Models
224 matched .
Explore AI models for text, images, audio and coding. Filter by model task, open or closed weights, and Hugging Face availability.
All types
Text · 2,080
Image · 398
Video · 224
Audio · 372
Coding · 40
Multimodal · 885
Structured data · 27
3D · 17
Weights and source
Explore other catalogs
Saved only in this browser. No account needed.
How to choose models
Start with the task you need the model to perform, then narrow the model type and weight availability. Open weights do not automatically mean unrestricted commercial use. Check the original model card for the license, input requirements, evaluation results and hardware needs before choosing a model.
-
SkyReels V1
Skywork AI
SkyReels V1 is a human-centric video foundation model tuned for cinematic, character-focused genera…
Video · Open weights
2
HF downloads
-
Vchitect 2.0
Shanghai AI Laboratory
Vchitect-2.0 is a parallel-transformer text-to-video diffusion model that scales to large video dat…
Video · Open weights
2
HF downloads
-
4DV.ai 4DV 4DV.ai builds 4D video creation, playback, and editing tools based on 4D Gaussian Splatting, turnin… Video · Open weights Open weights
-
Act Two Runway Act-Two is a narrative-aware video generator that turns scene directions into cohesive sequences. I… Video · Closed Closed weights
-
Agnes Video V2.0
Agnes AI
Agnes Video V2.0 is an asynchronous video generation model supporting text-to-video, image-to-video…
Video · Open weights
Open
weights
-
Agora 1 Odyssey Agora-1 is Odyssey’s multi-agent world model that lets multiple human or AI participants share and… Video · Open weights Open weights
-
Cara 4
Anam
Cara-4 is Anam's real-time avatar model that animates a custom image into an expressive, talking co…
Video · Closed
Closed
weights
-
Crystal Video Upscaler
ClarityAI
Crystal Video Upscaler is Clarity AI’s high-precision video upscaling model that turns low-resoluti…
Video · Closed
Closed
weights
-
Earth 2 Nowcasting NVIDIA Earth-2 Nowcasting is NVIDIA’s generative AI storm model that turns satellite and radar data into z… Video · Open weights Open weights
-
EchoJEPA bowang-lab Self-supervised echocardiography foundation model that predicts future ultrasound views in latent s… Video bowang-lab
-
Emu Video Meta Platforms AI model by Meta Platforms Video · Closed Closed weights
-
Express 3 Synthesia Express-3 is Synthesia's most lifelike AI avatar model yet, delivering advanced lip-sync, natural b… Video · Closed Closed weights
-
Fabric 1.0 Veed VEED Fabric 1.0 turns a single image and an audio clip into a realistic talking video, syncing lip… Video · Open weights Open weights
-
Fabric 1.0 Fast Veed VEED Fabric 1.0 Fast is an image-to-video API that turns a single static image and an audio clip in… Video · Closed Closed weights
-
FireRed OpenStoryline FireRedTeam FireRed-OpenStoryline is an AI video editing agent that turns natural-language intent into an editi… Video · Closed Closed weights
-
GameGen X GameGen-X GameGen-X is a diffusion transformer specifically built for open-world game video, generating and i… Video · Open weights Open weights
-
Gemini Omni 1.1 Flash Google DeepMind Gemini Omni 1.1 Flash is a generative video model offering scene extension up to 40 seconds, first… Video · Closed Closed weights
-
Gen 1 Runway AI model by Runway Video · Closed Closed weights
-
Gen 3 Alpha Runway Gen-3 Alpha is Runway’s next-gen video model for text/image-to-video and video editing. It delivers… Video · Closed Closed weights
-
Gen 4 Runway Gen-4 is a next-generation video model that raises fidelity, temporal stability, and physical reali… Video · Closed Closed weights
-
Gen 4 Turbo Runway Gen-4 Turbo is the high-throughput variant of Gen-4, trading a touch of peak fidelity for much fast… Video · Closed Closed weights
-
Gen 4.5 Runway Runway Gen-4.5 is Runway's latest text-to-video and image-to-video model, ranked #1 on independent… Video · Closed Closed weights
-
Gen-3 Alpha Turbo Runway Gen-3 Alpha Turbo is a speed-tuned upgrade to Gen-3 Alpha that delivers faster previews and lower l… Video · Closed Closed weights
-
Grok Imagine 1 xAI Grok Imagine is xAI’s video-audio generative model, exposed through the Imagine API, that turns tex… Video · Closed Closed weights
-
Grok Imagine Video 1.5 xAI Image-to-video generation model that produces short clips from a starting image and text prompt. Ge… Video · Closed Closed weights
-
H3 Max Turbo
Features and Labels
H3 Max Turbo is a fast text-to-video and image-to-video model from fal that generates short video c…
Video · Open weights
Open
weights
-
hailuo 02 pro MiniMax hailuo-02-pro is the flagship Hailuo model for high accuracy reasoning, coding, and multilingual wo… Video · Closed Closed weights
-
hailuo 02 standard MiniMax hailuo-02-standard is the balanced, cost efficient member of the Hailuo line. It delivers solid ins… Video · Closed Closed weights
-
Hailuo Video 01 Live MiniMax AI model by MiniMax Video · Closed Closed weights
-
HappyHorse 1.1 T2V Alibaba HappyHorse-1.1-T2V is a text-to-video generation model with improved semantic understanding, cinema… Video · Open weights Open weights
-
HappyOyster 1.0 Alibaba Real-time interactive world model that generates immersive video environments from text and image p… Video · Open weights Open weights
-
Helios
PKU-YuanGroup
Helios is a real-time long video generation model that targets minute-scale, high-quality video syn…
Video · Open weights
Open
weights
-
Higgsfield DoP Lite
Higgsfield
Cinematography-focused video model, Lite profile for balanced quality and speed with dependable cam…
Video · Closed
Closed
weights
-
Higgsfield DoP Standard
Higgsfield
Main DoP profile for higher fidelity, better motion coherence, and stronger control over camera, li…
Video · Closed
Closed
weights
-
Higgsfield DoP Turbo
Higgsfield
AI model by Higgsfield
Video · Closed
Closed
weights
-
HunyuanCustom Tencent HunyuanCustom is Tencent’s customization framework for the Hunyuan model family. It lets enterprise… Video · Open weights image to video pipeline