apps/infsh/ltx-video-2

ltx-video-2

LTX 2.0 audio-video foundation model. Generates videos with synced audio. Supports T2V, I2V, long video generation with multi-prompt sliding windows, and LoRA adapters.

run in browser run via API

run with your agent

# install belt

$curl -fsSL https://cli.inference.sh | sh

# view schema & details

$belt app get infsh/ltx-video-2

# run

$belt app run infsh/ltx-video-2

api reference

about

ltx 2.0 audio-video foundation model. generates videos with synced audio. supports t2v, i2v, long video generation with multi-prompt sliding windows, and lora adapters.

1. calling the api

install the client

the client provides a convenient way to interact with the api.

bash

1pip install inferencesh

setup your api key

set INFERENCE_API_KEY as an environment variable. get your key from settings → api keys.

bash

1export INFERENCE_API_KEY="inf_your_key"

run and get result

submit a request and wait for the final result. best for batch processing or when you don't need progress updates.

python

1from inferencesh import inference23client = inference()456result = client.run({7        "app": "infsh/ltx-video-2",8        "input": {}9    })1011print(result["output"])

stream live updates

get real-time progress updates as the task runs. ideal for showing progress bars, partial results, or long-running tasks.

python

1from inferencesh import inference23client = inference()456# stream=True yields updates as they arrive7for update in client.run({8        "app": "infsh/ltx-video-2",9        "input": {}10    }, stream=True):11    if update.get("progress"):12        print(f"progress: {update['progress']}%")13    if update.get("output"):14        print(f"output: {update['output']}")

2. authentication

the api uses api keys for authentication. see the authentication docs for detailed setup instructions.

3. files

file inputs are automatically handled by the sdk. you can pass local paths, urls, or base64 data.

automatic upload

the python sdk automatically detects local file paths and uploads them. urls are passed through as-is.

python

1# local file paths are automatically uploaded2result = client.run({3    "app": "infsh/ltx-video-2",4    "input": {5        "image": "/path/to/local/image.png",  # detected & uploaded6        "audio": "https://example.com/audio.mp3",  # url passed through7    }8})

manual upload

you can also upload files manually and use the returned url.

python

1# upload and get a hosted URL2file = client.files.upload("/path/to/file.png")3print(file.uri)  # https://cloud.inference.sh/...

4. webhooks

get notified when a task completes by providing a webhook url. when the task reaches a terminal state (completed, failed, or cancelled), a POST request is sent to your url with the task result.

python

1result = client.run({2    "app": "infsh/ltx-video-2",3    "input": {},4    "webhook": "https://your-server.com/webhook"5}, wait=False)

webhook payload

your endpoint receives a JSON POST with the task result:

json

1{2  "id": "task_abc123",3  "status": 9,4  "output": { ... },5  "error": "",6  "session_id": null,7  "created_at": "2024-01-15T10:30:00Z",8  "updated_at": "2024-01-15T10:30:05Z"9}

idstring— task id

statusnumber— terminal status (9=completed, 10=failed, 11=cancelled)

outputobject— task output (when completed)

errorstring— error message (when failed)

session_idstring— session id (if using sessions)

created_atstring— iso timestamp

updated_atstring— iso timestamp

5. schema

input

frame_ratenumber

frame rate for the output video

default: 24

guidance_scalenumber

scale for classifier-free guidance. use 1.0 for distilled models.

default: 4

heightinteger

height of the output video frames

default: 512

lorasarray

list of lora adapters to apply

negative_promptstring

negative prompt to specify undesired features

default: "shaky, glitchy, low quality, worst quality, deformed, distorted, disfigured, motion smear, motion artifacts, fused fingers, bad anatomy, weird hand, ugly, transition, static."

num_framesinteger

number of frames to generate. max ~20 seconds duration (e.g. 481 frames at 24fps, 1001 at 50fps). default 121 (~5 seconds at 24fps).

default: 121

num_inference_stepsinteger

number of denoising steps. use 8 for distilled models.

default: 40

promptstring*

text prompt to guide video generation. for long videos, use '|' to separate prompts for different segments (e.g. 'scene 1|scene 2|scene 3')

seedinteger

random seed for reproducibility. if not provided, a random seed is used.

start_framestring(file)

optional start frame image for image-to-video (i2v) generation. when provided, the i2v pipeline is used instead of t2v.

widthinteger

width of the output video frames

default: 768

output

output_metaobject*

usage metadata for pricing

videostring(file)*

video

ready to run ltx-video-2?

try in browser browse all tools

we use cookies

we use cookies to ensure you get the best experience on our website. for more information on how we use cookies, please see our cookie policy.

by clicking "accept", you agree to our use of cookies.
learn more.