KI-Video-Generator

Erstellen Sie Videos aus Textprompts oder erwecken Sie Ihre Bilder zum Leben. Mit den neuesten KI-Videomodellen wie Wan, Kling, Veo, Sora und mehr.

Text‑zu‑Video KI‑Generator

Please select a model to see the form.

Neueste Ergebnisse

Example Videos

See what you can create - Sign in to start generating your own videos

16:9
Example #1

The sun rises slowly between tall buildings. [Ground-level follow shot] Bicycle tires roll over a dew-covered street at dawn. The cyclist passes through dappled light under a bridge as the entire city gradually wakes up.

16:9
Example #2

A skier glides over fresh snow, kicking up large clouds of snow as he turns. Accelerating gradually down the slope, the camera moves smoothly alongside.

16:9
Example #3

A bright blue race car speeds along a snowy racetrack. [Low-angle shot] Captures several cars speeding along the racetrack through a harsh snowstorm. [Overhead shot] The camera gradually pulls upward, revealing the full race scene illuminated by storm lights.

Processing time varies by model (typically 15 seconds - 5 minutes)

AI VIDEO MODELS

Jedes KI-Video-Generator-Modell im Vergleich

Wan für Geschwindigkeit, Kling für Charakterbewegung, Veo und Sora für filmische Realität — vergleichen Sie die Spezifikationen und wählen Sie die richtige Engine für die Aufnahme.

Wan

Wan Models

by Alibaba
Wan 2.7
Wan 2.7
New
Hot
Pro
Latest Wan 2.7 with cinematic motion, first & last frame control, and up to 1080p
NEW
1080p
15s
3-5min
200 credits
Up to 15s
premium
Wan 2.6
Wan 2.6
New
Pro
Latest Wan 2.6 with multi-shot narrative support and up to 15s duration
Multi-Shot
15s
1080p
3-5min
200 credits
Up to 15s
premium
Wan 2.5
Wan 2.5
New
Wan 2.5 video model with built-in audio generation
Audio
2min
100 credits
Up to 10s
free
Wan 2.2 Turbo
Wan 2.2 Turbo
New
Ultra-fast Wan 2.2 Turbo video generation model with 2x faster processing
Turbo
15s
25 credits
Up to 8s
free
Wan 2.2 Fast
Wan 2.2 Fast
New
Hot
Ultra-fast text-to-video generation model with optimized pricing
Fast
Budget
15s
5 credits
Up to 5s
free
Wan 2.2 Lite
Wan 2.2 Lite
New
Fast and efficient Wan 2.2 Lite video generation model
Lite
1min
80 credits
Up to 5s
free
Wan 2.2
Wan 2.2
High-quality Wan 2.2 video generation model
Premium
2min
90 credits
Up to 8s
free
Happy Horse 1.1
Happy Horse 1.1
New
Hot
Pro
Cinematic text-to-video by Alibaba with smooth camera movement, expressive motion, and strong prompt fidelity — now with a more affordable 1080p tier
1.1
Alibaba
1080p
2-5min
280 credits
Up to 15s
premium
Happy Horse 1.0
Happy Horse 1.0
New
Hot
Pro
Cinematic text-to-video by Alibaba with smooth camera movement, expressive motion, and strong prompt fidelity
1.0
Alibaba
1080p
2-5min
280 credits
Up to 15s
premium
Seedance

