AI video models
Hedra strives to support every state-of-the-art video model — and is constantly adding new ones as they become available.
Hedra
Hedra AvatarHedra's latest longform avatar model, audio to video will full multi-language support. Perfect for talking and singing video with speaker selection up to 10 minutes long.Hedra Character 3Hedra's latest longform avatar model, audio to video will full multi-language support. Perfect for talking and singing video with speaker selection up to 10 minutes long.
Alibaba
Happy HorseOpen-weight video generation from a first frame.Wan 2.7Wan 2.7 video with native audio — from a text prompt, from a first frame with an optional last frame, or from reference images that keep subjects consistentWan 3.0Wan 3.0 video with native audio, up to 30 seconds in one shot — from a text prompt, from a first frame with an optional last frame, or from reference images that keep subjects consistent
Black Forest Labs
ByteDance
Omnihuman 1.5Creates vivid, emotional character videos driven entirely by your audio.Seedance 1.5 ProKeyframe-driven video with native audio, from a start frame, an end frame, or both.Seedance 2.0Reference-driven video up to 4K with native audio — hold a look across shots with reference images, clips, or audio.Seedance 2.0 MiniThe lightest Seedance tier — short reference-driven clips at 480p and 720p.Seedance 2.5Reference-driven video up to 30 seconds at 1080p, with native audio.
Gemini Omni FlashGemini's fast multimodal video model — cinematic clips with native audio from a prompt, a keyframe, or reference images.Veo 2Create smooth 5–8s motion from a single keyframe.Veo 3Hollywood-grade, cinematic video straight from text—your go-to for hero campaigns.Veo 3.1For unparalleled detail and nuance, perfect for when your vision requires the best possible quality.
Kling
Kling 1.6Kling 2.1 MasterCinema-grade video with striking textures and rich depth.Kling 2.5 TurboFast, high-quality video generation.Kling 2.6 Motion ControlTransfer movements from a reference video to any character image. Cost-effective mode for motion transfer, perfect for portraits and simple animations.Kling 2.6 ProCinematic visuals, fluid motion, and native audio generation.Kling AI Avatar v2Create avatar videos with realistic humans, animals, cartoons, or stylized characters from an image and audio input.Kling O1Generate from a single image with text-driven style and scene guidance.Kling O3Animate a start frame.Kling O3 EditEdit videos using natural language.Kling O3 ReferenceInput a reference video and preserve motion and camera style.Kling V3Animate a start frame.Kling V3 Motion ControlAnimate a character image to match the motion of a reference video. Standard tier for cost-effective generation.
Lightricks
Luma AI
MiniMax
OpenAI
PixVerse
Topaz Labs
Topaz Hyperion 2.5 HDRConvert SDR video to 10-bit HDR with richer highlights, color, and tonal separation. The output keeps the source resolution.Topaz ProteusPrecision upscaling that cleans compression and noise while staying faithful to the source.Topaz Starlight FastFaster generative diffusion upscaling at half the cost of Starlight Precise.Topaz Starlight HQGenerative diffusion upscaling balancing detail and sharpness for medium-to-high quality sources.Topaz Starlight PreciseGenerative diffusion upscaling for AI-generated and archival video with realistic faces, textures, and text.