Video Generation Models

Luma Reframe Video is a model that changes video aspect ratios using guided prompts and positioning controls, outputting 720p videos suitable for social media platforms.

Frames to Video Merger converts ZIP archives of image frames into ordered MP4 videos with adjustable playback speed.

twha Video Generation Model generates short videos (1-5 seconds) from textual prompts and optional starting images, with adjustable quality and stylistic controls.

Leonardo AI Motion 2.0 generates 5-second videos from text prompts with customizable styles and smooth transitions.

Enhance video quality with KEEP, leveraging Kalman-Inspired Feature Propagation for superior Face Super-Resolution. Restore, enhance, and upscale video faces effectively.

Kling Lip Sync adds synchronized lip movements to existing videos using either audio input or text-to-speech synthesis.

Stable Diffusion Dance generates dynamic video sequences or image frames that react to audio input, creating rhythmic visualizations synchronized to sound using Stable Diffusion.

VACE-14B Video Generation is a model for generating and editing videos using text prompts, input videos, masks, and reference images with customizable parameters.

Lightricks LTX Video Generation is a model for generating smooth, videos in real time using text prompts or input images, with granular control over video properties.

FramePack Video Diffusion is a model that generates videos progressively from an initial image using text prompts, implementing non-F1 FramePack video diffusion with efficient memory management.

PixVerse V3.5 Video Generation generates videos from text prompts and input images with customizable resolution, duration, motion effects, and artistic styles.

PixVerse Video Generator is a model that generates short AI videos from text or image inputs, with options for resolution, duration, and motion effects.

FramePack Runner generates short videos from a static image and text description of motion using FramePack architecture.

Kling V2.0 is a text-to-video model that generates short 720p videos from text prompts, with customization options for content control and duration.

Topaz Labs Video Upscale is a AI model for upscaling video resolution and increasing frame rates.

Nicolas Coutureau Video Utils processes input videos or images to perform specified tasks such as creating preview videos or converting formats, with customizable frame rate settings.

GIF Upscaler is a model that upscales animated GIFs to high-resolution MP4 videos by processing individual frames while preserving original timing.

Sonic Talking Face Animation generates animated portrait videos synchronized with input audio by analyzing global audio perception for natural facial movements.

Glass Face Video Generator generates videos with a glass face effect using text prompts, an initial image, and configurable parameters for style and generation control.

shridharathi/van-gogh-vid transforms videos into Van Gogh-style artistic animations using text prompts or starting images.

Ghibli Video Generation is a model for generating videos in Studio Ghibli anime style using text prompts and image inputs with customizable parameters.