Promote Sign in Sign up

Catalogs

Models

398 matched .

Explore AI models for text, images, audio and coding. Filter by model task, open or closed weights, and Hugging Face availability.

Clear search and filters

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 Clear filters
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. Midjourney V2 Midjourney Midjourney V2 brought better structure and subject coherence while keeping the strong stylistic voi… Image · Closed Closed weights
  2. Midjourney V3 Midjourney Midjourney V3 increased detail and control, improving multi-subject scenes, materials, and overall… Image · Closed Closed weights
  3. Midjourney V5 Midjourney Midjourney V5 pushed photorealism, dynamic range, and prompt fidelity further, while broadening sty… Image · Closed Closed weights
  4. Midjourney V8 Midjourney AI model by Midjourney Image · Closed Closed weights
  5. Midjourney V8.2 Midjourney Midjourney V8.2 is an update to the V8 image generation model focused on aesthetics, image quality,… Image · Closed Closed weights
  6. Motif Image 6B Preview Motif Technologies Motif Image 6B Preview is a 6-billion-parameter text-to-image generation model released by Motif Te… Image · Closed text to image pipeline
  7. Muse Google AI model by Google Image · Closed Closed weights
  8. Muse Image Meta Platforms Muse Image is Meta's agentic image generation model. Rather than mapping prompts directly to pixels… Image · Open weights Open weights
  9. Nanobanana Google DeepMind Nanobanana is Google’s nickname for Gemini 2.5 Flash Image, a fast image-generation and conversatio… Image · Closed Closed weights
  10. Niji V7 Midjourney Niji V7 is Midjourney’s newest anime-first image model with improved anime coherence, prompt follow… Image · Closed Closed weights
  11. Nova Canvas Amazon Nova Canvas is the Nova family’s image model. It turns prompts and references into production ready… Image · Closed Closed weights
  12. NSFW Model Infinite Red Image classification model trained on 60+ gigs of data to detect NSFW content. Classifies images in… Image · Closed Closed weights
  13. olmOCR Ai2 olmOCR is AllenAI’s open-source document recognition pipeline and model family that converts PDFs a… Image · Closed Closed weights
  14. OpenFold 3 OpenFold Consortium OpenFold3 is a protein structure and complex prediction model. It maps sequences to 3D structures w… Image · Closed Closed weights
  15. OVIE Kyutai OVIE is Kyutai’s open monocular novel view synthesis model for generating new viewpoints from a sin… Image · Closed Closed weights
  16. P Image Pruna AI P-Image is a performance text-to-image model tuned for sub-second generation with strong prompt adh… Image · Closed Closed weights
  17. P Image Edit Pruna AI P-Image-Edit is a performance image-to-image editing model designed to apply instruction-guided edi… Image Pruna AI
  18. P Image Ideogram Ideogram AI P-Image-Ideogram is a fast text-to-image model built with Pruna AI, offering four quality tiers (Ve… Image · Open weights Open weights
  19. P Image Upscale Pruna AI P-Image Upscale is Pruna AI’s image-to-image upscaling model built for fast, low-cost, high-quality… Image · Closed Closed weights
  20. PaLM-E Google AI model by Google Image · Closed Closed weights
  21. Pangram Image Pangram Pangram Image is a research-preview model that detects AI-generated images from major generators in… Image Pangram
  22. Paris Bagel LABS Paris by Bagel Labs is an open weight text to image diffusion model trained entirely through decent… Image · Closed Closed weights
  23. Parti Google AI model by Google Image · Closed Closed weights
  24. Photon 1 Luma 1 Photon is Luma’s controllable text-to-image model for high-fidelity, photoreal results with solid… Image · Closed Closed weights
  25. Pixel Perfect Depth Xiaomi Pixel-Perfect Depth is a monocular depth estimation model that uses pixel-space diffusion transform… Image · Closed Closed weights
  26. Precision V1 Generative Suite Precision V1 is an upscaler-detailer that enlarges images while restoring edges and textures with m… Image · Closed Closed weights
  27. Precision V2 Generative Suite Precision V2 refines V1 with cleaner micro-texture and steadier small-text legibility at similar sp… Image · Closed Closed weights
  28. Qwen Image 2.0 Alibaba Qwen-Image-2.0 is Qwen’s next-generation foundational image generation model built for professional… Image · Open weights Open weights
  29. Qwen Image 2.0 Pro Alibaba Qwen-Image-2.0-Pro is Qwen’s higher-fidelity image generation and editing model for professional vi… Image · Open weights Open weights
  30. Qwen Image 3.0 Alibaba Qwen Image 3.0 is Alibaba's third generation image generation model, built to produce information d… Image · Open weights Open weights
  31. Realism Freepik Company Realism targets lifelike renders with accurate materials and skin tones. Image Freepik Company
  32. Recraft V3 Recraft AI model by Recraft Image · Closed Closed weights
  33. Reve 2.1 Reve AI Reve 2.1 is an image generation and editing model that renders at native 4K (16 megapixels). It pla… Image · Closed Closed weights
  34. Reve Image 1.0 Reve AI Reve Image 1.0 (codename Halfmoon) is a state-of-the-art text-to-image AI model that excels in prom… Image · Closed Closed weights
  35. Reve Image 1.5 Reve AI AI model by Reve AI Image · Closed Closed weights
  36. Reve V1.1 Fast Reve AI Reve v1.1 Fast is a fast variant of Reve's v1.1 image model, ranked just below the full version on… Image · Closed Closed weights