Video
LTX-2.3 22B Distilled
Generate video and optional audio with the distilled LTX-2.3 22B route.
- Text to video
- Image to video
Sign in to create. Review the credit cost in the studio before running.
Catalog preview for LTX-2.3 22B Distilled. Review your own result before publishing.
A starting point.
Describe a continuous action, camera movement and audible events. Use the image-to-video operation when a starting image matters.
Before you publish.
Watch object continuity and listen for sound that misses the action; inspect the ending before editing.
Review the quote before running. A failed generation releases its reserved credits. Download the results you want to keep; stored media is retained for 30 days.
Settings and model questionsCheck the available settings and guidance when preparing your input.
Inputs and settings
prompt is required. Control the frame count with num_frames and include or omit generated sound with generate_audio.
Keep seed fixed while comparing enable_prompt_expansion or use_multiscale. image_strength is available only in the image operation; Raywake exposes no FPS control here.
Inputs, all modes and APIModel IDs, current input limits and the API generation workflow.
Supported inputs
These fields come from the current studio form for ltx-2.3-22b/distilled/text-to-video. Other modes may require different inputs.
| Input | Type | Requirement | Options and limits |
|---|---|---|---|
prompt | Text | Required | — |
acceleration | Text | Optional | — |
distill_lora_second_pass_scale | Number | Optional | ≥ 0 · ≤ 1 |
enable_prompt_expansion | On/off | Optional | — |
enable_safety_checker | On/off | Optional | — |
generate_audio | On/off | Optional | — |
negative_prompt | Text | Optional | — |
num_frames | Whole number | Optional | ≥ 9 · ≤ 481 |
scheduler | Text | Optional | — |
seed | Whole number | Optional | — |
use_multiscale | On/off | Optional | — |
video_output_type | Text | Optional | — |
video_write_mode | Text | Optional | — |
Check the full model schema for all options and cross-field rules. Request a quote for your selected settings before generating.
Other modes and their inputs
Open the operation you need and check its inputs. Settings from one mode do not automatically apply to another.
Image to videoltx-2.3-22b/distilled/image-to-video
Supported inputs
These fields come from the current studio form for ltx-2.3-22b/distilled/image-to-video. Other modes may require different inputs.
| Input | Type | Requirement | Options and limits |
|---|---|---|---|
image_url | Text | Required | — |
prompt | Text | Required | — |
acceleration | Text | Optional | — |
distill_lora_second_pass_scale | Number | Optional | ≥ 0 · ≤ 1 |
enable_prompt_expansion | On/off | Optional | — |
enable_safety_checker | On/off | Optional | — |
end_image_strength | Number | Optional | ≥ 0 · ≤ 1 |
generate_audio | On/off | Optional | — |
image_strength | Number | Optional | ≥ 0 · ≤ 1 |
interpolation_direction | Text | Optional | — |
negative_prompt | Text | Optional | — |
num_frames | Whole number | Optional | ≥ 9 · ≤ 481 |
scheduler | Text | Optional | — |
seed | Whole number | Optional | — |
use_multiscale | On/off | Optional | — |
video_output_type | Text | Optional | — |
video_write_mode | Text | Optional | — |
Check the full model schema for all options and cross-field rules. Request a quote for your selected settings before generating.
Use LTX-2.3 22B Distilled through the API.
Start with this model ID for the endpoint featured on this page:
ltx-2.3-22b/distilled/text-to-video
Input requirements belong to this model ID. Check a different mode’s schema separately when switching modes.
Available modes
- text-to-video ·
ltx-2.3-22b/distilled/text-to-video - image-to-video ·
ltx-2.3-22b/distilled/image-to-video
Check the current model schema for supported inputs and options. Other tasks may use different model IDs.
From quote to result.
Request a credit quote for your input and settings before submitting a generation. A sample output or the price of another model is not a quote for your request.
Follow the generation workflow, then poll the job for its status and result. The API and studio use the same balance.