Question 1

Does LTX 2.3 really generate audio with the video?

Accepted Answer

Yes. LTX-2 is a joint audio-visual foundation model, and this chute has generate_audio: true by default, so the returned MP4 includes a synchronized soundtrack. Lightricks notes audio without speech can be lower quality. Set generate_audio: false for silent output.

Question 2

Can I change the number of inference steps or use CFG like the full model?

Accepted Answer

No. This deployment runs the distilled-1.1 checkpoint, which is trained for exactly 8 steps at CFG=1; the endpoint silently overrides any num_inference_steps you send. You can still tune guidance_scale (default 3.1, range 1.0-5.1 per the chute readme).

Question 3

How does keyframe interpolation work?

Accepted Answer

Pass a keyframes array of 2 or more entries, each with a base64 image and a frame index (optionally strength and crf); at least one must have frame index 0. The model generates coherent motion through the anchors. keyframes takes precedence over input_image_b64.

Question 4

What resolutions and durations are supported?

Accepted Answer

Width and height snap to multiples of 64, from 256x256 up to 3840x2160. Duration caps scale with resolution: roughly 20 seconds at 480p-1080p, 10 seconds at 1440p, and 5 seconds at 4K width. Frame counts snap to Nx8+1 and fps runs 8-50 (default 24).

Question 5

How do I call the API?

Accepted Answer

POST a flat JSON body to https://vonkaiser-ltx-23-video.chutes.ai/generate with Authorization: Bearer $CHUTES_API_KEY. Only prompt is required. The response is raw video bytes (mp4 by default, webm optional); set return_json: true to get JSON instead.

Question 6

Can I use the output commercially?

Accepted Answer

The weights are under the LTX-2 Community License Agreement, not a standard OSI license. Review the license at github.com/Lightricks/LTX-2/blob/main/LICENSE for the permitted-use terms that apply to your case.

Question 7

What does enhance_prompt do and should I use it?

Accepted Answer

It expands your prompt on-GPU with Llama 3.2 3B Instruct before generation, and for I2V/keyframe jobs also captions the first image with Florence-2 so the rewrite matches your input. It is off by default and adds 1-3 seconds. Use it for terse prompts; skip it when you have already written a detailed prompt.

Question 8

Why did my 1920x1080 request come back as 1920x1088?

Accepted Answer

The chute snaps dimensions to multiples of 64, so 1080 rounds to 1088. Either accept the snap or request dimensions that are already multiples of 64.

LTX 23 Video

Sign in to use the playground

LTX 23 Video

Sign in to use the playground