Seedance Models

by ByteDance
Seedance 2.5
Seedance 2.5
New
Hot
Pro
Next-gen Seedance with native 30-second single-shot video, synchronized audio and end-frame control
2.5
30s
Audio
2-6min
360 credits
Up to 30s
premium
Seedance 2.0 Mini
Seedance 2.0 Mini
New
Hot
Pro
Budget-friendly Seedance 2.0 with native audio, end-frame control and a unique 4K tier — the most affordable way to get cinematic 2.0 output
2.0
Mini
Audio
1-3min
120 credits
Up to 15s
premium
Seedance 2.0
Seedance 2.0
New
Hot
Pro
Hollywood-grade cinematic video with native audio, end-frame control, and director-level prompting
2.0
Cinematic
Audio
2-5min
240 credits
Up to 15s
premium
Seedance 2.0 Fast
Seedance 2.0 Fast
New
Hot
Pro
Speed-optimized cinematic video with native audio and end-frame control, ~33% cheaper than standard
2.0
Fast
Audio
1-3min
200 credits
Up to 15s
premium
Seedance 1.5 Pro
Seedance 1.5 Pro
New
Pro
Generate high-quality videos with audio using Seedance 1.5 Pro
1.5 Pro
Audio
End Frame
1-3min
25 credits
Up to 12s
premium
Seedance 1.5 Pro Fast
Seedance 1.5 Pro Fast
New
Hot
Pro
Fast version of Seedance 1.5 Pro with quicker generation and lower cost
1.5 Pro
Fast
Audio
30s-2min
40 credits
Up to 12s
premium
Seedance 1.0 Lite
Seedance 1.0 Lite
New
Pro
High-quality text-to-video and image-to-video generation with flexible duration options
Lite
End Frame
1-3min
35 credits
Up to 12s
premium
Seedance 1.0 Pro
Seedance 1.0 Pro
New
Pro
Premium text-to-video and image-to-video generation with superior 1080p quality
Pro
1080p
2-5min
60 credits
Up to 12s
premium
Seedance 1.0 Pro Fast
Seedance 1.0 Pro Fast
New
Pro
Fast and cost-effective text-to-video and image-to-video generation with maximum performance
Fast
Budget
30s-2min
20 credits
Up to 12s
premium
Kling

Kling Models

by Kuaishou
Kling 3.0 Pro
Kling 3.0 Pro
New
Hot
Pro
Premium text/image-to-video with cinematic visuals, fluid motion, native audio, and multi-shot support
3.0
Pro
Audio
4-6min
225 credits
Up to 15s
premium
Kling 3.0 Standard
Kling 3.0 Standard
New
Hot
Top-tier text/image-to-video with cinematic visuals, fluid motion, native audio, and multi-shot support
3.0
Audio
Multi-Shot
3-5min
170 credits
Up to 15s
free
Kling O3 Pro
Kling O3 Pro
New
Hot
Pro
Premium O3 model with text/image-to-video, native audio, and extended 15-second duration
O3
Pro
Audio
4-6min
225 credits
Up to 15s
premium
Kling 2.6 Pro
Kling 2.6 Pro
New
Hot
Pro
Top-tier cinematic video generation with native audio support
Cinematic
Audio
5-7min
300 credits
Up to 10s
premium
Kling 2.5 Turbo Pro
Kling 2.5 Turbo Pro
New
Hot
Pro
Top-tier text and image-to-video generation delivering cinematic motion and precise prompt control
Turbo
4K
4-6min
150 credits
Up to 10s
premium
Kling 2.1 Master
Kling 2.1 Master
New
Hot
Pro
Ultimate text/image-to-video model delivering cinematic quality and exceptional motion synthesis
Master
Ultra HD
5-7min
550 credits
Up to 10s
premium
Hailuo

Hailuo Models

by MiniMax
MiniMax H3
MiniMax H3
New
Hot
Pro
MiniMax's frontier video model with native 2K/4K output and first-to-last keyframe control
H3
2K
4K
2-5min
160 credits
Up to 15s
premium
Hailuo-2.3 Standard
Hailuo-2.3 Standard
New
Hot
Advanced video generation with 768p resolution (Text-to-Video & Image-to-Video)
New
768p
Dual-Mode
1min
144 credits
Up to 10s
free
Hailuo-2.3 Pro
Hailuo-2.3 Pro
New
Hot
Pro
Premium quality video generation at 1080p resolution (Text-to-Video & Image-to-Video)
Pro
1080p
Premium Quality
2min
240 credits
Up to 10s
premium
Veo

