Image to video

Models 48

• Gen 4 Wan
  Wan Dancer 14B

  By Alibaba

  Wan Dancer 14B is an image-to-video and audio-to-video model that generates minute-scale, coherent dance videos from a reference image, a music track, and a dance style prompt. It produces stable 720p, 30fps dance videos exceeding one minute, overcoming the roughly 20-second limit of typical diffusion video models via hierarchical global keyframe planning and local temporal refinement. It supports five dance genres: Chinese classical, K-pop, street, Latin, and tap dance.

  🎥Videos📽️Image to video🎥Audio to video🎵Music videos💃🕺Dance videos
  NewVideo

  Released 7d ago
• Gen 4 LingBot
  LingBot World 2.0

  By Robbyant

  LingBot-World 2.0 is an interactive world model that generates real-time, controllable video worlds from a single image and action inputs. It supports diverse interactive actions (attacking, archery, spell-casting, shooting), an unbounded interaction horizon via causal pretraining, and a distilled real-time variant capable of driving 720p video at 60 fps. An agentic harness of pilot and director agents plans character behavior and synthesizes new environmental content as scenes progress.

  🎥Videos📽️Image to video🎥Interactive videos🌍Game worlds
  NewVideo

  Released 8d ago
• Gen 4 Wan
  ABot World 0 5B LF

  By Alibaba

  ABot-World-0-5B-LF is a 5B parameter causal video world model finetuned from Wan2.2-TI2V-5B. It generates infinite, action-conditioned interactive video worlds from a starting image and text prompt, running in real time at 720p and 16 FPS on a single desktop GPU with 1.2 second latency and 19GB of memory usage.

  🎥Videos📽️Image to video🌎World creation🌍Game worlds
  NewVideo

  Released 8d ago
• Gen 4 LingBot
  LingBot Video Dense 1.3B

  By Robbyant

  LingBot-Video-Dense is a 1.3 billion parameter dense video generation model from the open source LingBot-Video family, built for embodied intelligence research. It supports text to image, text to video, and text and image to video generation, and is designed to connect video synthesis with physical world understanding rather than general entertainment use.

  🎥Videos🖼️Image generation📽️Image to video🤖Robotics
  NewVideo

  Released 8d ago
• Gen 4 LingBot
  LingBot Video MoE

  By Robbyant

  LingBot-Video-MoE is an open source Mixture-of-Experts video generation model with 30B total and 3B active parameters, built for embodied intelligence. It supports text-to-image, text-to-video, and image-to-video generation, plus a refiner stage for higher quality output, and is trained on web video combined with over 70,000 hours of embodied data.

  🎥Videos🖼️Image generation📽️Image to video🤖Robotics
  NewVideo

  Released 8d ago
• Research previewGen 4
  Muse Video Preview

  By Meta Platforms

  Muse Video is Meta's preview video generation model, built on the same pretraining base as Muse Image. It delivers strong prompt adherence, visual fidelity, and temporal consistency, with native audio support, and is coming soon to creators and Meta AI.

  🎥Videos🎬Video editing📽️Image to video🎥Video effects
  NewVideo

  Released 10d ago
• Gen 4
  HappyOyster 1.0

  By Alibaba

  Real-time interactive world model that generates immersive video environments from text and image prompts. Supports character controls including movement, sprinting, jumping, crouching, attacking, and object interaction. Features Adventure Mode for real-time scene exploration and Directing Mode for narrative video creation up to 3 minutes with pause-and-rewind.

  🎥Videos📽️Image to video🎥Interactive videos🎮Interactive games
  NewVideo

  Released 1mo ago
• Gen 4 Grok
  Grok Imagine Video 1.5

  By xAI

  Image-to-video generation model that produces short clips from a starting image and text prompt. Generates 6-second, 720p videos in about 25 seconds with synchronized audio including sound effects, ambience, and dialogue. Available via xAI API as grok-imagine-video-1.5 and on grok.com/imagine.

  🎥Videos📽️Image to video🎥Text to video
  NewVideo

  Released 1mo ago
• Gen 4 Seedance
  Seedance 2.0 Mini

  By ByteDance

  Seedance 2.0 Mini is ByteDance's lightweight video generation model, the lowest-cost tier in the Seedance 2.0 family. It generates short videos from text prompts and image references with support for camera direction and scene control, optimized for faster output and lower cost per generated second compared to Seedance 2.0 Fast.

  🎥Video generation📽️Image to video🎥Text to video
  NewVideo

  Released 1mo ago
• Gen 4
  P Video Replace

  By Pruna AI

  P-Video-Replace is Pruna AI’s video-replacement model for inserting referenced people into a source video while preserving realistic motion and audio.

