Start free

Video modelsAI video generators

Seedance 2.0, Kling 3.0, Veo 3.1 and 58 more: every video model on Leap, with what it is for, what it starts from and what a run costs. They all run in the same studio, and you can start free.

Generators

  • Veo 3.1 FastGoogleGoogle's fast video model, with dialogue, effects and music in sync.Words or a first frame$0.44 to $1.32
  • Veo 3.1GoogleGoogle's highest-quality video model, with sound.Words or a first frame$0.88 to $3.52
  • Veo 3.1 LiteGoogleThe lowest-cost Veo, for drafts and volume.Words or a first frame$0.132 to $0.704
  • Kling 3.0KuaishouCinematic motion and strong physics, from text or a first frame.Words, a first frame or a last frame$0.924 to $1.848
  • Kling 2.6KuaishouKling's value model: smooth motion at a low price.Words or a first frame$0.231 to $0.462
  • Wan 2.6AlibabaOpen-weight video with a soundtrack, at 720p or 1080p.Words$0.55 to $1.65
  • Seedance 1.5 ProByteDanceSharp, steady video at a very low price, with optional sound.Words, a first frame or a last frame$0.06655 to $1.2826
  • Seedance 2.5ByteDanceLifelike motion with sound made in the same take, from text or a first frame with no real person in it.Words, a first frame, a last frame or up to 4 reference images$0.5962 to $9.53205
  • Seedance 2.0ByteDanceByteDance's reliable all-rounder: lifelike motion with sound, from text or a first frame with no real person in it.Words, a first frame or a last frame$0.38995 to $4.1822
  • Seedance 2.0 FastByteDanceSeedance 2.0, faster and for less, up to 720p: quick takes with sound, from text or a first frame with no real person in it.Words, a first frame or a last frame$0.3124 to $1.342
  • Seedance 2.0 MiniByteDanceThe lowest-priced Seedance 2.0: clips with sound up to 720p, for drafts and volume, from text or a first frame with no real person in it.Words, a first frame or a last frame$0.19525 to $0.8393
  • Grok Imagine VideoxAIFast video with sound, from text or a first frame.Words or a first frame$0.275 to $0.385
  • Grok Imagine Video 1.5xAIxAI's newer video model: expressive motion with sound, up to 1080p, from text or a first frame.Words or a first frame$0.44 to $2.75
  • Grok Imagine Video 1.5 LitexAIThe light Grok Imagine 1.5: quick, very cheap clips with sound, from text or a first frame.Words or a first frame$0.11 to $1.54
  • Wan 3.0 PrimeAlibabaThe fast Wan 3.0: polished clips with dialogue, music and effects in sync, for quick iteration.Words$0.374 to $3.08
  • MiniMax H3MiniMaxMiniMax's 2K video model, with sound.Words or a first frame$0.858
  • HappyHorse 1.1AlibabaAlibaba's video model with its own sound and lip-synced speech, at 720p or 1080p, from text or a first frame.Words or a first frame$0.462 to $2.97
  • Wan 2.7 Image to VideoAlibabaWan 2.7 from a first frame to an optional last one, at 720p or 1080p. It makes its own sound to go with the clip.Words, a first frame or a last frame$0.22 to $2.475
  • Wan 3.0AlibabaAlibaba's newest video model, with sound, from text or a first frame.Words, a first frame or a last frame$0.275 to $3.30
  • FLUX.3 VideoBlack Forest LabsBlack Forest Labs' first video model, from text or a first frame.Words or a first frame$0.935 to $6.38
  • H3 Maxfalfal's tune of MiniMax H3, for closer prompt following and a better look.Words, a first frame or a last frame$0.275 to $2.64
  • H3 Max TurbofalThe faster H3 Max, at half the price.Words, a first frame or a last frame$0.1375 to $1.32
  • Gemini Omni Flash 1.1GoogleGoogle's fast video model, from 360p to 4K.Words, a first frame or a last frame$0.099 to $3.30
  • Gemini Omni Flash 1.1 ReferenceGoogleGemini Omni Flash from up to ten reference images: the people, products and places in them, in a new shot, from 360p to 4K.Words or up to 10 reference images$0.099 to $3.30
  • Kling 2.5 Turbo ProKuaishouKling's fast model with fluid motion, from text or a first frame.Words, a first frame or a last frame$0.385 to $0.77
  • Kling 3.0 4KKuaishouKling 3.0 in native 4K, with optional sound, from text or a first frame.Words, a first frame or a last frame$2.31 to $4.62
  • Kling 3.0 ProKuaishouKling 3.0 in pro mode at 1080p, with optional sound, from text or a first frame to an optional last one.Words, a first frame or a last frame$0.3696 to $2.772
  • Kling 3.0 Turbo ProKuaishouKling 3.0 at 1080p, faster, from text or a first frame.Words or a first frame$0.462 to $2.31
  • Kling O3KuaishouKling's omni video model in standard mode, from text or from a first frame to an optional last one, with optional sound.Words, a first frame or a last frame$0.2772 to $1.848
  • Kling O3 ProKuaishouAnimates a first frame, to an optional last frame, with optional sound.Words, a first frame or a last frame$0.3696 to $2.31
  • Kling O3 ReferenceKuaishouA video that keeps the people, products or style of up to four reference images, named in the prompt as @Image1 to @Image4, with an optional first and last frame and sound.Words, a first frame, a last frame or up to 4 reference images$0.2772 to $1.848
  • Hailuo 02MiniMaxMiniMax's 768p video model, from text or a first frame.Words, a first frame or a last frame$0.297 to $0.495
  • Hailuo 2.3MiniMaxMiniMax's 768p video model, 6 or 10 seconds from text or a first frame. From text it is always 16:9; from a frame, the frame's shape.Words or a first frame$0.308 to $0.616
  • Hailuo 2.3 FastMiniMaxHailuo 2.3 from a first frame, faster and for less, at 768p.Words or a first frame$0.209 to $0.352
  • Hailuo 2.3 ProMiniMaxHailuo 2.3 at 1080p, from text or a first frame, at one price per video.Words or a first frame$0.539
  • PixVerse V6PixVersePixVerse's newest model: a photo to video, with optional sound.Words or a first frame$0.0275 to $1.8975

