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. UGC VideoCaptioner Memories.ai UGC VideoCaptioner is a 3B parameter omni model that writes detailed, paragraph style captions for… Multimodal · Open weights 13 HF downloads
  2. GuppyLM Arman Hossain GuppyLM is a tiny open-source language model that roleplays as a fish named Guppy. It has about 8.7… Text · Open weights 12 HF downloads
  3. Higgs Audio v3 TTS Boson AI Higgs Audio v3 TTS is Boson AI’s text-to-speech model for expressive conversational voice agents ac… Audio · Open weights 12 HF downloads
  4. Mage Flow Microsoft Mage-Flow is a compact 4B-parameter text-to-image diffusion model from Microsoft, built on a Native… Image · Closed 11 HF downloads
  5. Reka Edge Reka AI Reka Edge is Reka’s 7B vision-language model engineered for edge and physical-AI deployment, with s… Multimodal · Open weights 9 HF downloads
  6. StreamDiffusion ByteDance AI model by ByteDance Video · Closed 9 HF downloads
  7. Tsubaki 2 PixAI Tsubaki.2 is PixAI’s flagship image generation model, built to improve prompt understanding, anatom… Image · Open weights 9 HF downloads
  8. Claude Sonnet 3.5 Anthropic Claude 3.5 Sonnet is Anthropic’s balanced model—fast enough for everyday apps yet capable of solid… Text · Closed 8 HF downloads
  9. Lightning XL Leonardo Interactive Lightning XL is a speed optimized SDXL checkpoint that produces strong images in very few steps, id… Image · Closed 8 HF downloads
  10. DCGAN DCGAN DCGAN is a convolutional GAN architecture that stabilizes training and improves image quality. It r… Image · Closed 7 HF downloads
  11. Protenix ByteDance Protenix is ByteDance’s open-source biomolecular structure prediction model family for high-accurac… Multimodal · Open weights 7 HF downloads
  12. Baichuan Audio Baichuan Intelligent Technology Baichuan-Audio is an end-to-end speech interaction model that unifies audio understanding and audio… Multimodal · Open weights 6 HF downloads
  13. CogVideoX Z.ai CogVideoX is Zhipu AI's open text-to-video and image-to-video model family, released in 2B and 5B s… Video · Open weights 6 HF downloads
  14. F pre 8kv 8k 14k SWA Ai2 F_pre_8kv_8k_14k_SWA is an AllenAI OlmPool architectural-variation model for studying long-context… Text · Open weights 6 HF downloads
  15. Xiaomi-Robotics-1 Xiaomi Xiaomi-Robotics-1 is a vision-language-action robot foundation model pre-trained on over 100,000 ho… Multimodal · Open weights 3 HF downloads
  16. Chinchilla Google DeepMind Chinchilla is DeepMind’s 70B language model used to demonstrate compute-optimal scaling with more t… Text · Open weights 2 HF downloads
  17. 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
  18. 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
  19. 1 Bit Bonsai 4B PrismML 1-bit Bonsai 4B is PrismML’s mid-size ultra-efficient model designed for fast local inference. It u… Text · Open weights Open weights
  20. 1 Bit Bonsai 8B PrismML 1-bit Bonsai 8B is PrismML’s flagship ultra-efficient language model, built with 1-bit weights for… Text · Open weights Open weights
  21. 1-bit Bonsai Image 4B PrismML 1-bit Bonsai Image 4B is PrismML’s open-weight compressed image-generation model built for local di… Image · Open weights Open weights
  22. 1X World Model 1X Technologies The 1X World Model is a generative video-based simulator for 1X humanoid robots that predicts futur… Text 1X Technologies
  23. 4DV.ai 4DV 4DV.ai builds 4D video creation, playback, and editing tools based on 4D Gaussian Splatting, turnin… Video · Open weights Open weights
  24. 7 DreamShaper Stability AI DreamShaper 7 is a versatile SD checkpoint that balances realism and illustration for all purpose c… Image · Open weights Open weights
  25. A.X K1 SK Telecom A.X-K1 is SK Telecom’s 519B-parameter MoE frontier language model, trained on about 10T tokens to a… Text · Closed Closed weights
  26. ACE Step v1.5 StepFun ACE-STEP v1.5 is an open source, super fast music foundation model that uses a hybrid language mode… Audio · Open weights Open weights
  27. ACE-Step 1.5 XL (4B DiT) StepFun ACE-Step 1.5 XL is the 4B-parameter Diffusion Transformer decoder in the ACE-Step 1.5 music generat… Multimodal · Open weights Open weights
  28. ACT 2 Sunday ACT 2 is a robotics foundation model developed by Sunday Robotics for autonomous home manipulation.… Multimodal · Closed Closed weights
  29. Act Two Runway Act-Two is a narrative-aware video generator that turns scene directions into cohesive sequences. I… Video · Closed Closed weights
  30. Agnes 2.0 Flash Agnes AI Agnes 2.0 Flash is a fast, cost efficient language model built for high frequency production use. I… Multimodal · Open weights Open weights
  31. Agnes Image 2.0 Flash Agnes AI Agnes Image 2.0 Flash is an image generation and editing model supporting text-to-image, image-to-i… Image · Closed Closed weights
  32. Agnes Image 2.1 Flash Agnes AI Agnes Image 2.1 Flash is an image generation model from Sapiens AI supporting text-to-image and ima… Image · Closed Closed weights
  33. 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
  34. 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
  35. Aikido Infinite Aikido Aikido Infinite is a continuous autonomous penetration testing system that runs on every release an… Text · Closed Closed weights
  36. Aion 1.0 Instruct Microsoft Aion 1.0 Instruct is Microsoft’s on-device small language model for local text intelligence such as… Text · Closed Closed weights