  🎬Video editing📽️Image to video🎥Video effects
  NewVideo

  Released 1mo ago
• Gen 3
  Sulphur 2 base

  By SulphurAI

  Sulphur-2-base is SulphurAI’s uncensored video generation model based on LTX 2.3. It natively supports both text-to-video and image-to-video, and is positioned as a flexible base release that also works with other LTX 2.3 generation formats.

  🎥Videos📽️Image to video🎥Short videos
  NewMultimodal

  Released 2mo ago
• Gen 3
  HappyHorse 1.0

  By Alibaba

  HappyHorse-1.0 is a closed AI video generation model available through fal’s API and playground. It supports text-to-video, image-to-video, video editing, and reference-to-video, generates 1080p video with synchronized native audio, and is positioned as a top-ranked model on the Artificial Analysis Video Arena.

  🎥Videos📽️Image to video🔊Sound effects🎥Filmmaking
  Multimodal

  Released 3mo ago
• Gen 3 Qwen
  Wan2.7 Video

  By Alibaba

  Wan2.7-Video is Alibaba’s comprehensive video generation suite for director-style creation and editing. It includes text-to-video, image-to-video, reference-to-video, and video-editing models, and is built to support natural-language control over actions, dialogue, appearance, cinematography, and multi-shot narrative workflows.

  🎥Videos🎬Video editing📽️Image to video🎥Video extension
  Multimodal

  Released 3mo ago
• Gen 3 Wan
  Wan 2.7

  By Alibaba

  Wan 2.7 appears to be the latest generation of the Wan AI creative model line, focused on image and video generation. The current Wan site positions the platform around text-to-image, image-to-image, text-to-video, image-to-video, and image editing workflows, suggesting Wan 2.7 is aimed at general-purpose visual content creation rather than a narrow single-task model.

  🎥Videos🎬Video editing📽️Image to video🗣️Voice cloning🎤Lip sync videos
  Multimodal

  Released 3mo ago
• Gen 3 PixVerse
  PixVerse V6

  By Pixverse

  PixVerse V6 is PixVerse’s AI video generation model focused on longer, more production-ready clips. It supports 15-second 1080p generation, multi-shot storytelling, integrated audio generation, and flexible aspect ratios, aiming to move beyond short isolated clips toward more consistent narrative and marketing video workflows.

  🎥Videos📽️Image to video🎬Script to video🔊Audio
  Multimodal

  Released 3mo ago
• Gen 3 LTX
  LTX 2.3

  By Lightricks

  LTX-2.3 is a DiT-based audio-video foundation model that generates synchronized video and audio in a single model, with improved audio-visual quality and stronger prompt adherence versus LTX-2.

  🎥Text to video📽️Image to video📹Text-to-video generation
  Multimodal

  Released 4mo ago
• Gen 4
  P Video

  By Pruna AI

  P-Video is an image-to-video model that supports text, image, and audio inputs and can generate videos up to about 15 seconds with optional audio.

  📽️Image to video🎥Video enhancement🎥Video production guidance
  Video

  Released 4mo ago
• Gen 4 Reve
  Reve Image 1.5

  By Reve AI

  🖼️Image generation📽️Image to video🖌️Image editing🎨Custom image generation
  Image

  Released 4mo ago
• Gen 3 Vidu
  Vidu Q3

  By ShengShu Technology

  Vidu Q3 is ShengShu Technology’s long-form AI video model that generates a single 16-second clip with native, synchronized audio and 1080p video in one generation.

  🎥Videos📽️Image to video🎤Lip sync videos
  Multimodal

  Released 5mo ago
• Gen 3 LingBot
  LingBot World Base Cam

  By Robbyant

  LingBot World Base Cam is an open source image to video world model that generates long, real time interactive video from a starting image, text prompt, and camera pose controls. It maintains consistency across diverse environments including realistic, scientific, and cartoon styles over a minute long horizon.

  📽️Image to video📝Content creation🎥Videos🎮Interactive simulation🤖Robotics
  Video

  Released 5mo ago
• Gen 4 LingBot
  LingBot World Fast

  By Robbyant

  LingBot World Fast is an open source image to video world model that generates long, temporally consistent video from a starting image, text prompt, and camera pose signals. It supports 480P and 720P resolution and real time, low latency generation.

  📽️Image to video📝Content creation🎥Videos🤖Interactive robotics learning🎮Interactive simulation
  Video

  Released 5mo ago
• Gen 4 LingBot
  LingBot-World-Base (Act) Preview

  By Robbyant

  LingBot-World-Base (Act) is an open source world model that generates interactive videos from an image, text prompt, and action control signals. It maintains high fidelity across realistic, scientific, and cartoon environments, supports minute-level long term memory and consistency, and enables real time interactivity with under 1 second latency at 16 frames per second.

