put("quoted_credits",quote.getInt("credits_consumed"))
val nonce=System.getenv("WEBOT_JOB_NONCE") ?: UUID.randomUUID().toString() // Persist before submission.
val job=post("/api/v1/models/ltx23_trainer_v2_v2v/requests",body,nonce)
println(job) // Subscribe to events_url with the same Authorization header.
}5. Receive all results
The response includes a stable WEBOT request_id, events_url and result_url. Subscribe with a Bearer-authenticated HTTP stream. Nonterminal streams end after 25 seconds; reconnect to the same URL after at least 1.5 seconds. Current saved state is replayed immediately, including completion that happened while disconnected. A terminal event contains the result envelope. The JSON terminal flag describes generation completion. Keep reconnecting while financial_pending is true; stop after the terminal event confirms financial settlement. Never poll provider status/results. Native browser EventSource cannot send a Bearer header; keep the key on your server.
Completed output contains the full model result, including every generated media/document item, not just the first URL. Failed output is null with error and refund_state. Results are strictly limited to the key owner, including on reseller domains. Model-independent aliases: /api/v1/requests/{request_id}/result and /events. Revoking a key blocks subsequent reads and streams; saved results remain accessible with another valid key of the same account.
6. Schemas and parameter defaults
Required fields are marked with *. Required text must contain non-whitespace content. Defaults apply when an optional parameter is omitted; null, false, 0 and an empty array are distinct values. “No documented default” means WEBOT does not invent one. Examples are sample inputs, not defaults. WEBOT generation constraints can require an explicit value even when the provider publishes an automatic default.
Input schema · fields, constraints and defaults
| Parameter | Type | Required | Default when omitted | Description / constraints |
|---|---|---|---|---|
rank | integer | No | 32 | The rank of the LoRA adaptation. Higher values increase capacity but use more memory. enum: [8,16,32,64,128] |
split_input_into_scenes | boolean | No | true | If true, videos above a certain duration threshold will be split into scenes. |
frame_rate | integer | No | 24 | Target frames per second for the training video (LTX-2.3 native is 24). minimum: 8 · maximum: 60 |
validation_frame_rate | integer | No | 24 | Target frames per second for validation videos (LTX-2.3 native is 24). minimum: 8 · maximum: 60 |
validation_resolution | string | No | "high" | The resolution to use for validation. enum: ["low","medium","high"] |
number_of_steps | integer | No | 3000 | The number of training steps. minimum: 100 · maximum: 10000 |
stg_scale | number | No | 1 | STG (Spatio-Temporal Guidance) scale. 0.0 disables STG. Recommended value is 1.0. minimum: 0 · maximum: 3 |
validation_negative_prompt | string | No | "blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio, incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts." | A negative prompt to use for validation. Note: validation previews are single-stage approximations of the production two-stage (distilled) inference, so preview quality and guidance differ from final inference. |
trigger_phrase | string | No | "" | A phrase that will trigger the LoRA style. Will be prepended to captions during training. |
training_data_url | string | Yes * | No documented default | URL to a `.zip` archive of your training data. The exact file layout depends on the training mode — see this endpoint's documentation for the required structure. You can include a `.txt` caption alongside each media file (same base name). |
reference_temporal_scale_factor | integer | No | 1 | Temporally downsample the reference (IC-LoRA control) video by this factor (lower fps) before encoding, so the LoRA can be driven by a low-fps reference. 1 = same fps (default; unchanged behavior). minimum: 1 · maximum: 8 |
reference_downscale_factor | integer | No | 1 | Spatially downscale the reference (IC-LoRA control) video by this factor before encoding, so the LoRA learns to drive a full-resolution output from a coarse / low-res reference (e.g. a small pose/depth/sketch proxy). 1 = same resolution (default; unchanged behavior). Both the reference width/height and width/height divided by the factor must be divisible by 32. minimum: 1 · maximum: 8 |
