LTX-2.3 10Eros v1.4 I2V

About

LTX-2.3 10Eros v1.4 I2V is a specialized image-to-video fine-tune of LTX-2.3 22B for creators who want greater freedom with mature themes.

It animates a starting image into a 4–20 second clip and generates native dialogue and sound in the same pass. The fixed 9-step workflow supports landscape, portrait, and square formats with dimensions from 640 through 3840 pixels.

The model is strictly opt-in for adults: turn off the Sensitive Content Filter before submitting a job. It is currently available through the Sogni API and Sogni Creative Agent Skill for agentic creation, but not yet in Sogni Web or native apps.

Sogni serves the v1.4 checkpoint. TenStrip's upstream notes describe 10Eros as prompting-sensitive: make motion, scene evolution, camera direction, and audio explicit instead of assuming them from the source image. The upstream repository may list newer versions, so use the exact Sogni model ID on this page when you need v1.4.

Looking for still images? Explore Sogni's uncensored AI image generator for opt-in image models including Dark Beast Krea 2, Dark Beast Z-Image Turbo, and Chroma.

Prompting tips

Use the source image to establish the subject and composition, then be strict and descriptive about motion, scene evolution, camera, sound, and timing. TenStrip's upstream notes specifically recommend deliberate prompt refinement for this fine-tune.

• Motion — Describe what changes after the first frame: subject movement, environmental motion, and the final beat.
• Camera — Name one clear camera move, such as a slow push-in, orbit, pan, or locked-off shot.
• Audio — Write dialogue in quotation marks and describe the voice, ambience, and sound effects you want generated.

Available through the API and Creative Agent Skill

LTX-2.3 10Eros v1.4 is not currently available in Sogni Web or the native apps. Use the exact model ID through the Sogni API, or use the Sogni Creative Agent Skill for agentic image-to-video creation.

Compare it with MiniMax H3 on Sogni's uncensored AI video generator, or explore the uncensored AI image generator for opt-in mature-theme image models.

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 10Eros v1.4 I2V with the exact model id.

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-10eros-v1.4-fp8mixed_i2v',
  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

# ltx23-22b-10eros-v1.4-fp8mixed_i2v is addressable by id via the JavaScript SDK (see the JavaScript tab).
# The REST workflow API routes this family through its flagship alias instead:

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", "duration": 5 }
      }]
    },
    "confirm_cost": true
  }'

Addressable by id via the JavaScript SDK; the REST workflow API routes this family through its flagship alias. Full reference at docs.sogni.ai.