Editing, upscaling and other tools

  • Kling 3.0 Motion ControlKuaishouMoves the character in your image the way the person in a reference video moves, and keeps the face through turns, hands and hats. Billed by the length of the reference video.Words, a photo of a person or a reference video$0.1386 a second of your video
  • Auto SubtitlefalBurns word-timed captions into a video, in the font, colors and position you choose, and returns the transcript with SRT and VTT. Billed per minute of the video.A video$0.033 a minute
  • HappyHorse Video EditAlibabaEdits a video of up to 15 seconds from a prompt and up to four reference images, keeping its motion. Keep the original sound, or let the model decide whether to make new sound. Billed by the length of the video.Words, up to 4 reference images or a video$0.616 a second of your video
  • Wan 2.7 Video EditAlibabaEdits or restyles a video of up to 10 seconds from a prompt, at 720p or 1080p. Billed by the length of the video.Words or a video$0.33 a second of your video
  • FLUX.3 Video EditBlack Forest LabsRestyles or edits a video from a prompt at 720p, at three cents a second.Words or a video$0.033 a second of your video
  • Bria Video Remove BackgroundBriaRemoves the background behind the people and objects in a video and puts a solid color in its place. Billed by the length of the video.A video$0.055 a second of your video
  • Bria Video UpscaleBriaMakes a video two or four times larger and keeps its sound. Billed by the length of the video.A video$0.154 a second of your video
  • OmniHuman 1.5ByteDanceThe person in a photo speaks, sings or raps your recording, with the face, hands and body moving to it. Billed by the length of the recording.Words, a photo of a person or a sound file$0.176 a second of your recording
  • Video Depth AnythingByteDanceA depth map of every frame of your video, steady from frame to frame, in gray or in color, for compositing and effects. Billed by the length of the video.A video$0.044 a second of your video
  • ByteDance Video UpscalerByteDanceUpscales a video to 1080p at 30 fps and cleans it up, for under a cent a second.A video$0.00792 a second of your video
  • Lucy Edit ProDecartChanges one thing in a video from a prompt (an outfit, an object, a product, the background) and keeps the rest as filmed.Words or a video$0.165 a second of your video
  • Lucy RestyleDecartRedraws a whole video in the style you describe while the motion stays as filmed, at a cent a second.Words or a video$0.011 a second of your video
  • ElevenLabs DubbingElevenLabsDubs the speech in your video into another language. Name the language by its two-letter code, such as es or ja; without one it dubs into English. Billed per started minute.A video$0.011 a second of your video
  • H3 Max Turbo ExtendfalContinues your video by 5, 10 or 15 seconds from a prompt that says what happens next, and returns the whole video with its new ending.Words or a video$0.1375 to $2.64
  • Gemini Omni Flash 1.1 EditGoogleEdits a video from a plain instruction and keeps the rest of the scene, from 360p to 4K. Billed by the length of the video.Words or a video$0.11 a second of your video
  • MMAudio V2HKUSTAdds a soundtrack to a silent video: sound effects and ambience in time with what happens on screen, from a prompt. The result is the start of your video, as many seconds as you ask for (up to 30), with the new sound.Words or a video$0.0011 to $0.033
  • Kling 2.6 Motion ControlKuaishouMoves the character in your image the way the person in a reference video moves: dance, gestures, expressions. Billed by the length of the reference video.Words, a photo of a person or a reference video$0.077 a second of your video
  • Kling AI Avatar 2 ProKuaishouThe person in a photo says or sings your recording, lip-synced, with natural head and face motion. Billed by the length of the recording.Words, a photo of a person or a sound file$0.1265 a second of your recording
  • Kling O1 Video EditKuaishouEdits a video from a prompt, with up to four reference images: swap a product, a garment or a character and keep the shot. Takes videos at least 720 pixels wide.Words, up to 4 reference images or a video$0.1386 a second of your video
  • Kling O3 Video EditKuaishouEdits a video from a prompt, with up to four reference images: swap a product, a garment or a character and keep the shot. Takes videos of 3 to 15 seconds and 720 to 3,840 pixels. Billed by the length of the video.Words, up to 4 reference images or a video$0.1386 a second of your video
  • LTX 2.3 ReframeLightricksReframes a video to 1:1, 4:5, 5:4, 9:16 or 16:9 and fills the new edges to match the scene. Billed by the length of the video.A video$0.22 a second of your video
  • Luma Ray 3.2 ReframeLuma AIReframes a video of up to 10 seconds to a new aspect ratio and paints in what the wider frame shows, from a prompt. Billed by the length of the video.Words or a video$0.066 a second of your video
  • InfiniteTalkMeiGenA talking video at 480p from a photo and your text, as long as the line: up to about 8 seconds. A run takes about 5 to 10 minutes.Words, words or a first frame$11.00 per 1,000 characters
  • H3 Max RecastMiniMaxRecasts the people in a video from up to four photos, one per person, left to right, keeping the motion, camera, cuts and sound. Billed by the length of the video.Words, up to 4 reference images or a video$0.495 a second of your video
  • sync-3 LipsyncSync LabsLip-syncs a video of a person to new speech, keeping the face and the shot as filmed. Billed by the length of the video.A video or a sound file$0.146666668 a second of your video