auto_scale_input | boolean | No | false | If true, videos will be automatically scaled to the target frame count and fps. This option has no effect on image datasets. |
first_frame_conditioning_p | number | No | 0.1 | Probability of conditioning on the first frame during training. Lower values work better for video-to-video transformation. minimum: 0 · maximum: 1 |
validation_aspect_ratio | string | No | "1:1" | The aspect ratio to use for validation. enum: ["16:9","1:1","9:16"] |
aspect_ratio | string | No | "1:1" | Aspect ratio to use for training. enum: ["16:9","1:1","9:16"] |
split_input_duration_threshold | number | No | 30 | The duration threshold in seconds. If a video is longer than this, it will be split into scenes. minimum: 1 · maximum: 60 |
debug_dataset | boolean | No | false | When enabled, the trainer returns a downloadable archive of your preprocessed training data for manual inspection. Use this to verify that your videos, images, and captions were processed correctly before committing to a full training run. |
validation | array | No | [] | A list of validation inputs with prompts and reference videos. maxItems: 2 |
validation[].reference_video_url | string | Yes * | No documented default | URL to reference video for IC-LoRA validation. This is the input video that will be transformed. minLength: 1 |
validation[].prompt | string | Yes * | No documented default | The prompt to use for validation. |
resolution | string | No | "medium" | Resolution to use for training. Higher resolutions require more memory. enum: ["low","medium","high"] |
validation_number_of_frames | integer | No | 89 | The number of frames in validation videos. minimum: 9 · maximum: 121 |
learning_rate | number | No | 0.0002 | Learning rate for optimization. minimum: 1.0e-6 · maximum: 1 |
number_of_frames | integer | No | 89 | Number of frames per training sample. Must satisfy frames % 8 == 1 (e.g., 1, 9, 17, 25, 33, 41, 49, 57, 65, 73, 81, 89, 97). minimum: 9 · maximum: 121 |
{
"properties": {
"rank": {
"default": 32,
"title": "Rank",
"enum": [
8,
16,
32,
64,
128
],
"examples": [
32
],
"description": "The rank of the LoRA adaptation. Higher values increase capacity but use more memory.",
"type": "integer"
},
"split_input_into_scenes": {
"default": true,
"title": "Split Input Into Scenes",
"description": "If true, videos above a certain duration threshold will be split into scenes.",
"examples": [
true
],
"type": "boolean"
},
"frame_rate": {
"default": 24,
"title": "Frame Rate",
"maximum": 60,
"examples": [
24
],
"description": "Target frames per second for the training video (LTX-2.3 native is 24).",
"minimum": 8,
"type": "integer"
},
"validation_frame_rate": {
"default": 24,
"title": "Validation Frame Rate",
"maximum": 60,
"examples": [
24
],
"description": "Target frames per second for validation videos (LTX-2.3 native is 24).",
"minimum": 8,
"type": "integer"
},
"validation_resolution": {
"default": "high",
"title": "Validation Resolution",
"enum": [
"low",
"medium",
"high"
],
"examples": [
"high"
],
"description": "The resolution to use for validation.",
"type": "string"
},
"number_of_steps": {
"maximum": 10000,
"description": "The number of training steps.",
"minimum": 100,
"default": 3000,
"step": 100,
"type": "integer",
"title": "Number Of Steps",
"examples": [
3000
]
},
"stg_scale": {
"default": 1,
"title": "Stg Scale",
"maximum": 3,
"description": "STG (Spatio-Temporal Guidance) scale. 0.0 disables STG. Recommended value is 1.0.",
"minimum": 0,
"type": "number"
},
"validation_negative_prompt": {
"default": "blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio, incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts.",
"title": "Validation Negative Prompt",
"description": "A negative prompt to use for validation. Note: validation previews are single-stage approximations of the production two-stage (distilled) inference, so preview quality and guidance differ from final inference.",
"type": "string"
},
"trigger_phrase": {
"default": "",
"title": "Trigger Phrase",
"description": "A phrase that will trigger the LoRA style. Will be prepended to captions during training.",
"examples": [
""
],
"type": "string"
},
"training_data_url": {
"title": "Training Data Url",
"description": "URL to a `.zip` archive of your training data. The exact file layout depends on the training mode \u2014 see this endpoint's documentation for the required structure. You can include a `.txt` caption alongside each media file (same base name).",
