LTX-Video (Lightricks)

MyndbandasmíðTiltækt
eftir LightricksAuðkenni módels: ltx-video-lightricks

Lightricks' 2B DiT video model. Realtime generation on consumer GPUs (~6s @ H100, 24fps).

Verð
≈ 0,0229 USD/keyrsla
Inntak → úttak
Texti + Mynd → Myndbandi
Þróunaraðili
Lightricks
Uppfært
23. september 2026
01

Leiksvæði

Prófaðu LTX-Video (Lightricks)

Inntak og úttak

≈ 0,0229 USD/keyrsla
Prófaðu LTX-Video (Lightricks)
Niðurstaða
Myndbandið þitt birtist hér.

Þessi keyrsla

um 0,0229 USD · 2,29 inneign

0,0685 USD (6,85 inneign) eru fráteknar við upphaf; raunverulegur GPU-tími er innheimtaður.

Fyrir reikninga án kaupa: keyrslur yfir 2 inneign þurfa áfyllingu.

Nýr hér?

10 ókeypis inneign (0,10 USD) þegar þú skráir þig með Google

Hægt að nota 24 klst. eftir skráningu, allt að 5 keyrslur á dag og að hámarki 2 inneign á keyrslu. Aðrar innskráningaraðferðir byrja án inneignar.

02

Examples

Real outputs from the public examples of this model on Replicate, with the prompt and settings that produced them. They were not generated live on this page.
  • Prompt

    A woman with long brown hair and light skin smiles at another woman with long blonde hair. The woman with brown hair wears a black jacket and has a small, barely noticeable mole on her right cheek. The camera angle is a close-up, focused on the woman with brown hair's face. The lighting is warm and natural, likely from the setting sun, casting a soft glow on the scene. The scene appears to be real-life footage.

    Lengd: 0:04

    Settings

    negative_prompt: low quality, worst quality, deformed, distorted, watermark

    aspect_ratio
    16:9
    length
    97
  • InputInput

    Prompt

    A man in a blue plaid shirt turns his head to look at a woman walking past in a red top. His expression is curious as he glances away from his companion in a light blue sleeveless top. The scene takes place on a busy city street with buildings and pedestrians visible in the background. The natural lighting suggests it's daytime. The camera captures the scene from street level, with the woman in red slightly out of focus in the foreground.

    Lengd: 0:04

    Settings

    negative_prompt: low quality, worst quality, deformed, distorted, watermark

    aspect_ratio
    16:9
    length
    97
  • Prompt

    A chef prepares food in a professional kitchen. He has olive skin and dark, close-cropped hair, wearing traditional white chef's attire. Steam rises from the pan he's working with. The kitchen's stainless steel surfaces reflect the bright overhead lighting. The camera follows his hands as he cooks. The scene appears to be real-life footage.

    Lengd: 0:04

    Settings

    negative_prompt: low quality, worst quality, deformed, distorted, watermark

    aspect_ratio
    16:9
    length
    97
03

Um LTX-Video (Lightricks)

StuttlegaFrá og með 23. september 2026

LTX-Video (Lightricks) er módel frá Lightricks í flokknum Myndbandasmíð. Á Railwail kostar LTX-Video (Lightricks) ≈ 0,0229 USD fyrir hverja keyrslu.

Bakgrunnur

Um Lightricks

Stofnað 2013 · Jerusalem, Israel

Lightricks was founded in 2013 by Zeev Farbman (CEO), Yaron Inger, Itai Tsiddon, Nir Pochter and Amit Goldstein, spinning out of Hebrew University of Jerusalem's computer-graphics research group. The company is best known for the consumer photo and video apps Facetune, Videoleap, Photoleap and Filtertune, which together have hundreds of millions of installs. Lightricks raised more than $300M from Insight Partners, Goldman Sachs and others, at a $1.8B valuation. In November 2024 Lightricks open-sourced LTX-Video, a 2B-parameter real-time video diffusion model optimized for speed on consumer hardware. LTX-Video positioned the company as one of the few Western players shipping open-weight video AI, and is now embedded in the Videoleap and LTX Studio products.

Heimsækja Lightricks

Arkitektúr

Diffusion Transformer (DiT) at 2B parameters with heavy spatial-temporal compression

LTX-Video is a 2B-parameter Diffusion Transformer designed for real-time-ish inference: at launch it generated 5-second 768x512 videos in under 4 seconds on a single H100, and 30-frame clips faster than real time. The architecture compresses video aggressively into a 1:192 spatio-temporal latent (vs the 1:48 typical of HunyuanVideo) using a heavy 3D causal VAE; the DiT denoiser then operates on this very compact latent grid. Position information uses 3D RoPE, and the model is trained with Flow Matching using v-prediction. Text conditioning combines a CLIP-style encoder and a Llama-class LLM encoder. LTX-Video supports text-to-video and image-to-video, with a 'mid-conditioning' mode that allows inserting an intermediate frame for guided motion. The model is published under an open licence designed to enable both research and commercial use.

Breytur
2 billion

Geta

  • Real-time-class generation: ~5s clip in ~4s on H100 at 768x512
  • Open-weight 2B-parameter DiT model
  • Text-to-video and image-to-video
  • Mid-frame conditioning for guided motion
  • Aggressive spatial-temporal compression (1:192 latent)
  • Runs on a single 24-48 GB consumer GPU with optimisations
  • Apache-style permissive licence on weights
  • Active community ecosystem on Hugging Face and ComfyUI
  • Best for: interactive creative tools, on-device pipelines, prototyping.

Þjálfun og leyfi

Curated multi-million-clip dataset filtered for aesthetics, motion and caption alignment, with dense captions produced by a vision-language model.