Veo Models

by Google
Veo 3.1 Fast
Veo 3.1 Fast
New
Hot
Pro
Google's latest Veo 3.1 with fast generation speed and enhanced quality
Fast
Audio
1080p
1-3 minutes
480 credits
Up to 8s
premium
Veo 3.1
Veo 3.1
New
Hot
Pro
Google DeepMind's flagship Veo 3.1 model with premium quality and audio
Best Quality
Audio
1080p
3-5 minutes
1280 credits
Up to 8s
premium
Gemini Omni Flash
Gemini Omni Flash
New
Hot
Pro
Google's fast Gemini Omni Flash model with synchronized audio generation
Fast
Audio
New
1-2 minutes
416 credits
Up to 10s
premium
Sora

Sora Models

by OpenAI
Sora 2 Standard
Sora 2 Standard
New
Hot
Pro
OpenAI's Sora 2 text-to-video model with audio generation (Standard 720p)
OpenAI
Sora 2
Audio
3-5min
200 credits
Up to 12s
premium
Sora 2 Pro
Sora 2 Pro
New
Hot
Pro
OpenAI's Sora 2 text-to-video model with audio generation (Pro 1080p)
OpenAI
Sora 2 Pro
Audio
5-10min
600 credits
Up to 12s
premium
Flux

Flux Models

by Black Forest Labs
Flux 3
Flux 3
New
Hot
Pro
Black Forest Labs' frontier video model with cinematic motion and native audio, up to 20s in 1080p
NEW
Audio
20s
3-6min
340 credits
Up to 20s
premium
Grok

Grok Models

by xAI
Grok Video 1.5 T2V
Grok Video 1.5 T2V
New
Hot
Pro
Generate videos with audio from text using xAI's Grok Imagine Video 1.5 model
xAI
Grok 1.5
Audio
2-4min
192 credits
Up to 15s
premium
Grok Video T2V
Grok Video T2V
New
Hot
Pro
Generate videos with audio from text using xAI's Grok Imagine Video model
xAI
Grok
Audio
2-4min
120 credits
Up to 15s
premium
LTX

LTX Models

by Lightricks
LTX Video 2.0 Fast
LTX Video 2.0 Fast
New
Hot
Pro
Dual-mode video generation with audio support, up to 20s
Lightricks
Audio
Up to 20s
1-3min
96 credits
Up to 20s
premium
LTX Video 2.0 Pro
LTX Video 2.0 Pro
New
Pro
High-fidelity dual-mode video generation with audio support
Lightricks
Audio
Pro Quality
3-5min
144 credits
Up to 10s
premium

AI VIDEO PROVIDERS

Unterstützt von den Laboren, die KI-Video definieren

Alibaba, Kuaishou, Google DeepMind, OpenAI, MiniMax und ByteDance — führende Text-zu-Video und Bild-zu-Video Modelle, vereint in einem Tool.