"type": "string"
},
"reference_temporal_scale_factor": {
"default": 1,
"title": "Reference Temporal Scale Factor",
"maximum": 8,
"description": "Temporally downsample the reference (IC-LoRA control) video by this factor (lower fps) before encoding, so the LoRA can be driven by a low-fps reference. 1 = same fps (default; unchanged behavior).",
"minimum": 1,
"type": "integer"
},
"reference_downscale_factor": {
"default": 1,
"title": "Reference Downscale Factor",
"maximum": 8,
"description": "Spatially downscale the reference (IC-LoRA control) video by this factor before encoding, so the LoRA learns to drive a full-resolution output from a coarse / low-res reference (e.g. a small pose/depth/sketch proxy). 1 = same resolution (default; unchanged behavior). Both the reference width/height and width/height divided by the factor must be divisible by 32.",
"minimum": 1,
"type": "integer"
},
"auto_scale_input": {
"default": false,
"title": "Auto Scale Input",
"description": "If true, videos will be automatically scaled to the target frame count and fps. This option has no effect on image datasets.",
"examples": [
false
],
"type": "boolean"
},
"first_frame_conditioning_p": {
"default": 0.1,
"title": "First Frame Conditioning P",
"maximum": 1,
"description": "Probability of conditioning on the first frame during training. Lower values work better for video-to-video transformation.",
"minimum": 0,
"type": "number"
},
"validation_aspect_ratio": {
"default": "1:1",
"title": "Validation Aspect Ratio",
"enum": [
"16:9",
"1:1",
"9:16"
],
"examples": [
"1:1"
],
"description": "The aspect ratio to use for validation.",
"type": "string"
},
"aspect_ratio": {
"default": "1:1",
"title": "Aspect Ratio",
"enum": [
"16:9",
"1:1",
"9:16"
],
"examples": [
"1:1"
],
"description": "Aspect ratio to use for training.",
"type": "string"
},
"split_input_duration_threshold": {
"default": 30,
"title": "Split Input Duration Threshold",
"maximum": 60,
"examples": [
30
],
"description": "The duration threshold in seconds. If a video is longer than this, it will be split into scenes.",
"minimum": 1,
"type": "number"
},
"debug_dataset": {
"default": false,
"title": "Debug Dataset",
"description": "When enabled, the trainer returns a downloadable archive of your preprocessed training data for manual inspection. Use this to verify that your videos, images, and captions were processed correctly before committing to a full training run.",
"type": "boolean"
},
"validation": {
"maxItems": 2,
"default": [],
"title": "Validation",
"description": "A list of validation inputs with prompts and reference videos.",
"items": {
"properties": {
"reference_video_url": {
"title": "Reference Video Url",
"description": "URL to reference video for IC-LoRA validation. This is the input video that will be transformed.",
"minLength": 1,
"type": "string"
},
"prompt": {
"title": "Prompt",
"description": "The prompt to use for validation.",
"type": "string"
}
},
"required": [
"prompt",
"reference_video_url"
],
"title": "V2VValidation",
"description": "Validation input for video-to-video training.",
"x-webot-order-properties": [
"prompt",
"reference_video_url"
],
"type": "object"
},
"type": "array"
},
"resolution": {
"default": "medium",
"title": "Resolution",
"enum": [
"low",
"medium",
"high"
],
"examples": [
"medium"
],
"description": "Resolution to use for training. Higher resolutions require more memory.",
"type": "string"
},
"validation_number_of_frames": {
"default": 89,
"title": "Validation Number Of Frames",
"maximum": 121,
"examples": [
89
],
"description": "The number of frames in validation videos.",
"minimum": 9,
"type": "integer"
},
"learning_rate": {
"step": 0.0001,
"default": 0.0002,
"title": "Learning Rate",
"maximum": 1,
"description": "Learning rate for optimization.",
"minimum": 1.0e-6,
"type": "number"
},
"number_of_frames": {
"default": 89,
"title": "Number Of Frames",
"maximum": 121,
"examples": [
89
],
"description": "Number of frames per training sample. Must satisfy frames % 8 == 1 (e.g., 1, 9, 17, 25, 33, 41, 49, 57, 65, 73, 81, 89, 97).",
"minimum": 9,
"type": "integer"
}
},
"required": [
"training_data_url"
],
"title": "V2VInput",
"description": "Video-to-video IC-LoRA training (reference conditioning).",
"x-webot-order-properties": [
"training_data_url",
"rank",
"number_of_steps",
"learning_rate",
"number_of_frames",
"frame_rate",
"resolution",
"aspect_ratio",
