ltx-2.3/image-to-video-lora

POST

/openapi/v2/rhart-video/ltx-2.3/image-to-video-lora

A LoRA inference version designed for users needing personalized visual styles in image-to-video generation. Building on LTX-2.3's foundation, it supports simultaneous loading of up to three custom LoRA adapters to directly inject brand-specific aesthetics, character likenesses, or camera languages into the generation pipeline. Whether maintaining consistent product visuals, ensuring character continuity across shots, or achieving specific cinematic camera movements, lightweight LoRA modules provide precise control without retraining the entire model. Ideal for scaled brand content production, IP character animation, and stylized commercial video creation.

Request

Authorization

Header Params

Body Params application/jsonRequired

Example

{
    "98##image": "89f8673002dc2ec7743dcbdf1386fa85610bd0f70f62ed911c8daed8a193834c.png",
    "245##select": "1",
    "240##select": "2",
    "222##value": 5,
    "254##lora_name": "framee_4000.safetensors",
    "254##strength_model": 0,
    "257##lora_name": "framee_4000.safetensors",
    "257##strength_model": 0,
    "258##lora_name": "framee_4000.safetensors",
    "258##strength_model": 0,
    "269##prompt": "Start from a low angle and slowly circle around the robot bartender, the camera moving in a smooth 360° circular motion. The robot's metallic head and mechanical arms mix drinks fluidly. The vintage wooden bar is filled with bottles, neon signs in the background flicker on and off, warm spotlights shine on the bartending actions, hanging greenery sways gently, floating dust particles catch the light in the air, creating a fully moody dark atmosphere, cinematic depth of field, 24 frames per second, natural motion blur, no clipping or stuttering."
}

Request Code Samples

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location 'https://www.runninghub.ai/openapi/v2/rhart-video/ltx-2.3/image-to-video-lora' \
--header 'Authorization: Bearer [Your API KEY]' \
--header 'Content-Type: application/json' \
--data '{
    "98##image": "89f8673002dc2ec7743dcbdf1386fa85610bd0f70f62ed911c8daed8a193834c.png",
    "245##select": "1",
    "240##select": "2",
    "222##value": 5,
    "254##lora_name": "framee_4000.safetensors",
    "254##strength_model": 0,
    "257##lora_name": "framee_4000.safetensors",
    "257##strength_model": 0,
    "258##lora_name": "framee_4000.safetensors",
    "258##strength_model": 0,
    "269##prompt": "Start from a low angle and slowly circle around the robot bartender, the camera moving in a smooth 360° circular motion. The robot'\''s metallic head and mechanical arms mix drinks fluidly. The vintage wooden bar is filled with bottles, neon signs in the background flicker on and off, warm spotlights shine on the bartending actions, hanging greenery sways gently, floating dust particles catch the light in the air, creating a fully moody dark atmosphere, cinematic depth of field, 24 frames per second, natural motion blur, no clipping or stuttering."
}'

Responses

🟢200成功

application/json

Task result query endpoint: /openapi/v2/query

Bodyapplication/json

Examples

Submit response exampleTask success response example

{
    "taskId": "2013508786110730241",
    "status": "RUNNING",
    "errorCode": "",
    "errorMessage": "",
    "results": null,
    "clientId": "f828b9af25161bc066ef152db7b29ccc",
    "promptTips": "{\"result\": true, \"error\": null, \"outputs_to_execute\": [\"4\"], \"node_errors\": {}}"
}

Modified at 2026-07-30 07:05:27

wan-3.0-prime/image-to-video

ltx-2.3/image-to-video