  📽️Image to video📝Content creation🎥Videos🤖Robotics
  Video

  Released 5mo ago
• Gen 3 Lucy
  Lucy 2

  By Decart AI

  Lucy 2.0 is Decart’s real-time video transformation model that generates and edits video live with near-zero latency, enabling prompt-driven scene restyling and character swaps during a continuous stream.

  🎬Video editing📽️Image to video🎥Video enhancement
  Video

  Released 5mo ago
• Gen 4 LTX
  LTX 2

  By Lightricks

  LTX-2 is Lightricks’ 19B diffusion-based audio-video foundation model that generates synchronized 4K video and stereo audio from text or images, with distilled and LoRA variants for faster local generation.

  🎥Videos🔍SEO content🎵Music📽️Image to video
  Video

  Released 6mo ago
• Gen 3
  PersonaLive

  By GVC Lab

  PersonaLive is a real-time diffusion model for expressive portrait image animation in live streaming. It is built to turn a single portrait into continuous, streamable talking-head motion driven by input video, and is specifically designed for infinite-length generation rather than short fixed clips.

  🎨Portrait animation📽️Image to video📹Live streams🎥Video avatars
  Multimodal

  Released 7mo ago
• Gen 4 Runway Gen
  Gen 4.5

  By Runway AI

  Runway Gen-4.5 is Runway's latest text-to-video and image-to-video model, ranked #1 on independent benchmarks for motion, realism and prompt adherence, delivering cinematic, physics-aware clips with fine camera, style and timing control for creators and studios.

  🎥Videos📽️Image to video
  Video

  Released 7mo ago
• Gen 4 Kling
  Kling o1

  By Kuaishou Technology

  Kling Video O1 is Kling AI’s unified multimodal video model that fuses text-to-video generation with image- and video-based editing, using advanced reasoning and motion control to create short, high-quality cinematic clips in a single workflow.

  🎥Videos🎬Video editing📽️Image to video
  Video

  Released 7mo ago
• Gen 7
  Valley3

  By ByteDance

  Valley3 is a next-generation text and image to video model that improves temporal stability, physical plausibility, and identity locking. It offers precise control of camera and pacing with in-place edits for production use.

  📽️Image to video🏗️Architectural planning🖼️Image generation
  Text

  Released 8mo ago
• Gen 4Krea
  Krea Realtime

  By Krea.ai

  Krea Realtime is a live generative image engine that updates as you type, draw, or use a camera. It is built for on-canvas ideation, quick style transfer, and interactive edits for concept art, product shots, and motion tests.

  🖼️Image generation📽️Image to video🖌️Image editing🗣️Speech training
  Video

  Released 8mo ago
• Gen 4 Vidu
  Vidu Q2

  By ShengShu Technology

  Vidu Q2 is an upgraded text and image to video model. It delivers sharper detail, steadier motion, stronger identity and style locking, and precise control over camera and pacing. It supports text to video, image to video, and in-place edits for fast iteration to production-ready clips.

  🎥Videos🎬Video editing📽️Image to video🎥Video summaries
  Video

  Released 8mo ago
• Gen 4 Nova
  Nova Reel

  By Amazon

  Nova Reel is the video model for text or image to video and in place edits. It delivers stable motion, identity and style locking, and precise control of camera and pacing for clips that drop into real production timelines.

  🎥Videos🎬Video editing📽️Image to video
  Video

  Released 9mo ago
• Gen 4 Sora
  Sora 2 pro

  By OpenAI

  Flagship text to video profile for complex scenes, realistic physics, and long, stable takes.

  🎥Videos🎬Video editing📽️Image to video
  Video

  Released 9mo ago
• Gen 4 Kling
  Kling 2.5 Turbo

  By Kuaishou Technology

  Kling 2.5 Turbo is Kuaishou’s high-speed text-to-video engine. It delivers sharper, longer, more stable clips with tight identity/style locking and precise camera/motion control—supporting text→video, image→video, and in-place edits—optimized for rapid iteration and production delivery.

  🎥Videos🎬Video editing📽️Image to video
  Video

  Released 9mo ago
• Gen 4 Lucy
  Lucy Edit

  By Decart AI

  Lucy Edit by Decart AI is a text-guided video editor. You upload a clip, describe the change in natural language, and it performs the edit—outfit swaps, character replacements, object insertions, background/scene changes—while keeping motion, lighting, and composition consistent.