Leyfi: Open weights under a permissive licence (research and commercial use with attribution).

Öryggispróf: Data-level filtering and recommended NSFW classifier for deployment; no formal RSP.

Þekkt takmörk

  • Resolution capped at 768x512 in the base model
  • Short native duration (~5s)
  • No audio
  • Aggressive compression can cause loss of fine detail and text
  • Smaller parameter count than Mochi / Hunyuan limits absolute quality
04

Verðlagning

Verð í Bandaríkjadölum. Notkun er rukkuð frá fyrirframgreiddum inneign.
Dæmigerð keyrsla (≈ 19 s á L40S)0,0229 USD fyrir hverja keyrslu
GPU-tími (L40S)0,00117 USD fyrir hverja GPU-sekúndu
  • Reikningsfærðir eru GPU-tíminn sem keyrslan tekur í raun. Þegar keyrslan hefst er 3× dæmigerðu verðinu frátekin frá inneign þinni og jöfnuð síðar.
  • 1 inneign = 0,01 USD

Kostnaðarreiknir

Verðreiknir

s

Dæmigert samkvæmt veitanda: um 19,5 s

Samtals

2,29 USD

229 inneign

Fyrir hverja keyrslu

0,0229 USD · 2,29 inneign

Innheimt er fyrir raunverulegan GPU-tíma; þetta er mat.

05

API

Kallaðu LTX-Video (Lightricks) með Railwail API-lyklinum þínum. Notaðu þessa módel-auðkenningu í beiðninni:
ltx-video-lightricksAPI-skjölFáðu API-lykil
curl https://railwail.com/api/v1/videos/generations \
  -H "Authorization: Bearer $RAILWAIL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "ltx-video-lightricks",
    "prompt": "A slow drone shot over a misty pine forest at sunrise"
  }'

# Response: {"job_id": "...", "status": "queued", ...}
# Poll until status is completed, failed or cancelled:
curl https://railwail.com/api/v1/jobs/JOB_ID \
  -H "Authorization: Bearer $RAILWAIL_API_KEY"
Stilltu lykil þinn sem RAILWAIL_API_KEYBúa til API-lykil

Myndbönd keyra ósamstillt: fyrri kall skilar job_id; sendu fyrirspurn á /api/v1/jobs/JOB_ID þar til staðan er completed.

06

Forskriftir

Módel-auðkenni
ltx-video-lightricks
Þróunaraðili
Lightricks
Inntak
Texti, Mynd
Úttak
Myndbandi
Reikningur
Eftir notkun (tókar eða GPU-tími)
Stærð módels
2 billion
Leyfi
Open weights under a permissive licence (research and commercial use with attribution).
Vörulistafærsla uppfærð
23. september 2026

Inntaksbreytur

Inntak og stillingar úr inntakskerfi módelsins. Dæmið í API-hlutanum sýnir hverjar þeirra API samþykkir.

  • promptnauðsynlegt
    Tegund: Texti
    Sjálfgefið: –
    Leyfðir gildir: –
  • start_image
    Tegund: Mynd
    Sjálfgefið: –
    Leyfðir gildir: –

Merki

  • lightricks
  • ltx
  • text-to-video
  • open-weights
  • realtime
  • pricing-tbd
07

Notkunartilvik

Það sem það er notað fyrir

  • Real-time creative tools
  • Mobile / desktop on-device pipelines
  • Storyboarding and rapid iteration
  • Open-source research baseline
  • Image-to-video animation
  • Interactive prompting UX
08

Algengar spurningar

Hvað er LTX-Video (Lightricks)?

LTX-Video (Lightricks) er módel frá Lightricks í flokknum Myndbandasmíð. Á Railwail geturðu kallað það með API-lykli í gegnum Railwail API.

Hvað kostar LTX-Video (Lightricks) á Railwail?

Á Railwail kostar LTX-Video (Lightricks) ≈ 0,0229 USD fyrir hverja keyrslu. Þér er rukkað fyrir það sem hver beiðni notar í raun. Notkun er greidd úr fyrirframgreiddum inneign; 1 inneign jafngildir 0,01 USD.

Hvaða stillingar styður LTX-Video (Lightricks)?

Samkvæmt inntaksskema sínu þekkir LTX-Video (Lightricks) þessa færibreytu: prompt og start_image.

Hversu hratt er LTX-Video (Lightricks)?

Það eru ekki nóg mældar keyrslur af LTX-Video (Lightricks) á Railwail ennþá til að tilgreina keyrslutíma. Það fer eftir inntakinu, stillingum og álagi hjá veitandanum.

Er LTX-Video (Lightricks) betra en Google Veo 3.1?

Það fer eftir verkefninu. LTX-Video (Lightricks) (Lightricks) og Google Veo 3.1 (Google DeepMind) eru bæði módel í flokknum Myndbandasmíð. Samanburðarsíðan sýnir verð og forskriftir þeirra hlið við hlið.

Bera saman LTX-Video (Lightricks) og Google Veo 3.1

Getur LTX-Video (Lightricks) notað mynd sem inntak?

Já. Sendu myndina í færibreytuna start_image.

Hvernig nota ég LTX-Video (Lightricks) í gegnum API?

Búðu til Railwail API-lykil og sendu beiðni þína með módel-auðkenninu ltx-video-lightricks. Kóðadæmi fyrir curl, Python og JavaScript eru í API-hlutanum á þessari síðu.

09

Sambærileg módel

Öll í þessum flokki

Notaðu LTX-Video (Lightricks) í gegnum API

Einn API-lykil fyrir öll módel á Railwail. Notkun er rukkuð frá fyrirframgreiddum inneign, 1 inneign = 0,01 USD.