-
Notifications
You must be signed in to change notification settings - Fork 0
Provider Ltx
Mode: video · Models: 8
Vendor: Lightricks LTX · Official API docs: docs.ltx.video
LTX 2.3 (by Lightricks) is a video model with synchronized native audio, first-to-last frame image control, and resolutions up to 4K. The Pro flagship handles text-to-video, image-to-video, audio-to-video, retake, and extend; the Fast variant trades fidelity for speed and longer clips.
| id | Name | Input type |
|---|---|---|
ltx-v2.3-pro |
LTX 2.3 Pro | t2v |
ltx-v2.3-fast |
LTX 2.3 Fast | t2v |
ltx-2.3-a2v |
LTX 2.3 Audio-to-Video | a2v |
ltx-v2.3-extend |
LTX 2.3 Extend | v2v |
ltx-v2.3-retake |
LTX 2.3 Retake | v2v |
ltx-pro-t2v |
LTX Pro | t2v |
ltx-v2-fast |
LTX Fast | t2v |
ltx-v2-retake |
LTX Retake | v2v |
# text-to-video with native audio
gen-ai generate -m ltx-v2.3-pro \
-p "aerial shot over a misty forest at dawn, slow push-in, ambient birdsong" \
--ar 16:9 -r 1080p -d 8 --audio-gen
# image-to-video: animate a start frame
gen-ai generate -m ltx-v2.3-pro -p "the camera drifts forward as fog rolls in" -i ./still.jpg
# audio-driven generation
gen-ai generate -m ltx-2.3-a2v -p "a singer performing on a neon stage" -a ./vocals.mp3
# extend an existing clip
gen-ai generate -m ltx-v2.3-extend -p "the scene continues into night" --video ./clip.mp4{ "name": "picsart_generate",
"arguments": {
"model": "ltx-v2.3-pro",
"prompt": "aerial shot over a misty forest at dawn, slow push-in",
"aspectRatio": "16:9",
"resolution": "1080p",
"duration": 8,
"generateAudio": true
} }Full parameter surface for every model, sourced from gen-ai models info <id> --json. CLI flags show the primary short form; the canonical --kebab-case long form always works too.
Try ltx-v2.3-pro in Playground ↗
Input type: t2v
| Param | CLI flag | Type | Values |
|---|---|---|---|
prompt |
-p |
text | required |
duration |
-d |
enum |
6 · 8 · 10 (default 6) |
resolution |
-r |
enum |
1080p · 1440p · 2160p (default 1080p) |
aspectRatio |
--ar |
enum |
16:9 · 9:16 (default 16:9) |
generateAudio |
--audio-gen |
boolean |
true · false (default true) |
imageUrls |
-i |
file | image (up to 1) |
Try ltx-v2.3-fast in Playground ↗
Input type: t2v
| Param | CLI flag | Type | Values |
|---|---|---|---|
prompt |
-p |
text | required |
duration |
-d |
enum |
6 · 8 · 10 · 12 · 14 · 16 · 18 · 20 (default 6) |
resolution |
-r |
enum |
1080p · 1440p · 2160p (default 1080p) |
aspectRatio |
--ar |
enum |
16:9 · 9:16 (default 16:9) |
generateAudio |
--audio-gen |
boolean |
true · false (default true) |
imageUrls |
-i |
file | image (up to 1) |
Try ltx-2.3-a2v in Playground ↗
Input type: a2v
| Param | CLI flag | Type | Values |
|---|---|---|---|
prompt |
-p |
text | free text |
audioUrl |
-a |
file | required audio |
imageUrls |
-i |
file | image (up to 1) |
cfgScale |
--cfg |
number |
1–50, default 5
|
Try ltx-v2.3-extend in Playground ↗
Input type: v2v
| Param | CLI flag | Type | Values |
|---|---|---|---|
prompt |
-p |
text | free text |
duration |
-d |
enum |
5 · 10 · 15 · 20 (default 5) |
videoUrl |
--video |
file | required video |
Try ltx-v2.3-retake in Playground ↗
Input type: v2v
| Param | CLI flag | Type | Values |
|---|---|---|---|
prompt |
-p |
text | required |
duration |
-d |
enum |
5 · 10 · 15 · 20 (default 5) |
videoUrl |
--video |
file | required video |
Try ltx-pro-t2v in Playground ↗
Input type: t2v
| Param | CLI flag | Type | Values |
|---|---|---|---|
prompt |
-p |
text | required |
duration |
-d |
enum |
6 · 8 · 10 (default 6) |
resolution |
-r |
enum |
1080p · 1440p · 2160p (default 1080p) |
generateAudio |
--audio-gen |
boolean |
true · false (default true) |
imageUrls |
-i |
file | image (up to 1) |
Try ltx-v2-fast in Playground ↗
Input type: t2v
| Param | CLI flag | Type | Values |
|---|---|---|---|
prompt |
-p |
text | required |
duration |
-d |
enum |
6 · 8 · 10 · 12 · 14 · 16 · 18 · 20 (default 6) |
resolution |
-r |
enum |
1080p · 1440p · 2160p (default 1080p) |
generateAudio |
--audio-gen |
boolean |
true · false (default true) |
imageUrls |
-i |
file | image (up to 1) |
Try ltx-v2-retake in Playground ↗
Input type: v2v
| Param | CLI flag | Type | Values |
|---|---|---|---|
prompt |
-p |
text | required |
duration |
-d |
enum |
5 · 10 · 15 · 20 (default 5) |
videoUrl |
--video |
file | required video |
Notes: A2V / extend / retake are Pro-only and take audio/video inputs; the Fast variant adds longer durations at 1080p.
gen-ai pricing ltx-v2.3-pro -d 8 -r 1080pCost scales with duration, resolution, and audio.
Picsart CLI & MCP · Repo · AI Playground app
Getting Started
Interfaces
Concepts
Model Reference
Providers
- All providers
- Async
- ByteDance
- Creatify
- ElevenLabs
- Flux (Black Forest Labs)
- Grok (xAI)
- Happy Horse
- HeyGen
- Hunyuan
- Ideogram
- Kling
- LTX (Lightricks)
- Luma
- MiniMax
- OpenAI
- OVI
- Picsart
- Pika
- PixVerse
- Qwen (Alibaba)
- Recraft
- Reve
- Runway
- Seedance
- Seedream
- Topaz
- VEED
- Videography
- Wan (Alibaba)
More