  🎥Videos🎬Video dubbing🎬Video editing📽️Image to video
  Video

  Released 9mo ago
• Gen 4
  Fabric 1.0 Fast

  By Veed

  VEED Fabric 1.0 Fast is an image-to-video API that turns a single static image and an audio clip into a realistic talking video, syncing lip movement, head motion, and gestures to the audio. This is the speed-optimized endpoint of Fabric 1.0, trading a small pricing premium for faster generation.

  🎥Videos📽️Image to video🕺Avatar animation📺Video ads
  Video

  Released 10mo ago
• Gen 4
  VEED Fabric 1.0 (Text)

  By Veed

  Turns a single static image and a text script into a realistic talking video. The model auto-generates a matching voice from the image and syncs lips, head, and body motion to it, producing clips up to 5 minutes long in 480p or 720p.

  🎥Videos🔊Text to speech📽️Image to video🎤Lip sync videos
  Video

  Released 10mo ago
• Gen 4
  Fabric 1.0

  By Veed

  VEED Fabric 1.0 turns a single image and an audio clip into a realistic talking video, syncing lip movements, facial expressions, and body motion to the audio. Delivered via API with 480p and 720p output options for avatars and personalized video content.

  📽️Image to video🕺Avatar animation🎥Video avatars🎤Lip sync videos🎥Personalized videos
  Video

  Released 10mo ago
• Gen 4 PixVerse
  PixVerse V5

  By Pixverse

  PixVerse V5 is an advanced text and image to video model on ImagineArt that generates cinematic, high motion realism clips with keyframe control, camera and style customization, plus fusion modes to extend or remix existing footage.

  🎥Videos📽️Image to video📷Images🎬Animations
  Video

  Released 10mo ago
• Gen 4 Wan
  Wan2.2 TI2V 5B

  By Alibaba

  Wan2.2-TI2V-5B is a lightweight text-and-image-to-video model. Give it a prompt plus a reference frame or style image and it generates coherent, temporally stable clips with preserved identity, controllable camera/motion, and fast iteration for cost-sensitive workflows.

  🎥Videos📽️Image to video
  Video

  Released 11mo ago
• Gen 4 Wan
  Wan2.2 I2V A14B

  By Alibaba

  Wan2.2-I2V-A14B is an image-to-video model that animates a single frame or storyboard into a temporally stable clip. It preserves identity and style, follows camera and motion cues, supports targeted edits, and exports cleanly for production workflows.

  📽️Image to video🎥Videos
  Video

  Released 11mo ago
• Gen 4 Wan
  Wan2.2 T2V A14B

  By Alibaba

  Wan2.2-T2V-A14B is a text-to-video model focused on high-fidelity, temporally stable generation. It supports prompt-to-clip, image-to-video, and targeted edits, with stronger identity/style consistency, camera and motion control, and practical export for production use.

  🎥Videos🎬Video editing📽️Image to video
  Video

  Released 11mo ago
• Gen 4 Higgsfield
  Higgsfield DoP Lite

  By Higgsfield

  Cinematography-focused video model, Lite profile for balanced quality and speed with dependable camera language and identity consistency.

  🎥Videos🎬Video editing📽️Image to video
  Video

  Released 1y ago
• Gen 3
  HunyuanVideo I2V

  By Tencent

  HunyuanVideo I2V is an image-to-video generation model based on the HunyuanVideo framework, built to turn a single reference image into a short video while keeping strong first-frame consistency.

  📽️Image to video🖼️Image generation
  Multimodal

  Released 1y ago
• Gen 4 Pika
  Pika 2.2

  By Mellis

  Text and image to video model with better motion control, identity consistency, and cleaner small details.

  🎥Videos🎬Video editing📽️Image to video
  Video

  Released 1y ago
• Gen 4 LTX
  LTX 2 Pro

  By Lightricks

  LTX-2 Pro is a high-fidelity text and image-to-video model with integrated upscaling and sound-ready timing.

  🎥Videos🎬Video editing📽️Image to video
  Video

  Released 1y ago
• Gen 4 Stable Diffusion
  Stable Video Diffusion 1.1

  By Stability AI

  Image-to-Video; Latent diffusion model generating 25 frames (1024x576) at 6 FPS from a single ima...

  📽️Image to video🎥Videos
  Video

  Released 2y ago
• Gen 4
  Motion 1.0

  By Leonardo Interactive

  Motion 1.0 is the original short-clip image-to-video generator for quick motion studies and social loops.

  📽️Image to video🖼️Image generation👻Horror image generation
  Video

  Released 2y ago
• Gen 3 Stable Diffusion
  Stable Video

  By Stability AI

  Image-to-video generation model.

  📽️Image to video🖼️Image generation
  Image

  Released 2y ago