"trigger_phrase",
"auto_scale_input",
"split_input_into_scenes",
"split_input_duration_threshold",
"debug_dataset",
"first_frame_conditioning_p",
"validation",
"validation_negative_prompt",
"validation_number_of_frames",
"validation_frame_rate",
"validation_resolution",
"validation_aspect_ratio",
"stg_scale",
"reference_downscale_factor",
"reference_temporal_scale_factor"
],
"type": "object"
}Output (inside result.output) schema · fields, constraints and defaults
| Parameter | Type | Required | Default when omitted | Description / constraints |
|---|---|---|---|---|
config_file | object | Yes * | No documented default | Configuration used for setting up inference endpoints. |
config_file.content_type | string | null | No | No documented default | The mime type of the file. |
config_file.url | string | Yes * | No documented default | The URL where the file can be downloaded from. |
config_file.file_size | integer | null | No | No documented default | The size of the file in bytes. |
config_file.file_name | string | null | No | No documented default | The name of the file. It will be auto-generated if not provided. |
audio | object | null | No | No documented default | Combined validation audio preview for the audio-only-output endpoints (/v2a, /a2a, /t2a, /audio-extend-prefix, /audio-extend-suffix, /audio-inpaint), if any. |
audio.variant0.content_type | string | null | No | No documented default | The mime type of the file. |
audio.variant0.url | string | Yes * | No documented default | The URL where the file can be downloaded from. |
audio.variant0.file_size | integer | null | No | No documented default | The size of the file in bytes. |
audio.variant0.file_name | string | null | No | No documented default | The name of the file. It will be auto-generated if not provided. |
debug_dataset | object | null | No | No documented default | Downloadable archive of the preprocessed training data, when debug_dataset is enabled. |
debug_dataset.variant0.content_type | string | null | No | No documented default | The mime type of the file. |
debug_dataset.variant0.url | string | Yes * | No documented default | The URL where the file can be downloaded from. |
debug_dataset.variant0.file_size | integer | null | No | No documented default | The size of the file in bytes. |
debug_dataset.variant0.file_name | string | null | No | No documented default | The name of the file. It will be auto-generated if not provided. |
video | object | null | No | No documented default | Combined validation video preview (video-producing endpoints), if any. |
video.variant0.content_type | string | null | No | No documented default | The mime type of the file. |
video.variant0.url | string | Yes * | No documented default | The URL where the file can be downloaded from. |
video.variant0.file_size | integer | null | No | No documented default | The size of the file in bytes. |
video.variant0.file_name | string | null | No | No documented default | The name of the file. It will be auto-generated if not provided. |
lora_file | object | Yes * | No documented default | URL to the trained LoRA weights (.safetensors). |
lora_file.content_type | string | null | No | No documented default | The mime type of the file. |
lora_file.url | string | Yes * | No documented default | The URL where the file can be downloaded from. |
lora_file.file_size | integer | null | No | No documented default | The size of the file in bytes. |
lora_file.file_name | string | null | No | No documented default | The name of the file. It will be auto-generated if not provided. |
{
"properties": {
"config_file": {
"properties": {
"content_type": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Content Type",
"description": "The mime type of the file.",
"examples": [
"image/png"
]
},
"url": {
"title": "Url",
"description": "The URL where the file can be downloaded from.",
"type": "string"
},
"file_size": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "File Size",
"description": "The size of the file in bytes.",
"examples": [
4404019
]
},
"file_name": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "File Name",
"description": "The name of the file. It will be auto-generated if not provided.",
"examples": [
"z9RV14K95DvU.png"
]
}
},
"required": [
"url"
],
"title": "File",
"x-webot-order-properties": [
"url",
"content_type",
"file_name",
"file_size"
],
"type": "object",
"description": "Configuration used for setting up inference endpoints."
