Video to Video & Editing AI Models
Edit, restyle, extend and transform existing videos with an instruction, using Kling O3 and 3.0 Omni, Wan 3.0, Veo 3.1, Grok Imagine, LTX and Gemini Omni.
All Video to Video & Editing AI Models
Preview the output style, compare capabilities, then open any model for full specs, pricing, and a live Playground.
InfiniteTalk Video to Video
InfiniteTalk dubs an existing video: it re-animates lips, face and body to match new speech audio.
HeyGen Lipsync Speed
HeyGen v3 Lipsync (speed) replaces the speech in a video and re-syncs the speaker's lips to the new audio.
HeyGen Lipsync Precision
HeyGen v3 Lipsync (precision) replaces the speech in a video and re-syncs the speaker's lips to the new audio.
ByteDance DreamActor 2.0
DreamActor 2.0 by ByteDance transfers motion, facial expressions and lip movement from a driving video to the character in a reference image.
Wan 2.2 Animate Move
Wan 2.2 Animate Move animates the character in the image with the motion of the reference video.
FlashVSR
FlashVSR is a video super-resolution model that upscales videos to higher resolutions (720p / 1080p / 2K / 4K) with fast inference.
LTX 2.3 Pro Retake
Ltx 2.3 Pro Retake by Lightricks - AI-powered video editing and transformation. Apply style transfer, motion control, lip-sync, and visual effects to existing videos with natural language instructions...
LTX 2.3 Pro Video Extend
Ltx 2.3 Pro Extend by Lightricks - AI-powered video editing and transformation. Apply style transfer, motion control, lip-sync, and visual effects to existing videos with natural language instructions...
ByteDance Video Upscaler
Bytedance Video Upscaler upscales videos to 4K resolution with AI-powered enhancement. Supports multiple quality tiers (fast, standard, pro), frame rate interpolation to 60fps, and presets optimized f...
SeedVR2 Video Upscale
Seedvr Upscale Video by Bytedance - AI-powered video editing and transformation. Apply style transfer, motion control, lip-sync, and visual effects to existing videos with natural language instruction...
Wan 2.2 Animate Replace
Wan 2.2 Animate Replace replaces the person in the reference video with the character from the image.
Topaz Video Upscale
Upscale Video is Topaz Labs's video-to-video AI model. Transform, enhance, and edit video content using text prompts - from style changes to object manipulation and scene modification.
Sync 3 Lipsync
Sync 3 by sync. re-animates the speaker's lips in an existing video to match new audio, with studio-grade identity preservation.
VEED Lipsync 2.0
VEED Lipsync 2.0 makes the person in a video articulate a new audio track.
Grok Imagine Video Extend
Grok Imagine Video Extend is xAI's video-to-video AI model. Transform, enhance, and edit video content using text prompts - from style changes to object manipulation and scene modification.
Grok Imagine Video Edit
Grok Imagine Video Edit is xAI's video-to-video AI model. Transform, enhance, and edit video content using text prompts - from style changes to object manipulation and scene modification.
Veo 3.1 Fast Video Extend
Veo3.1 Fast Extend Video by Google - AI-powered video editing and transformation. Apply style transfer, motion control, lip-sync, and visual effects to existing videos with natural language instructio...
Veo 3.1 Video Extend
Veo3.1 Extend Video is Google's video-to-video AI model. Transform, enhance, and edit video content using text prompts - from style changes to object manipulation and scene modification.
Kling V3
Kling V3 by Kuaishou is a single entry point for Kling 3.0 video: text, image, reference, and video-guided generation in Standard, Pro, or 4K quality, with optional native audio.
Kling O3 Standard Video Reference
Kling O3 Standard Video Reference by Kuaishou generates a new 720p shot that follows the style and camera motion of a reference video, optionally guided by reference images.
Kling O3 Pro Video Reference
Kling O3 Pro Video Reference by Kuaishou generates a new 1080p shot that follows the style and camera motion of a reference video, optionally guided by reference images.
Kling O3 4K Video Reference
Kling O3 4K Video Reference by Kuaishou generates a new native 4K shot that follows the style and camera motion of a reference video, optionally guided by reference images.
Kling 3.0 Omni Pro Video Edit
Kling 3.0 Omni Pro Video Edit by Kuaishou edits an input video from a text instruction, optionally guided by reference images, at 1080p.
Kling O3 Standard Video Edit
Kling O3 Standard Video Edit by Kuaishou edits an input video from a text instruction, optionally guided by reference images, at 720p.
Kling O3 Pro Video Edit
Kling O3 Pro Video Edit by Kuaishou edits an input video from a text instruction, optionally guided by reference images, at 1080p.
Kling O3 4K Video Edit
Kling O3 4K Video Edit by Kuaishou edits an input video from a text instruction, optionally guided by reference images, at native 4K.
Kling O3
Kling O3 by Kuaishou is a single entry point for Kling 3.0 Omni video: text, image, reference, and video-guided generation in Standard, Pro, or 4K quality, with optional native audio.
Kling V2.6 Pro Motion Control
Kling V2.6 Pro Motion Control by Kuaishou transfers the motion, expressions, and camera movement of a reference video onto the character in an image, producing a 1080p video up to 30 seconds.
Kling V2.6 Standard Motion Control
Kling V2.6 Standard Motion Control by Kuaishou transfers the motion, expressions, and camera movement of a reference video onto the character in an image, producing a 720p video up to 30 seconds.
