Discover
Video Models
Text-to-video, image-to-video, and video editing models - find the right one for your shot.
Featured first: our default picks, then the top-ranked model for each kind of job.
Do high precision video upscaling that respects the original video perfectly using Crystal Upscaler's new video upscaling method!
Luma Ray 3.2 re-renders an existing video into new cinematic motion guided by a text prompt, preserving the source's look and movement while controlling resolution, duration, and HDR.
LTX-2.3 Reframe converts your videos to any aspect ratio without destructive cropping. It intelligently recenters the original footage and generatively fills the newly exposed areas with content that seamlessly matches the scene, so the result looks like it was shot natively in the target format. Turn landscape footage into vertical 9:16 for social, square 1:1 for feeds, or anything in between. Supports videos up to 60 seconds, with 720p and 1080p outputs across 1:1, 4:5, 5:4, 9:16 and 16:9.
Heygen Translate Model with Extreme Precision
Replace or dub audio on an existing video with high-accuracy avatar-inference lip-sync.
Extend Veo-Created Videos up to 30 seconds
Generate synced sounds for any video, and return it with its new sound track (like MMAudio)
Kling O1 Omni generates new shots guided by an input reference video, preserving cinematic language such as motion, and camera style to produce seamless scene continuity.
Wan Motion is a streamlined character animation model that transfers motion from a driving video onto a reference character image. Based on Wan-Animate which preserves the original character's proportions, Simple uses pose retargeting to adapt the driving video's skeleton to match the reference character's body shape, producing more natural results when the two have different builds. It outputs at 720p with optimized defaults for fast, high-quality generation — just provide a video, an image, and an optional prompt.
VOID removes objects from videos along with all interactions they induce on the scene
SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks.
The video upscaler endpoint uses RealESRGAN on each frame of the input video to upscale the video to a higher resolution.
Interpolate videos with RIFE - Real-Time Intermediate Flow Estimation
Extend videos with xAI's Grok Imagine video model
Upscale your videos using FlashVSR with the fastest speeds!
Extend Veo-Created Videos up to 30 seconds
FLUX 3 is Black Forest Labs' frontier video model. This endpoint continues an existing clip beyond its final frame, generating additional footage that stays consistent with the original motion and scene.
Professional generative video upscaling powered by Topaz Labs. Starlight models rebuild detail that is not in the source, with Fast variants at half the price. Best for low-quality, compressed or archive footage.
Automatically remove backgrounds from videos -perfect for creating clean, professional content without a green screen.
Infinitalk model generates a talking avatar video from an image and audio file. The avatar lip-syncs to the provided audio with natural facial expressions.