Skip to main content

LightricksZ.aiVideo model matchup

LTX-2 19Bvs.CogVideoX1.5-5B I2V

CogVideoX1.5-5B I2V has no LMArena rating yet.

Text to videoLMArena rating
1,156

LTX-2 19B

Place 21 of 23

n/a

CogVideoX1.5-5B I2V

Image to videoLMArena rating
1,161

LTX-2 19B

Place 19 of 20

n/a

CogVideoX1.5-5B I2V

Longest clipSeconds per request
n/a

LTX-2 19B

6 s

CogVideoX1.5-5B I2V

Test videos

The first clip from a single request each, showing the first five seconds.

What to look for: Anatomy, object consistency, camera tracking, rain, and reflections. Sound muted, as the test protocol requires.

LTX-2 19B

Run details

fal.ai. fal-ai/ltx-2-19b/text-to-video. 16:9, one request, first output, requested 5 s, seed 1843750023, request {"prompt":"Generate exactly one continuous five-second 16:9 cinematic video. A fictional bicycle courier in a mustard-yellow raincoat rides a red city bicycle from left to right across a rain-wet Hamburg street at blue hour for the entire clip. The camera tracks her smoothly at waist height. Both hands remain visible on the handlebars, the bicycle geometry stays physically correct, and a transparent umbrella fixed to the bicycle moves naturally in the wind. Wet-street reflections and raindrops follow realistic physics. No cuts, no slow motion, no text, no logos, no subtitles, and no audio.","video_size":"landscape_16_9","num_frames":121,"fps":24,"generate_audio":false,"use_multiscale":true,"camera_lora":"none","acceleration":"regular","guidance_scale":3,"num_inference_steps":40,"enable_prompt_expansion":false,"enable_safety_checker":true,"video_output_type":"X264 (.mp4)","video_quality":"high","video_write_mode":"balanced"}, configured price estimate $0.25.

Generated Aug 24, 2026. Source

CogVideoX1.5-5B I2V

No clip: this task has not yet been tested for the model.

Show the prompt given to both models

Generate exactly one continuous five-second 16:9 cinematic video. A fictional bicycle courier in a mustard-yellow raincoat rides a red city bicycle from left to right across a rain-wet Hamburg street at blue hour for the entire clip. The camera tracks her smoothly at waist height. Both hands remain visible on the handlebars, the bicycle geometry stays physically correct, and a transparent umbrella fixed to the bicycle moves naturally in the wind. Wet-street reflections and raindrops follow realistic physics. No cuts, no slow motion, no text, no logos, no subtitles, and no audio.

Where is the difference?

Text to videoNo rating for CogVideoX1.5-5B I2V
Image to videoNo rating for CogVideoX1.5-5B I2V
Longest clipNo clip length for LTX-2 19B

Bar length shows the gap: for ratings full width from 60 points, for price from four times as much, for clip length from 20 seconds. Solid means clearly ahead, hatched slightly ahead, a thin grey bar level.

All data side by side

The better value is bold. For ratings only when the gap is clear.

MetricLTX-2 19BCogVideoX1.5-5B I2V
Performance
Text to videoLMArena rating1,156Place 21 of 23n/a
Image to videoLMArena rating1,161Place 19 of 20n/a
Output
Resolutionn/aup to 1360 px on the long side; short side at least 768 px
Longest clipn/a6 s
Soundgenerated by the modelyesn/a
Access
Weightsopenopen
Parameters19B5B
RoutesAPI, web, locallocal
ReleasedOctober 2025November 2024
Statusavailableavailable

Prices: public API price of the documented standard configuration; resolution and sound can change it

LTX-2 19B and CogVideoX1.5-5B I2V in the field

Every video model of our comparison with a rating, both models of this matchup highlighted.

Text to video

Rating from anonymous comparisons in the LMArena · higher is better

Gemini Omni 1.1 Flash1,513
Gemini Omni Flash1,509
FLUX.3 Video1,491
Grok Imagine Video 1.51,488
Dreamina Seedance 2.0 720p1,483
Dreamina Seedance 2.5 720p1,479
Muse Video1,457
MiniMax H31,456
Sora 2 Pro1,367
Veo 3.11,363
Veo 3.1 Fast1,361
Sora 21,342
Grok Imagine Video1,341
Wan 2.71,337
Wan 2.61,324
PixVerse V5.61,238
Runway Gen-4.51,223
Kling 2.6 Pro1,216
Hailuo 2.31,205
HunyuanVideo 1.51,168
LTX-2 19B1,156
Wan 2.2 A14B1,132
Pika 2.21,009

As of November 9, 2026 · Source: LMArena

Image to video

Rating from anonymous comparisons in the LMArena · higher is better

Dreamina Seedance 2.5 720p1,494
MiniMax H31,493
Gemini Omni 1.1 Flash1,487
Dreamina Seedance 2.0 720p1,480
Gemini Omni Flash1,463
Grok Imagine Video 1.51,453
FLUX.3 Video1,451
Wan 2.71,427
Grok Imagine Video1,411
Veo 3.11,399
Veo 3.1 Fast1,386
Vidu Q3 Pro1,363
Kling 3.0 Pro1,353
Wan 2.61,309
PixVerse V5.61,299
Kling 2.6 Pro1,294
Hailuo 2.31,263
HunyuanVideo 1.51,199
LTX-2 19B1,161
Pika 2.2998

As of November 9, 2026 · Source: LMArena

Is there a better choice?

Successor of LTX-2 19BLTX-2.3Documentation
Best model for text to videoFLUX.3 Video

Text to video 1,491, Place 3 of 23. $0.85 per 5 s clip.

LTX-2 19B vs. FLUX.3 Video

Sources and method

Show 4 sources and the method

Ratings come from the LMArena: people see two videos for the same prompt without knowing which model made them and pick the better one. Many such picks add up to a rating, higher is better. Text to video and image to video are separate lists and are never added together.

“Ahead” means one model stays clearly higher even with the rating’s uncertainty. “Slightly ahead” means its value is higher but the gap is not certain yet. Otherwise both count as level. Places count only the models of our comparison.

Prices and clip lengths come from the providers’ documentation. From a factor of 1.25 a model counts as cheaper or longer, below that as about the same.

More comparisons

Compare LTX-2 19B and CogVideoX1.5-5B I2V with the models people compare them with most often.

Compare another matchup