NVIDIA
Explore
Models
Blueprints
GPUs
Docs
⌘KCtrl+K
Terms of Use
Privacy Policy
Your Privacy Choices
Contact

Copyright © 2026 NVIDIA Corporation

17 results for

Filters (1)

  • Free Endpoint
    5
  • Partner Endpoint
    6
  • Download Available
    9
  • Enterprise
    1
  • Launchable
    0
  • Image-to-Text
    3
  • Image Generation
    1
  • Optical Character Recognition
    1
  • Medical Imaging
    1
  • Object Detection
    1
  • Deep Infra
    5
  • Bitdeer AI
    3
  • Together AI
    3
  • GMI Cloud
    2
  • Baseten
    0
  • NVIDIA
    9
  • Meta
    2
  • Mistral AI
    2
  • Qwen
    2
  • Google
    1
  • NVIDIA Isaac GR00T
    1
  • NVIDIA Omniverse
    1
  • NVIDIA AI
    0
  • image
    • DGX Spark
    1 HR

    FLUX.1 Dreambooth LoRA Fine-tuning

    Fine-tune FLUX.1-dev 12B model using Dreambooth LoRA for custom image generation
    Playbook
    Image Generation
    6mo
    Items per page
    of 1 pages
    Meta
    Downloadable

    llama-3.2-90b-vision-instruct

    Cutting-edge vision-Language model exceling in high-quality reasoning from images.
    Model
    Image-Text Retrieval
    1.41M
    10mo
    NVIDIA
    DeprecatedFree Endpoint

    visual-changenet

    Visual Changenet detects pixel-level change maps between two images and outputs a semantic change segmentation mask
    Model
    image
    462
    1y
    Qwen
    Downloadable

    qwen3.5-397b-a17b

    Next-gen Qwen 3.5 VLM (400B MoE) brings advanced vision, chat, RAG, and agentic capabilities.
    Model
    MoE
    12.42M
    2mo
    Meta
    Downloadable

    llama-3.2-11b-vision-instruct

    Cutting-edge vision-language model exceling in high-quality reasoning from images.
    Model
    Image-Text Retrieval
    1.04M
    10mo
    Mistral AI
    DeprecatedFree Endpoint

    mistral-small-3.1-24b-instruct-2503

    Efficient multimodal model excelling at multilingual tasks, image understanding, and fast-responses
    Model
    language generation
    1.24M
    11mo
    NVIDIA
    Downloadable

    llama-3.1-nemotron-nano-vl-8b-v1

    Multi-modal vision-language model that understands text/img and creates informative responses
    Model
    doc intelligence
    8.88M
    9mo
    NVIDIA
    Downloadable

    nvclip

    NV-CLIP is a multimodal embeddings model for image and text.
    Model
    Computer vision
    90.73K
    10mo
    DGX Spark
    1 HR

    Vision-Language Model Fine-tuning

    Fine-tune Vision-Language Models for image and video understanding tasks using Qwen2.5-VL and InternVL3
    Playbook
    DGX
    6mo
    Microsoft
    Downloadable

    TRELLIS

    MSFT TRELLIS is a 3D AI model that generates high-quality 3D assets from text or image inputs.
    Model
    text-to-3d
    3.38K
    7mo
    Mistral AI
    Downloadable

    mistral-small-4-119b-2603

    Hybrid MoE model unifying instruct, reasoning, and coding with multimodal input and 256k context
    Model
    code generation
    8.53M
    1mo
    Google
    Free Endpoint

    paligemma

    Vision language model adept at comprehending text and visual inputs to produce informative responses
    Model
    image
    38.52K
    1y
    Qwen
    Downloadable

    qwen3.5-122b-a10b

    122B MoE LLM (10B active) for coding, reasoning, multimodal chat. Agent-ready.
    Model
    tool calling
    9.06M
    1mo
    NVIDIA
    DeprecatedFree Endpoint

    retail-object-detection

    EfficientDet-based object detection network to detect 100 specific retail objects from an input video.
    Model
    Object Detection
    380
    1y
    NVIDIA
    Downloadable

    vista-3d

    VISTA-3D is a specialized interactive foundation model for segmenting and anotating human anatomies.
    Model
    Interactive Annotation
    1.03K
    1y
    NVIDIA
    DeprecatedFree Endpoint

    ocdrnet

    OCDNet and OCRNet are pre-trained models designed for optical character detection and recognition respectively.
    Model
    Optical Character Recognition
    848
    1y
    NVIDIA
    Enterprise

    Synthetic Manipulation Motion Generation for Robotics

    Generate exponentially large amounts of synthetic motion trajectories for robot manipulation from just a few human demonstrations.
    Blueprint
    synthetic data
    2mo