Kling V3 Standard Motion Control
Kling V3 Standard Motion Control by Kuaishou transfers the motion, expressions, and camera movement of a reference video onto the character in an image, producing a 720p video up to 30 seconds.
Kling V3 Pro Motion Control
Kling V3 Pro Motion Control by Kuaishou transfers the motion, expressions, and camera movement of a reference video onto the character in an image, producing a 1080p video up to 30 seconds.
Happy Horse Video Edit
Happy Horse Video Edit by Alibaba - AI-powered video editing and transformation. Apply style transfer, motion control, lip-sync, and visual effects to existing videos with natural language instruction...
Wan 2.7 Video Extend
Alibaba Wan 2.7 Video Extend continues an input clip from a text instruction, optionally ending on a chosen last frame, for a total length of up to 15 seconds.
Wan 2.7 Video Edit
Alibaba Wan 2.7 video editing model.
Gemini Omni Flash Edit
Gemini Omni Flash Edit by Google applies natural-language edits to an existing short video, such as changing style, lighting, or objects, while keeping the rest of the scene consistent.
MiniMax H3 Reference to Video
Generate native-stereo 2K video guided by image, video, and audio references with MiniMax H3.
Wan 3.0 Prime Video Extend
Wan 3.0 Prime Video Extend by Alibaba continues an input video forward from a text instruction, optionally guided by reference images and audio, with native audio.
Wan 3.0 Prime Video Edit
Wan 3.0 Prime Video Edit by Alibaba restyles or modifies an input video from a text instruction, optionally guided by reference images and audio, keeping the original length.
Wan 3.0 Prime Video
Alibaba Wan 3.0 Prime Video generates videos up to 30 seconds with native audio from text, a first/last frame, or reference images, videos, and audio.
Wan 3.0 Video Extend
Wan 3.0 Video Extend by Alibaba continues an input video forward from a text instruction, optionally guided by reference images and audio, with native audio.
Wan 3.0 Video Edit
Wan 3.0 Video Edit by Alibaba restyles or modifies an input video from a text instruction, optionally guided by reference images and audio, keeping the original length.
Wan 3.0 Video
Alibaba Wan 3.0 Video generates videos up to 30 seconds with native audio from text, a first/last frame, or reference images, videos, and audio.
Gemini Omni Flash 1.1 Edit
Gemini Omni Flash 1.1 Edit by Google applies natural-language edits to an existing video of up to ten seconds, such as changing style, lighting, or objects, at 360p to 4K output.
MiniMax H3 Max Turbo Video Extend
MiniMax H3 Max Turbo, the fastest tier of the H3 family post-trained by fal, continues an existing video with 1-15 seconds of new footage with native audio.
Gemini Omni Flash 1.2 Edit
Gemini Omni Flash 1.2 Edit by Google applies natural-language edits to an existing video of up to 15 seconds, such as swapping objects, backgrounds, lighting, or style, at 360p to 4K output.
Kling V4 Video Edit
Kling V4 Video Edit by Kuaishou edits a 3-30 second source video from a text instruction and optional reference images.
Change a video you already have
Video-to-video models take an input clip and change it: restyle the scene, replace objects, follow a reference shot, or continue the clip.
- Edit from an instruction: Kling O3 and 3.0 Omni Video Edit, Kling 4.0 Video Edit, Wan 3.0 and 2.7 Video Edit, Gemini Omni Flash Edit.
- Follow a reference shot: Kling O3 Video Reference reuses the style and camera motion of a clip.
- Extend: continue a clip with video extend endpoints such as Wan 3.0, Veo 3.1 and MiniMax H3 Max Turbo.
- Retake: LTX 2.3 Pro Retake regenerates part of a clip.
Upscaling and lip sync also take video input: see upscalers and lip sync.
Start using Video to Video & Editing AI Models on SandBase
One API key and one request shape for every model on this page.
- 01
Create an API key
Sign in to the SandBase Console and create a key on the API Keys page. Keep it in an environment variable and never commit it to source control.
TERMINALexport SANDBASE_API_KEY="YOUR_SANDBASE_API_KEY" - 02
Submit a run
Send a request to the Unified Run API with model kwaivgi/kling-video/o3/pro/edit. Only the model field changes between models on this page.
TERMINALcurl https://api.sandbase.ai/v1/run \ -H "Authorization: Bearer $SANDBASE_API_KEY" \ -H "Content-Type: application/json" \ -d '{"model": "kwaivgi/kling-video/o3/pro/edit", "prompt": "Change environment to be fully snow as @Image1. Replace animal with @Element1", "video": "https://static.sandbase.ai/examples/f2a6296e-188b-460a-9d91-c0a68096ad4d/input/6cbd685e-53b2-47f5-8076-57ab4e2684e4.mp4"}' - 03
Fetch the result
The response includes a run id. Poll it every few seconds until the status is completed, then download the output URL.
TERMINALcurl https://api.sandbase.ai/v1/run/$RUN_ID \ -H "Authorization: Bearer $SANDBASE_API_KEY"
Questions, answered
What can I change with a text instruction?
Style, environment, lighting and objects. Kling O3 Edit also accepts reference images for the new elements.
Does the output keep my clip’s length?
Edit endpoints such as Wan 3.0 Video Edit keep the original length. Extend endpoints add new footage.
What video formats work?
Pass a public HTTPS URL to an MP4 or MOV file. Each model page lists limits on length and size.
Is video editing asynchronous?
Yes. Submit to POST /v1/run and poll GET /v1/run/{id}.
Build with Video to Video & Editing AI Models.
One key, consistent APIs, and usage-based pricing across every model on this page.