Blog Promote Sign in Sign up

Catalogs

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
Weights and source
Open weights Closed On Hugging Face
Most downloaded A–Z Recently synced
Explore other catalogs
Models Datasets Demos Devices Robots MCPs Papers Investors Fundraises Repositories News
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.

Understand our sources and data limits

  1. Ternary Bonsai Image 4B PrismML Ternary Bonsai Image 4B is PrismML’s open-weight compressed image-generation model that trades slig… Image · Open weights Open weights
  2. Tiny Aya Cohere Small multilingual model family aimed at running offline/at-the-edge while supporting a large numbe… Text · Open weights Open weights
  3. TIPS g/14 Google DeepMind TIPS is a vision language model that produces image embeddings combining global semantic understand… Multimodal · Open weights Open weights
  4. Titan Image Generator V2 Amazon Amazon Titan Image Generator V2 is AWS’s latest text-to-image model on Bedrock, built for high-qual… Image · Closed Closed weights
  5. Titan Text Premier Amazon Amazon Titan Text Premier is AWS’s top-tier text generation model on Bedrock, built for enterprise-… Text · Closed Closed weights
  6. Toast 1 mixedbread ai Toast 1 is a specialized search agent that decomposes a query into subqueries, executes multi round… Text · Open weights Open weights
  7. Topaz Starlight Precise 2.5 Topaz Labs Topaz Starlight Precise 2.5 is an upgraded video upscaling model available through ComfyUI Partner… Video · Closed Closed weights
  8. Toto 2.0 Datadog Toto 2.0 is Datadog’s open-source time-series forecasting model family for multivariate, zero-shot,… Structured data · Closed Closed weights
  9. TranslateGemma Google DeepMind TranslateGemma is Google’s open Gemma-based translation model family for text and image-text transl… Text · Closed Closed weights
  10. TRIBE v2 Meta Platforms TRIBE v2 is Meta’s multimodal brain-encoding research demo. It predicts whole-brain fMRI responses… Multimodal Meta Platforms
  11. Tripo H3.1 Tripo AI Tripo H3.1 is Tripo’s high-detail 3D generation model for producing production-ready assets from te… 3D · Open weights Open weights
  12. Tripo3D P1.0 Tripo AI Tripo P1.0, also called Smart Mesh P1.0, is Tripo’s structured mesh-generation model for producing… 3D · Open weights Open weights
  13. TripoSplat Tripo AI TripoSplat is TripoAI / VAST AI Research’s MIT-licensed image-to-3D model for converting a single 2… Multimodal · Closed Closed weights
  14. TwiL LM1.7B webAI TwiL LM1.7B is a compact 1.7-billion-parameter formal-logic model from webAI that translates plain… Text · Open weights Open weights
  15. TwiL LM3B webAI TwiL LM3B is a 3-billion-parameter formal-logic model from webAI that translates plain English into… Text · Open weights Open weights
  16. Ultralytics YOLO Ultralytics Ultralytics YOLO is a family of real-time computer-vision models for detection, segmentation, class… Image · Open weights Open weights
  17. UltraShape 1.0 PKU-YuanGroup UltraShape 1.0 is a two-stage diffusion framework for high-fidelity 3D shape generation, using a sc… Image · Closed Closed weights
  18. Uni 1 Luma Uni-1 is Luma’s multimodal reasoning model that can generate pixels, built to understand intent, re… Multimodal · Closed Closed weights
  19. Uni 1.1 Luma Uni-1.1 API is Luma’s closed-source REST API for image generation and natural-language image editin… Multimodal · Open weights Open weights
  20. UnifoLM OminiA 0.3 Unitree Robotics A multimodal embodied AI model from Unitree built for the G1 humanoid robot, unifying household and… Structured data · Closed Closed weights
  21. Universal 3 Pro AssemblyAI Universal-3 Pro is a promptable speech language model that turns raw audio into highly accurate tra… Audio · Open weights Open weights
  22. v0 1.0 md Vercel v0-1.0-md is Vercel's original composite AI coding model for the v0 platform. It combines Anthropic… Coding · Closed Closed weights
  23. v0 1.5 lg Vercel v0-1.5-lg is Vercel's larger composite AI coding model for full-stack web app generation. It pairs… Coding · Closed Closed weights
  24. v0 1.5 md Vercel v0-1.5-md is a composite AI coding model from Vercel that generates full-stack web application code… Coding · Closed Closed weights
  25. V5 Midjourney AI model by Midjourney Image · Closed Closed weights
  26. Valley3 ByteDance Valley3 is a next-generation text and image to video model that improves temporal stability, physic… Text · Open weights Open weights
  27. VEED Fabric 1.0 (Text) Veed Turns a single static image and a text script into a realistic talking video. The model auto-genera… Video · Closed Closed weights
  28. VEED Lipsync V2 Veed VEED Lipsync V2 generates production quality lip synced videos from a source video and a replacemen… Video · Closed Closed weights
  29. Veed Video Background Removal Green Screen Veed VEED Video Background Removal (Green Screen) is a chromakey-specialized video processing model that… Video · Closed Closed weights
  30. Veo 1.0 Google DeepMind Veo 1.0 is Google DeepMind’s first Veo video-generation model for creating high-quality videos from… Video · Closed Closed weights
  31. Veo 2.0 Google DeepMind Veo 2.0 is Google DeepMind’s upgraded text-to-video and image-to-video model for higher-quality, mo… Video · Closed Closed weights
  32. Veo 3 Google DeepMind Veo 3 is Google DeepMind’s video-generation model that adds stronger realism and native audio gener… Video · Closed Closed weights
  33. Veo 3.1 Google DeepMind Veo 3.1 is Google’s state-of-the-art cinematic video-generation model for 4K-style storytelling, na… Video · Closed Closed weights
  34. Veo 3.1 Fast Google DeepMind Veo 3.1 Fast is Google’s faster Veo 3.1 tier for high-quality video generation with lower latency t… Video · Closed Closed weights
  35. Veo 3.1 Lite Google DeepMind Veo 3.1 Lite is Google’s cost-efficient Veo 3.1 video model for high-volume, developer-first video… Multimodal · Closed Closed weights
  36. VGAN MIT Computer Science and Artificial Intelligence Laboratory VGAN, the 2016 Video GAN, generates short clips directly from noise using a spatio temporal GAN. It… Video · Open weights Open weights