LTX 2.3 Trainer (V2) - Masked Video-to-Video

Name: LTX 2.3 Trainer (V2) - Masked Video-to-Video
Author: fal

other

Train a LoRA that regenerates only the masked region of a video, guided by both the kept pixels and a separate reference/control video.

Capabilities

Show unsupported (8)

No supported capabilities recorded.

Model IDfal-ai/ltx23-trainer-v2/v2v-masked

Providerfal

Creatorfal

Family—

License—

Statusactive

Typeother

Input modalities—

Output modalities—

Open weight—

Parameters—

Architecture—

Context window—

Max input—

Max output—

Reasoning tokens—

Knowledge cutoff—

Release date2026-06-17

Sourceofficial

GET/v1/models/fal/fal-ai/ltx23-trainer-v2/v2v-masked

fal-ai/ltx23-trainer-v2/v2v-masked

Train a LoRA that regenerates only the masked region of a video, guided by both the kept pixels and a separate reference/control video.

Changes · 4 entries

fal-ai/ltx23-trainer-v2/v2v-maskedcreateca7a400Nov 2, 2026, 03:02 AM

fal-ai/ltx23-trainer-v2/v2v-maskedupdate20c73acJul 17, 2026, 02:34 AM

last_seen_at2026-06-22→2026-07-13

fal-ai/ltx23-trainer-v2/v2v-maskedupdate88d97e5Jun 30, 2026, 04:49 AM

last_seen_at2026-06-17→2026-06-22

fal-ai/ltx23-trainer-v2/v2v-maskedcreateab879c8Jun 18, 2026, 08:32 AM