LTX-2.3 22B Distilled Text-to-Video

Model Information

Display Name: LTX-2.3 22B Distilled Text-to-Video

API Model ID: lightricks/ltx-23-22b-distilled-t2v

Category: Text To Video

Description: Distilled variant of Lightricks' LTX-2.3 22B model optimized for faster text-to-video generation. Generates high-quality video from text prompts with built-in audio synthesis, camera control LoRAs, and multi-scale generation. **Key Features:** - 22B parameter distilled architecture for faster inference - Text-to-video generation with prompt expansion - Built-in audio generation - Camera control LoRAs (dolly, jib, static) - Multi-scale generation for enhanced quality - Multiple acceleration modes (none/regular/high/full) - Multiple output formats (MP4, VP9, ProRes, GIF) **Capabilities:** - Text-to-video generation - Automatic audio synthesis - Camera movement control - Negative prompt support - Prompt expansion for better results - Seed control for reproducibility **Best For:** - Fast text-to-video generation - Creative video content with camera movements - Marketing and social media videos - Video prototyping with audio - Rapid iteration with acceleration modes **Parameters:** - aspect_ratio: 16:9 (default), 9:16, 1:1, 4:3, 3:4, 3:2, 2:3, 21:9 - num_frames: frame count (default 121) - fps: frames per second (default 24) - camera_lora: dolly_in/out, dolly_left/right, jib_up/down, static, none - generate_audio: true/false (default true) - acceleration: none, regular, high, full - video_quality: low, medium, high, maximum **Pricing:** - Per video megapixel (width x height x frames) - Distilled model is more cost-effective than standard - Example: 1280x720, 121 frames ≈ /bin/bash.19

How to Use This Model

To use LTX-2.3 22B Distilled Text-to-Video via the HInow.ai API, use the model ID: lightricks/ltx-23-22b-distilled-t2v

API Request Example (Chat/Text)


POST https://api.hinow.ai/v1/chat/completions
Authorization: Bearer YOUR_API_KEY
Content-Type: application/json

{
  "model": "lightricks/ltx-23-22b-distilled-t2v",
  "messages": [
    {"role": "user", "content": "Your message here"}
  ]
}
              

Pricing

  • total: $0.19

Available Parameters

  • aspect_ratio: Output video aspect ratio (Options: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 21:9)
  • num_frames: Number of frames (more frames = longer video) (Options: 61, 81, 97, 121, 161)
  • fps: Frames per second (Options: 16, 24, 30)
  • generate_audio: Generate synchronized audio (Options: true, false)
  • negative_prompt: What to avoid in the video
  • seed: Random seed for reproducibility
  • camera_lora: Camera movement preset (Options: none, pan_left, pan_right, tilt_up, tilt_down, zoom_in, zoom_out, orbit_left, orbit_right)
  • video_quality: Output video quality (Options: low, medium, high)

Quick Reference

To use this model, set: "model": "lightricks/ltx-23-22b-distilled-t2v"

Featured: No

Documentation: https://hinow.ai/models/lightricks/ltx-23-22b-distilled-t2v

API Endpoint: https://api.hinow.ai/v1

Back to Models

LTX-2.3 22B Distilled Text-to-Video

lightricks/ltx-23-22b-distilled-t2v

$0.190
per image

About

Distilled variant of Lightricks' LTX-2.3 22B model optimized for faster text-to-video generation. Generates high-quality video from text prompts with built-in audio synthesis, camera control LoRAs, and multi-scale generation.

Key Features:

  • 22B parameter distilled architecture for faster inference
  • Text-to-video generation with prompt expansion
  • Built-in audio generation
  • Camera control LoRAs (dolly, jib, static)
  • Multi-scale generation for enhanced quality
  • Multiple acceleration modes (none/regular/high/full)
  • Multiple output formats (MP4, VP9, ProRes, GIF)

Capabilities:

  • Text-to-video generation
  • Automatic audio synthesis
  • Camera movement control
  • Negative prompt support
  • Prompt expansion for better results
  • Seed control for reproducibility

Best For:

  • Fast text-to-video generation
  • Creative video content with camera movements
  • Marketing and social media videos
  • Video prototyping with audio
  • Rapid iteration with acceleration modes

Parameters:

  • aspect_ratio: 16:9 (default), 9:16, 1:1, 4:3, 3:4, 3:2, 2:3, 21:9
  • num_frames: frame count (default 121)
  • fps: frames per second (default 24)
  • camera_lora: dolly_in/out, dolly_left/right, jib_up/down, static, none
  • generate_audio: true/false (default true)
  • acceleration: none, regular, high, full
  • video_quality: low, medium, high, maximum

Pricing:

  • Per video megapixel (width x height x frames)
  • Distilled model is more cost-effective than standard
  • Example: 1280x720, 121 frames ≈ /bin/bash.19

Capabilities

Text To Video

Parameters

aspect_ratio

Output video aspect ratio

1:116:99:164:33:43:22:321:9
num_frames

Number of frames (more frames = longer video)

618197121161
fps

Frames per second

162430
generate_audio

Generate synchronized audio

truefalse
negative_prompt

What to avoid in the video

seed

Random seed for reproducibility

camera_lora

Camera movement preset

nonepan_leftpan_righttilt_uptilt_downzoom_inzoom_outorbit_leftorbit_right
video_quality

Output video quality

lowmediumhigh

Code Examples

curl -X POST https://api.hinow.ai/v1/videos \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $HINOW_API_KEY" \
  -d '{
    "model": "lightricks/ltx-23-22b-distilled-t2v",
    "prompt": "A cat playing with a ball",
    "parameters": {
      "aspect_ratio": "1:1",
      "num_frames": "61",
      "fps": "16",
      "generate_audio": "true",
      "negative_prompt": "",
      "seed": "",
      "camera_lora": "none",
      "video_quality": "low"
    }
  }'