Models

4,400 in the directory.

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

Most downloaded A–Z Recently synced

Grok Imagine v0.9 xAI Ling-flash-2.0 is a high-speed multilingual instruction model built for very low latency and high t… Multimodal · 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
Grok Voice Think Fast 1.0 xAI Grok Voice Think Fast 1.0 is xAI’s fastest and most capable voice-agent model so far. It is built f… Multimodal · Closed Closed weights
Grok Voice Think Fast 2.0 xAI Grok Voice Think Fast 2.0 is a speech-to-speech voice model built for real-time conversational voic… Audio · Closed Closed weights
Groq Gemma Groq Groq Gemma is Google’s Gemma model family served on Groq hardware for ultra-low-latency inference.… Text · Open weights Open weights
Groq Llama Groq Groq Llama is Meta’s Llama family served on Groq hardware, giving Llama-quality outputs with very l… Text · Open weights Open 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 2.3 MiniMax Hailuo 2.3 is a high-quality text-to-video model for longer, steadier shots and stronger physics Image · Closed Closed weights
Hailuo 2.3 Fast MiniMax Hailuo 2.3 Fast is a speed-tuned mode that trades a little peak fidelity for much lower latency. Image · Closed Closed weights
Hailuo Audio 01 music MiniMax Hailuo Audio 01 music is an earlier music generation model for hooks, riffs, and ambient beds. Audio · Closed Closed weights
Hailuo Audio 2.0 music MiniMax Hailuo Audio 2.0 music generates short musical clips from text and style prompts. Audio · Closed Closed weights
Hailuo Audio 2.5 hd MiniMax Hailuo Audio 2.5 hd is a high-fidelity TTS model for production-quality narration and content. Audio · Closed Closed weights
Hailuo Audio 2.5 Turbo MiniMax Hailuo Audio 2.5 turbo is a low-latency TTS model for live assistants and high-throughput use. Audio · Closed Closed weights
Hailuo Video 01 Live MiniMax AI model by MiniMax Video · Closed Closed weights
Handoff Hark Handoff is Hark's computer-use agent built for long-horizon, autonomous work on the internet. Given… Multimodal · Closed Closed weights
HappyHorse 1.0 Alibaba HappyHorse-1.0 is a closed AI video generation model available through fal’s API and playground. It… Multimodal · 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
Harrier OSS v1 Microsoft Harrier is Microsoft’s new open-source text embedding model series for retrieval, grounding, and ag… Text · Open weights Open weights
Harvey II Harvey AI Harvey II is the next generation of Harvey's legal AI platform, built around agents that inherit th… Text · Closed Closed weights
Heaviside 1 Arena Physica Heaviside 1 is a 350M parameter foundation model for electromagnetics. It takes fully 3D structures… Structured data · Closed Closed 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
Hertz-dev Standard Inteligence AI model by Standard Inteligence Audio · Closed Closed 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
Holo 3 H Company Holo3 is H Company’s computer-use agent model for enterprise workflows. It is designed to see, reas… Multimodal H Company
HTS HTS Working Group HTS is a statistical text-to-speech system that models speech with HMMs, then uses a vocoder to syn… Audio · Closed Closed weights
Humain M3 HUMAIN Humain M3 is a text-only Arabic-focused large language model built on the MiniMax-M3 architecture (… Text · Open weights Open weights
Hunyuan HY-T1 Alibaba Hunyuan T1 is Tencent’s deep reasoning model positioned for stronger structured reasoning and long-… Image · Closed Closed weights
Hunyuan Motion 1.0 Tencent Tencent HY-Motion 1.0 is an open text-to-3D human motion generator using billion-scale Diffusion Tr… Image · Open weights Open weights
Hunyuan Translation Model 1.5 Tencent Tencent-HY-MT1.5 is a multilingual machine-translation family with 1.8B and 7B models, supporting 3… Text · Open weights Open weights
Hunyuan3D-Paint Tencent Hunyuan3D-Paint is Tencent’s text-to-3D painting and texture generation model. It takes existing 3D… Image · Open weights Open weights
HunyuanCustom Tencent HunyuanCustom is Tencent’s customization framework for the Hunyuan model family. It lets enterprise… Video · Open weights image to video pipeline