},
"audio": {
"anyOf": [
{
"properties": {
"content_type": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Content Type",
"description": "The mime type of the file.",
"examples": [
"image/png"
]
},
"url": {
"title": "Url",
"description": "The URL where the file can be downloaded from.",
"type": "string"
},
"file_size": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "File Size",
"description": "The size of the file in bytes.",
"examples": [
4404019
]
},
"file_name": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "File Name",
"description": "The name of the file. It will be auto-generated if not provided.",
"examples": [
"z9RV14K95DvU.png"
]
}
},
"required": [
"url"
],
"title": "File",
"x-webot-order-properties": [
"url",
"content_type",
"file_name",
"file_size"
],
"type": "object"
},
{
"type": "null"
}
],
"description": "Combined validation audio preview for the audio-only-output endpoints (/v2a, /a2a, /t2a, /audio-extend-prefix, /audio-extend-suffix, /audio-inpaint), if any."
},
"debug_dataset": {
"anyOf": [
{
"properties": {
"content_type": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Content Type",
"description": "The mime type of the file.",
"examples": [
"image/png"
]
},
"url": {
"title": "Url",
"description": "The URL where the file can be downloaded from.",
"type": "string"
},
"file_size": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "File Size",
"description": "The size of the file in bytes.",
"examples": [
4404019
]
},
"file_name": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "File Name",
"description": "The name of the file. It will be auto-generated if not provided.",
"examples": [
"z9RV14K95DvU.png"
]
}
},
"required": [
"url"
],
"title": "File",
"x-webot-order-properties": [
"url",
"content_type",
"file_name",
"file_size"
],
"type": "object"
},
{
"type": "null"
}
],
"description": "Downloadable archive of the preprocessed training data, when debug_dataset is enabled."
},
"video": {
"anyOf": [
{
"properties": {
"content_type": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Content Type",
"description": "The mime type of the file.",
"examples": [
"image/png"
]
},
"url": {
"title": "Url",
"description": "The URL where the file can be downloaded from.",
"type": "string"
},
"file_size": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "File Size",
"description": "The size of the file in bytes.",
"examples": [
4404019
]
},
"file_name": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "File Name",
"description": "The name of the file. It will be auto-generated if not provided.",
"examples": [
"z9RV14K95DvU.png"
]
}
},
"required": [
"url"
],
"title": "File",
"x-webot-order-properties": [
"url",
"content_type",
"file_name",
"file_size"
],
"type": "object"
},
{
"type": "null"
}
],
"description": "Combined validation video preview (video-producing endpoints), if any."
},
"lora_file": {
"properties": {
"content_type": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Content Type",
"description": "The mime type of the file.",
"examples": [
"image/png"
]
},
"url": {
"title": "Url",
"description": "The URL where the file can be downloaded from.",
"type": "string"
},
"file_size": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "File Size",
"description": "The size of the file in bytes.",
"examples": [
4404019
]
},
"file_name": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "File Name",
"description": "The name of the file. It will be auto-generated if not provided.",
"examples": [
"z9RV14K95DvU.png"
]
}
},
"required": [
"url"
],
"title": "File",
"x-webot-order-properties": [
"url",
"content_type",
"file_name",
"file_size"
],
"type": "object",
"description": "URL to the trained LoRA weights (.safetensors)."
