Models › LTX-2

LTX-2 19B, image-to-video

fal-ai/ltx-2-19b/image-to-video

1 framenative audioopen weights576×1024 portrait

price$0.0018

wait p50 / max47s / 1:46

checks all green6 of 9

lines heard50%

refused0

spent here$2.92

The price floor, and it shows on anything with dialogue or fast motion. Its portrait_16_9 preset delivers 576×1024, not the 768×1344 the name implies.

Everything it rendered

9 inputs, 11 takes. Click any one for the full request and its measurements.

Character serial, block 1 $0.45 · 84s lines 1/4 · synth voice · motion 0.49

Character serial, block 2 $0.45 · 1:46 lines 1/3 · synth voice · motion 0.73

One face, one line $0.22 · 24s lines 1/1 · motion 2.13

Two people, two lines $0.22 · 39s lines 2/2 · motion 1.12

Legible text on a sign $0.22 · 47s motion 3.33

Product on a turntable $0.22 · 51s motion 0.82

Fast camera, fast subject $0.22 · 40s motion 6.14

Stylised animation $0.22 · 55s · 3 replicates motion 10.96

The same fox, a different scene $0.22 · 45s motion 3.52

Repeatability

The same input sent again, more than once. The number is the spread of motion across replicates over its mean — lower is steadier.

Input	Replicates	Motion CV	Detail
Stylised animation	3	0.773	3 replicates · motion 10.96 / 11.79 / 0.86

Identity across calls

Character	Mean similarity	Appearances	Detail
The baker	0.961	2	2 calls compared to their own centroid · 10/10 sampled frames passed the fidelity gate
serial-flyer	—	0	the entity was not found in any sampled frame — no score possible
The paper fox	0.941	2	2 calls compared to their own centroid · 9/10 sampled frames passed the fidelity gate

How every model compared →

fal page Artificial Analysis Arena