image-to-video AI Models

🤖 Model 📝 → 🎥

shridharathi/ghibli-vid

Generate Studio Ghibli–style anime videos from a text prompt. Optionally animate a starting image into a short clip (17–...

📝 → 🎥 • text-to-video • image-to-video • anime • 111 runs

🤖 Model 🖼️ → 🎥

atonamy/images-to-webm-p

Convert sequential image frames into WebM (VP9) video or animated WebP loops. Accept a sequence of PNG/WebP frames or a...

🖼️ → 🎥 • image-to-video • sticker-generation • animated-webp • 34 runs

🤖 Model 🖼️ → 🎥

lucataco/ugc-ad

Generate UGC-style advertisement videos from a single input image and a short user description. Edit and enhance the ima...

🖼️ → 🎥 • image-to-video • ugc-ads • 5 runs

🤖 Model 🖼️ → 🎥

wyhsirius/lia

Animate a still image using the motion from a driving video, producing a new video of the source subject moving like the...

🖼️ → 🎥 • image-to-video • motion-transfer • 21.5K runs

🤖 Model 🖼️ → 🎥

lucataco/magic-animate

Animate a person in a still image using the motion from a driving video, producing a temporally consistent video. Transf...

🖼️ → 🎥 • image-to-video • video-consistent-character-generation • 56.4K runs

🤖 Model 🖼️ → 🎥

yoyo-nb/thin-plate-spline-motion-model

Animate a still image using the motion from a driving video. Provide a source image and a driving video; the model trans...

🖼️ → 🎥 • image-to-video • image-animation • motion-transfer • 590.8K runs

🤖 Model 🖼️ → 🎥

okaris/live-portrait

Animate a single image into a talking-head video by transferring motion from a driving video. Accept a source image or s...

🖼️ → 🎥 • image-to-video • video-to-video • face-animation • 164.4K runs

🤖 Model 🖼️ → 🎥

erbridge/vhs-degrade

Transform images into videos with a vintage VHS tape effect, optionally adding atmospheric background music.

🖼️ → 🎥 • image-to-video • vhs-effect • video-generation • 13 runs

🤖 Model 🖼️ → 🎥

pipeline-examples/maude

Generates video from an image input, utilizing dependencies such as text extraction and audio diarization for enhanced m...

🖼️ → 🎥 • image-to-video • text-extraction • audio-diarization • 1 runs

🤖 Model 🖼️ → 🎥

runwayml/gen4-turbo

Generate short videos from a text prompt and a reference image. Extend the input image into a 5s or 10s 720p clip with r...

🖼️ → 🎥 • image-to-video • video-consistent-character-generation • 35.6K runs

🤖 Model 🖼️ → 🎥

paullux/framepack-runner

Animate a single image into a short video using a motion-focused text prompt. Accepts one image and a motion description...

🖼️ → 🎥 • image-to-video • image-animation • 97 runs

🤖 Model 🖼️ → 🎥

sunfjun/stable-video-diffusion

Generates short videos from a single input image using Stable Video Diffusion. Supports two video lengths: 14 frames wit...

🖼️ → 🎥 • image-to-video • 103.8K runs

🤖 Model 📝 → 🎥

deforum-art/deforum-stable-diffusion

Generate animated videos from text prompts, optionally using an init image or a source video. Control 2D and 3D camera m...

📝 → 🎥 • text-to-video • image-to-video • video-to-video • 73.7K runs

🤖 Model 🖼️ → 🎥

christophy/stable-video-diffusion

Generates videos from input images using Stable Video Diffusion. Converts a single image into a 14-frame or 25-frame vid...

🖼️ → 🎥 • image-to-video • 31.6K runs

🤖 Model 🖼️ → 🎥

aicapcut/stable-video-diffusion-img2vid-xt-optimized

Animate a single image into a short video clip. Accepts one image as input and outputs a video, with controls for width,...

🖼️ → 🎥 • image-to-video • img2vid • stable-video-diffusion • 12.6K runs

🤖 Model 🖼️ → 🎥

pollinations/3d-photo-inpainting

Convert a single RGB-D input image into a 3D photo using context-aware layered depth inpainting. Generate multi-layer re...

🖼️ → 🎥 • 3d-photography • depth-inpainting • image-to-video • 6.1K runs

🤖 Model 🖼️ → 🎥

zf-kbot/live-portrait

Animate a single image using a driving video to produce a talking-head video with audio. Provide a portrait image and a...

🖼️ → 🎥 • image-to-video-with-audio • face-reenactment • 39.6K runs

🤖 Model 🖼️ → 🎥

fofr/live-portrait

Animate a face photo using a driving video to produce an animated portrait video. Accepts a face image and a driving vid...

🖼️ → 🎥 • image-to-video • portrait-animation • face-reenactment • 84.2K runs

🤖 Model 🖼️ → 🎥

lucataco/talking-avatar

Generate talking avatars by combining an input image of a person and an audio file for lip synchronization. The model in...

🖼️ → 🎥 • talking-avatar • lip-sync • video-generation • 291 runs

🤖 Model 🖼️ → 🎥

camenduru/aniportrait-vid2vid

Generate photorealistic portrait animations from a reference image and source video, driven by audio input. This model s...

🖼️ → 🎥 • video-generation • audio-driven-animation • portrait-animation • 4.4K runs