}
},
"required": [
"lora_file",
"config_file"
],
"title": "LTX2V2Output",
"description": "Output for every ``ltx23-trainer-v2`` endpoint.",
"x-webot-order-properties": [
"video",
"audio",
"lora_file",
"config_file",
"debug_dataset"
],
"type": "object"
}Errors and limits
401 invalid/expired/revoked key · 403 key scope or domain mismatch · 404 unavailable model or unowned request · 409 quote changed, balance, concurrency or idempotency conflict · 413 JSON exceeds 2 MB · 415 wrong content type · 422 invalid fields/media · 429 rate limit · 503 temporary/ambiguous submission. Respect Retry-After. Current limits per account: 12 quotes/submissions, 120 result reads and 8 stream connections per minute. One submission preparation at a time per account. Do not automatically regenerate failed jobs.
Your requests
LTX 2.3 Trainer V2 - Video to Video · Your account only
Select Requests to load your history.
| Request ID | Created at (IST) | Status | Credits used | Refunded | Processing time | Report |
|---|
Your model analytics
LTX 2.3 Trainer V2 - Video to Video · Request dates in IST
Select Analytics to load your metrics.
Request counts
Daily requests by their current status
Request outcomes
Completed, failed and pending requests
Credits used
Daily recorded charges before refunds
Processing time
Daily average for completed requests with recorded timing
Processing percentiles
Completed requests only · Time from submission to recorded completion
How to use LTX 2.3 Trainer V2 — Video to Video
This model learns a reusable appearance, subject or style from your training examples. Training creates a model asset, rather than simply making one finished picture or video.
Required inputs
- Training Data Url: The examples used to teach a model. Follow the required archive layout, file formats and captions. Relevant, varied and consistent examples matter more than merely adding unrelated files.
Workflow
- Prepare your source material and fill the required inputs above. Review the supported settings for this model.
- Sign in to calculate the credit estimate. Review the estimate before choosing Generate.
- Keep this model page open while the request runs. Completed results arrive in the result area; use the available player or download controls to review the output.
When to use this workflow
- Teach a supported model a particular subject or style.
- Create a reusable trained asset for compatible generation tools.
Key settings
- Training Data Url
- The examples used to teach a model. Follow the required archive layout, file formats and captions. Relevant, varied and consistent examples matter more than merely adding unrelated files.
- Rank
- The capacity of a learned adapter. A higher rank can store more adjustments but may use more memory or create larger files. It is not a direct measure of output quality. Supported choices: 8, 16, 32, 64, 128
- Number Of Steps
- The number of learning updates during training. Too few may not learn enough; too many may copy the training examples too closely. A longer run can use more processing. Minimum: 100. Maximum: 10000
- Learning Rate
- How much a model changes during each learning update. Too high can make learning unstable; too low can learn too slowly. More is not automatically better. Start with this trainer’s documented value. Minimum: 1.0E-6. Maximum: 1
- Number Of Frames
- The total number of still pictures used to form the clip. This is different from FPS. When playback FPS stays fixed, more frames make a longer clip. For example, 120 frames at 24 FPS last 5 seconds. Some models accept only particular frame counts. Minimum: 9. Maximum: 121
- Frame Rate
- Frames per second: how many still pictures are played in one second of video. A frame is one of those pictures. 24 FPS means 24 pictures each second. More FPS can look smoother if the model supports it. With a fixed frame count, higher FPS makes the clip shorter: 120 frames at 24 FPS is 5 seconds, at 30 FPS it is 4 seconds. Minimum: 8. Maximum: 60