Models · Video
AI video models in Fliki
Compare the leading text-to-video, image-to-video, and lip-sync models. Pick the right model for the shot, then generate inside Fliki.
Veo 3.1 Fast
Google DeepMind
Cinematic 1080p with native audio and dialogue
HappyHorse 1.0
Alibaba
Multi-reference 720p, up to 9 reference images
Kling 2.5 Turbo
Kuaishou
Cost-efficient 1080p for high-volume image-to-video
Kling 2.6 Pro
Kuaishou
Motion transfer — keep motion, swap the character
Kling 3.0 Pro
Kuaishou
Flagship cinematic 1080p with synchronized audio
Kling 3.0 Standard
Kuaishou
Cost-tier 720p Kling 3.0 with audio
LTX-2 Fast
Lightricks
Open-source DiT audio-video, speed tier
LTX-2.3
Lightricks
Open-source DiT audio-video, latest generation
OmniHuman 1.5
Bytedance
Photo + audio talking-head lip-sync
P-Video
PrunaAI
Image-to-video with optional lip-sync audio
PixVerse v5 Fast
PixVerse
Fast stylized short-form video
Seedance 2.0
Bytedance
Multi-shot coherence with reference-driven motion
Seedance Pro Fast
Bytedance
Speed-tier 1080p with strong motion physics