For kontoer uten tidligere kjøp: kjøringer over 2 credits trenger påfyll.
Ny her?
10 gratis credits (0,10 USD) når du registrerer deg med Google
Kan brukes 24 timer etter registrering, opptil 5 kjøringer per dag og maksimalt 2 credits per kjøring. Andre påloggingsmetoder starter uten credits.
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 dog riding a skateboard
Lengde: 0:05
Settings
aspect_ratio
16:9
duration
5
Eksempelprompts
Eksempler fra Railwail-katalogen. De ble ikke generert live på denne siden.
Nature Scene
Lengde: 0:08
Aerial drone shot slowly rising above a misty old-growth forest at dawn, revealing a winding river cutting through the valley below, golden sunlight breaking through clouds
Cinematic Portrait
Lengde: 0:05
Close-up of a woman's face as she opens her eyes and looks into the camera, shallow depth of field, soft golden backlight, hair gently moving in the breeze, cinematic 24fps
03
Om Google Veo 2
Kort sagtPer 23. september 2026
Google Veo 2 er en modell fra Google DeepMind i kategorien Videogenerering. På Railwail koster Google Veo 2 0,60 USD per videosekund. En standardkjøring på 8 sekunder koster 4,80 USD. Støttede bildeformat: 16:9 og 9:16. Mulige lengder: 5, 6, 7 eller 8 s. Nyere versjon: Google Veo 3.1.
Bakgrunn
Om Google DeepMind
Grunnlagt 2010 · London, United Kingdom
Google DeepMind is the merged AI research organisation formed in April 2023 when Google Brain and DeepMind (acquired by Google in 2014) were combined into a single unit led by Demis Hassabis (CEO). DeepMind was founded in 2010 by Hassabis, Shane Legg and Mustafa Suleyman, and is famous for AlphaGo, AlphaFold and the Gemini language-model family. On the video side, DeepMind shipped Imagen Video (2022), Lumiere (2024), Veo (May 2024, Google I/O), Veo 2 (December 2024), Veo 3 with native audio (May 2025) and Veo 3.1 (late 2025). Veo is exposed via Vertex AI, the Gemini API, Google Labs (VideoFX, Whisk) and YouTube's Dream Screen.
Latent video diffusion / Diffusion Transformer hybrid with cascaded super-resolution
Veo 2 is a closed text-to-video and image-to-video model that builds on DeepMind's Imagen and Lumiere research. It uses a spatio-temporal latent diffusion architecture with a transformer-based denoiser conditioned on rich text embeddings from Gemini-family encoders and optional image embeddings. Veo 2 generates clips up to 8 seconds at up to 4K resolution (extended versions reach minutes), with strong understanding of camera language ('dolly', 'aerial', '35mm anamorphic') and real-world physics. DeepMind report substantial gains over Veo 1 on motion realism, prompt adherence and detail. The pipeline combines a base diffusion model with cascaded spatial and temporal super-resolution and an upscaler. Veo 2 was trained on a curated YouTube-and-partner video corpus with synthetic captioning at multiple granularities, and post-trained with reward models for prompt adherence and aesthetic quality.
Parametere
Undisclosed
Evner
Text-to-video and image-to-video generation
Up to 8-second clips, up to 4K resolution
Rich cinematographic prompt vocabulary (lenses, lighting, camera moves)
Strong real-world physics and object permanence
Available via Vertex AI, Gemini API, VideoFX and YouTube Dream Screen
SynthID watermarking embedded in every frame
Multilingual prompts via Gemini text encoders
Lower hallucination of artefacts than Veo 1
Best for: high-quality marketing, film previs, broadcast inserts, enterprise creative.
Trening og lisens
Curated mix of licensed video, public web video (including YouTube under Google's terms) and synthetic data, with multi-granularity captioning produced by Gemini vision models. Exact dataset size undisclosed.
Lisens: Proprietary commercial licence via Google Cloud / Vertex AI and the Gemini API; commercial usage permitted under Google's generative AI terms; SynthID watermark required on all output.
