Modellix

Kling AI 模型系列

Kling is Kuaishou's AI video generation model that turns text or image prompts into high-quality, realistic, cinematic videos with strong motion and character consistency.

23 个模型更新于 2026年11月

全部 Kling 模型

kling/kling-4.0-flash-video-edit

kling/kling-4.0-flash-video-edit

视频生视频

Video editing in the Flash series for scene restyling, object changes, and reference-guided revisions. It combines source footage with image, video, or subject references to shape the resulting scene.

kling/kling-4.0-flash-i2v

kling/kling-4.0-flash-i2v

图生视频

Single-image animation for product showcases, character motion, and social video. It turns a starting image into a short clip, using the reference to guide the opening composition.

kling/kling-4.0-flash-t2v

kling/kling-4.0-flash-t2v

文生视频

Fast text-to-video generation for product previews, advertising drafts, and short social clips. It combines prompt-directed scenes and flexible framing for frequent creative iteration.

kling/kling-4.0-video-edit

kling/kling-4.0-video-edit

视频生视频

Reference-guided video editing for removing objects, restyling scenes, and revising existing footage. Image, video, and subject references help guide changes while keeping the surrounding scene and recognizable subjects consistent.

kling/kling-4.0-i2v

kling/kling-4.0-i2v

图生视频

Image-to-video generation for animating product shots, characters, and illustrated scenes. First, middle, and final keyframes guide the visual progression for planned motion and scene transitions.

kling/kling-4.0-t2v

kling/kling-4.0-t2v

文生视频

Text-to-video generation for advertising concepts, storyboards, and short narrative scenes. It combines prompt-directed composition and widescreen framing to turn scene ideas into finished clips.

kling/kling-v3-turbo-i2v

kling/kling-v3-turbo-i2v

图生视频

Kling's fast image-to-video model for turning one still into a short clip. It makes a 3 to 15 second video at 720p or 1080p.

kling/kling-v3-turbo-t2v

kling/kling-v3-turbo-t2v

文生视频

Kling's fast text-to-video model for short-form drafts and high-volume clips. It makes a 3 to 15 second clip at 720p or 1080p, in widescreen, square, or vertical frames.

kling/kling-v3-omni-i2v

kling/kling-v3-omni-i2v

图生视频

Kling's reference-to-video model for a scene that keeps subjects and style consistent, with optional native sound and automatic shot changes. It uses 1 to 7 reference images in a 3 to 15 second clip at 720p, 1080p, or 4K.

kling/kling-v3-omni-t2v

kling/kling-v3-omni-t2v

文生视频

Kling's storyboard text-to-video model for multi-beat scenes and consistent characters, with optional native sound and automatic shot changes. It makes a 3 to 15 second clip at 720p, 1080p, or 4K, in widescreen, square, or vertical frames.

kling/kling-video-o1-i2v

kling/kling-video-o1-i2v

图生视频

Kling's reasoning image-to-video model for complex motion grounded in reference frames. It uses 1 to 7 reference images in a 3 to 10 second clip at 720p or 1080p.

kling/kling-video-o1-t2v

kling/kling-video-o1-t2v

文生视频

Kling's reasoning text-to-video model for complex physical motion and scenes that have to follow the prompt closely. It makes a 3 to 10 second clip at 720p or 1080p, in widescreen, square, or vertical frames.

kling/kling-v3-omni-video

kling/kling-v3-omni-video

视频生视频

Kling's video-to-video model for restyling or changing a clip from a reference video, with optional stills and sound. It uses one reference video and up to four images in a 3 to 15 second clip at 720p, 1080p, or 4K.

kling/kling-video-o1

kling/kling-video-o1

视频生视频

Kling's reasoning video model for editing a clip from a reference video while keeping the source motion. It uses one reference video and up to four images in a 3 to 10 second clip at 720p or 1080p.

kling/kling-v3-i2v

kling/kling-v3-i2v

图生视频

Kling's image-to-video model for animating a still into a longer scene, with an optional end frame, native sound, and automatic shot changes. It makes a 3 to 15 second clip at 720p, 1080p, or 4K.

kling/kling-v3-t2v

kling/kling-v3-t2v

文生视频

Kling's text-to-video model for cinematic scenes and longer shots, with optional native sound and automatic shot changes. It makes a 3 to 15 second clip at 720p, 1080p, or 4K, in widescreen, square, or vertical frames.

kling/kling-v3-omni-image

kling/kling-v3-omni-image

图像编辑

Kling's image model for cinematic stills and a connected series, from a prompt or up to 10 reference images. It renders at 1K, 2K, or 4K, including a set of 2 to 9 related frames.

kling/kling-v3-i2i

kling/kling-v3-i2i

图像编辑

Kling's image-editing model for style changes and prompt-guided edits from one reference image. It returns up to 9 images at 1K or 2K, including vertical 9:16 and ultrawide 21:9 frames.

kling/kling-v3-t2i

kling/kling-v3-t2i

文生图

Kling's text-to-image model for concept art and photorealistic stills. It returns up to 9 images at 1K or 2K, including vertical 9:16 and ultrawide 21:9 frames.

kling/kling-video-effects

kling/kling-video-effects

图生视频

Kling's effects model for turning one or two photos into a short themed clip, such as a dance or a bullet-time shot. It applies a preset effect in a 5 or 10 second video.

kling/kling-avatar

kling/kling-avatar

图生视频

Kling's talking-avatar model for presenters and portrait performances. It lip-syncs one portrait to an audio track or a generated voice, with expression and camera direction in the prompt.

kling/kling-image-expansion

kling/kling-image-expansion

图像编辑

Kling's image expansion model for extending a cropped photo or widening its frame while the original picture stays. It can grow any side by up to twice that edge and return up to 9 variations.

kling/kling-image-o1

kling/kling-image-o1

图像编辑

Kling's reasoning image model for complex layouts and blends of reference subjects. It uses up to 10 reference images and returns up to 9 results at 1K or 2K, including vertical 9:16 and ultrawide 21:9 frames.

没有找到需要的模型? 告诉我们。

探索更多