LTX-2.3 22B

About

LTX-2.3 22B is Lightricks' audio-driven video model: production-ready text-to-video and image-to-video with native dialogue and sound generated in the same pass.

Distilled builds run the current eight-step schedule for fast, cheap generation. Dev builds run the full 20-step schedule for maximum coherence and quality at higher latency.

The family also exposes audio-to-video, image+audio-to-video, and video-to-video model IDs, including ControlNet-assisted V2V for canny, pose, depth, detailer, outpaint, and inpaint workflows.

Variants

LTX-2.3 22B ships in 10 workflow and quality variants. Pick the mode that fits, or start with the default.

Prompting tips

LTX-2.3 is audio-driven and cinematic — the strongest prompts describe four things. Use the prompt field’s wand button to auto-expand a short idea into this shape.

• What — the subject, action, and setting.
• Feel — style, mood, and genre.
• Camera — lens, angle, and how it moves.
• Time — motion type, speed, and frame-rate intent.

LoRAs

LTX-2.3 has grown a real LoRA ecosystem in Sogni. TalkVid-3K powers voice identity for Sogni Chat Personas and is available in Sogni Web Voice Transfer. The Lightricks control LoRAs and community LoRAs are integrated in Sogni Chat, the Sogni Client SDK, and Sogni Creative Agent, with more Sogni apps coming soon.

The LoRA catalog is integrated server-side by workflow and app surface; it is not silently attached to ordinary LTX renders. Pick the Sogni surface that exposes the workflow you need, and Sogni handles the adapter details behind it.

Pricing

Use pay-as-you-go Spark packs for each clip (1 Spark = $0.005), or choose a flat-rate Sogni plan for credit-free fair-use generation in the app.

API

One Sogni API key reaches every model on the Supernet — call LTX-2.3 22B with the exact model id for the variant you want.

import { SogniClient } from '@sogni-ai/sogni-client';

const client = await SogniClient.createInstance({
  appId: crypto.randomUUID(),
  apiKey: process.env.SOGNI_API_KEY,
  network: 'fast',
});

const project = await client.projects.create({
  type: 'video',
  modelId: 'ltx23-22b-fp8_t2v_distilled',
  positivePrompt: 'a slothicorn surfing a wave of liquid paint, slow push-in, cinematic',
  numberOfMedia: 1,
  duration: 5,
});

const [url] = await project.waitForCompletion();
console.log(url); // result link — download within 24h

curl https://api.sogni.ai/v1/creative-agent/workflows \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $SOGNI_API_KEY" \
  -d '{
    "input": {
      "title": "First render",
      "steps": [{
        "id": "step1",
        "toolName": "generate_video",
        "arguments": { "prompt": "a slothicorn surfing a wave of liquid paint, slow push-in, cinematic", "videoModel": "ltx23", "duration": 5 }
      }]
    },
    "confirm_cost": true
  }'

Example uses ltx23-22b-fp8_t2v_distilled. Use any exact model id from the Variants table above. Full reference at docs.sogni.ai.