Sikkerhetstesting: Subject to Google's responsible AI framework with safety filters, public-figure filters, child-safety classifiers and provenance via SynthID; covered by Google's Responsible AI Progress Reports.
Kjente begrensninger
No native audio in Veo 2 (audio first appears in Veo 3)
8-second clip limit per base generation
Closed access with gated waitlist on some surfaces
Strict moderation on people, brands and political content
Limited control over exact frame composition without seed images
curl https://railwail.com/api/v1/videos/generations \
-H "Authorization: Bearer $RAILWAIL_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "google-veo-2",
"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"
import os
import time
import requests
API = "https://railwail.com/api/v1"
headers = {"Authorization": f"Bearer {os.environ['RAILWAIL_API_KEY']}"}
job = requests.post(
f"{API}/videos/generations",
headers=headers,
json={
"model": "google-veo-2",
"prompt": "A slow drone shot over a misty pine forest at sunrise",
},
).json()
while True:
status = requests.get(f"{API}/jobs/{job['job_id']}", headers=headers).json()
if status["status"] in ("completed", "failed", "cancelled"):
break
time.sleep(5)
print(status["status"], status.get("output_url"))
const API = "https://railwail.com/api/v1";
const headers = {
Authorization: `Bearer ${process.env.RAILWAIL_API_KEY}`,
"Content-Type": "application/json",
};
const job = await fetch(`${API}/videos/generations`, {
method: "POST",
headers,
body: JSON.stringify({
model: "google-veo-2",
prompt: "A slow drone shot over a misty pine forest at sunrise"
}),
}).then((r) => r.json());
let status;
do {
await new Promise((r) => setTimeout(r, 5000));
status = await fetch(`${API}/jobs/${job.job_id}`, { headers }).then((r) => r.json());
} while (!["completed", "failed", "cancelled"].includes(status.status));
console.log(status.status, status.output_url);
Proprietary commercial licence via Google Cloud / Vertex AI and the Gemini API; commercial usage permitted under Google's generative AI terms; SynthID watermark required on all output.
Katalogoppføring oppdatert
23. september 2026
Inndataparametere
Inndataer og innstillinger fra modellens inndataskjema. Eksemplet i API-delen viser hvilke av dem APIen godtar.
Google Veo 2 er en modell fra Google DeepMind i kategorien Videogenerering. På Railwail kan du kalle den med en API-nøkkel gjennom Railwail API.
Hvor mye koster Google Veo 2 på Railwail?
På Railwail koster Google Veo 2 0,60 USD per videosekund. En standardkjøring på 8 sekunder koster 4,80 USD. Prisen er kjent før kjøringen starter. Bruk betales fra forhåndskjøpte kreditter; 1 kreditt tilsvarer 0,01 USD.
Hvilke innstillinger støtter Google Veo 2?
I henhold til inndataskjemaet kjenner Google Veo 2 disse parametrene: prompt, duration (5, 6, 7 eller 8), start_image og aspect_ratio (16:9 eller 9:16).
Hvor rask er Google Veo 2?
Det finnes ennå ikke nok målte kjøringer av Google Veo 2 på Railwail til å angi en kjøretid. Det avhenger av inndataene, innstillingene og belastningen hos leverandøren.
Er Google Veo 2 bedre enn Google Veo 3.1?
Det avhenger av oppgaven. Google Veo 2 (Google DeepMind) og Google Veo 3.1 (Google DeepMind) er begge modeller i kategorien Videogenerering. Sammenligningssiden viser prisene og spesifikasjonene deres side ved side.
Opprett en Railwail API-nøkkel og send forespørselen din med modell-ID-en google-veo-2. Kodeeksempler for curl, Python og JavaScript finnes i API-delen av denne siden.
Kuaishou's Kling v2.1, generating 5 and 10 second videos at 720p or 1080p from text or an image. Known for cinematic camera work and realistic physical motion, available on Replicate via the official KwaiVGI account.