Alibaba

Wan

by Alibaba

9 models

ByteDance

Seedance

by ByteDance

9 models

Kuaishou

Kling

by Kuaishou

6 models

MiniMax

Hailuo

by MiniMax

3 models

Google

Veo

by Google

3 models

OpenAI

Sora

by OpenAI

2 models

xAI

Grok

by xAI

2 models

Lightricks

LTX

by Lightricks

2 models

Alibaba

Wan

by Alibaba

9 models

ByteDance

Seedance

by ByteDance

9 models

Kuaishou

Kling

by Kuaishou

6 models

MiniMax

Hailuo

by MiniMax

3 models

Google

Veo

by Google

3 models

OpenAI

Sora

by OpenAI

2 models

xAI

Grok

by xAI

2 models

Lightricks

LTX

by Lightricks

2 models

Alibaba

Wan

by Alibaba

9 models

ByteDance

Seedance

by ByteDance

9 models

Kuaishou

Kling

by Kuaishou

6 models

MiniMax

Hailuo

by MiniMax

3 models

Google

Veo

by Google

3 models

OpenAI

Sora

by OpenAI

2 models

xAI

Grok

by xAI

2 models

Lightricks

LTX

by Lightricks

2 models

Alibaba

Wan

by Alibaba

9 models

ByteDance

Seedance

by ByteDance

9 models

Kuaishou

Kling

by Kuaishou

6 models

MiniMax

Hailuo

by MiniMax

3 models

Google

Veo

by Google

3 models

OpenAI

Sora

by OpenAI

2 models

xAI

Grok

by xAI

2 models

Lightricks

LTX

by Lightricks

2 models

SPEC SHEET

Jedes Modell, spezifiziert wie eine Kamera

Was jedes Modell am besten kann, wie schnell es entwickelt und welche Modi es unterstützt — damit du das richtige Werkzeug für den Frame wählst.

MODELBEST FORSPEEDMODES
WanFast turbo generation, everyday text-to-video and image-to-video~30ST2V · I2V
KlingSmooth character motion and expressive performances~2MINT2V · I2V
VeoCinematic realism and complex camera moves~3MINT2V · I2V
SoraLong coherent shots with strong scene understanding~3MINT2V · I2V
HailuoStylized motion and dynamic action shots~2MINT2V · I2V
SeedanceFast iterations with reliable prompt following~1MINT2V · I2V

FEATURES

Von einem Satz oder einem einzelnen Foto zum fertigen Video

Text-zu-Video und Bild-zu-Video KI, kostenlos ausprobieren — die meisten Aufnahmen sind in ein bis drei Minuten fertig.

Über 30 Text‑zu‑Video‑KI‑Modelle

Greifen Sie auf die weltweit führenden Text‑zu‑Video‑KI‑Modelle auf einer Plattform zu. Von Wan Turbo mit 15‑sekündiger Generierung bis zu Veo mit kinoreifem 1080p‑Output – unser Generator lässt Sie das perfekte Modell für jedes Projekt wählen, allein durch einen einfachen Textprompt.

Ultraschnelle Text‑zu‑Video‑KI

Erleben Sie blitzschnelle Text‑zu‑Video‑Generierung mit Turbo‑Modellen. Wan Fast liefert Ergebnisse in nur 15 Sekunden, während Seedance Pro Fast Premium‑Qualität bei doppelter Geschwindigkeit bietet. Unsere Technologie verwandelt Ihre Ideen schneller denn je in Videos.

KI‑Videos mit nativer Tonspur

Erstellen Sie vollständige Produktionen mit synchronisiertem Audio. Veo 3.1, Sora 2 und LTX 2.0 generieren automatisch passende Soundtracks – kein separates Audiobearbeiten nötig. Unsere Text‑zu‑Video‑KI liefert sendefertige Inhalte aus reinem Text.

HOW TO

Wie Sie KI-Videos aus Text oder Bildern generieren

1

Beschreiben Sie die Bewegung oder laden Sie ein Foto hoch

Beschreiben Sie die Szene und die Kamerabewegung für Text-zu-Video, oder wechseln Sie den Tab und laden Sie ein Bild hoch, das animiert werden soll. Bewegungsverben wie 'Schwenk', 'langsamer Zoom' geben der KI-Video-Generierung klare Anweisungen.

2

Wählen Sie ein Modell und die Dauer

Wan ist der schnellste Weg zu einem kostenlosen KI-Video; Kling glänzt bei Personen; Veo und Sora liefern filmische Realität. Legen Sie das Seitenverhältnis und die Dauer fest und generieren Sie.

3

Herunterladen und anpassen

Videos landen in Meine Kreationen mit ihrem Prompt und den Einstellungen. Laden Sie sie in HD herunter oder passen Sie den Prompt an und generieren Sie erneut — Credits werden nur für das verbraucht, was Sie generieren.

FAQ

KI-Video-Generator FAQ

Generieren Sie Ihr erstes KI-Video kostenlos

Kostenlose Credits bei der Anmeldung — verwandeln Sie einen Satz oder ein Foto in Minuten in ein Video.

Tägliche Gratis‑Credits • 30+ KI‑Modelle • Keine Wasserzeichen