AI-Generated Art and Videos for Enterprises

NVIDIA Picasso

AI foundry for building and deploying generative AI models for visual design.

What Is NVIDIA Picasso?

NVIDIA Picasso is an AI foundry for software developers and service providers to build and deploy cutting-edge generative AI models for visual content. NVIDIA Picasso offers a path to train and customize state-of-the-art visual generative AI models that are both commercially safe and deployable through NVIDIA DGX™ Cloud. Developers can also bring their own model and run inference seamlessly through a straightforward API workflow.

NVIDIA Edify Unlocks 3D Generative AI, New Image Controls for Visual Content Providers

Image courtesy of iStock

AI Foundry for Visual Generative AI Models

Create custom visual generative AI models for your applications and services. Choose NVIDIA's multimodal Edify architecture or seamlessly deploy the model of your preference.

Edify Visual Foundation Models

Train NVIDIA Edify on your data, to build bespoke models. Edify models can generate high-quality 4K images, 3D assets, video, 360 HDRi, and physically based rendering (PBR) materials.

Automated Fine-Tuning

Picasso simplifies the customization of Edify models with a complete self-service workflow. You can bring in your data and tune Edify models to your unique style.

Rapid Inference in the Cloud

Use Edify or bring your choice of visual foundation model and run inference with an easy-to-use API. Deploy through NVIDIA DGX Cloud in major cloud service providers (CSPs), including AWS, GCP, OCI, and Microsoft Azure.

Build NVIDIA Edify Visual Foundation Models

Train the state-of-the-art NVIDIA Edify diffusion model on your data to generate a range of visual content types from 2D to 3D.

Edify Image

Build models to generate, control, and modify 4K images.

Image Generation

Generate high-quality, realistic imagery with text and image prompts.

Inpainting

Add characters or objects with text prompts or replace specific elements.

Outpainting

Expand images to various aspect ratios with text prompts.

Depth

Reimagine a composition with a variety of characters and environments.

Sketch

Transform sketches to unique images with guided prompts.

Segment

Segment any object automatically to generate masks quickly during editing workflows.

Edify 3D

Develop models to create 3D assets at speed.

Text to 3D

Create simple 3D assets for rapid prototyping and set dressings.

Image to 3D

Quickly generate 3D assets from single image reference.

Edify 360 HDRi

Train model to match lighting for 3D scenes.

360 HDRi

Train models to generate environment maps to relight 3D scenes and add reflections.

Edify Materials

Train models for PBR material generation.

PBR Materials

Generate tileable materials and textures with text prompts—like brick or mosaic—for virtual scenes.

Edify Video

Train the Edify model to generate video.

Video

Generate high-fidelity videos with temporal consistency.

Edify Fine-Tuning

Optimized solution for customizing commercially safe, visual generative AI models.

Self Service

Automated workflow that’s easy to use and needs no coding.

High Performance

Fast tuning time and multi-GPU scaling for optimized performance.

Secure

Enterprise-grade security that ensures data and models are only accessible by you.

End-to-End Workflow

Data processing, training, evaluation, and deployment for custom stylization.

Deployed In Leading Cloud Service Providers Through NVIDIA DGX Cloud

AI Generators Powered by NVIDIA Edify

Pioneers have created commercially safe AI generators for images and 3D, revolutionizing creative workflows across industries with ongoing feature enhancements.

Getty Images | iStock

Advanced AI generators combine Getty Images’ pre-shot library for commercially safe and legally protected images with NVIDIA’s cutting-edge AI, enabling the rapid creation of high quality imagery from text or image prompts.

Advanced editing tools, such as inpainting and outpainting allow for rapid image modification. Customization APIs for model fine-tuning, depth, segmentation, and sketch are coming soon.

Commercially-safe service also compensates artists and creators for allowing their work to be part of the model.

Shutterstock

Shutterstock’s 3D AI Service lets both experienced and novice 3D creators quickly conceptualize and create assets for prototypes, set dressings, immersive environments, and more.

Trained on Shutterstock’s high-quality licensed data, it also provides indemnification, filters inappropriate content, and compensates contributing artists for each asset generated. You can integrate it into creative applications or plug-ins using Shutterstock APIs.

Leading Adopters

Deploying Custom Visual Foundation Models

Stay Up to Date With NVIDIA Picasso

Sign up to receive updates on optimizing, deploying, and customizing NVIDIA AI Foundation models for content generation.

Resources

Watch the Picasso Announcement

Did you miss NVIDIA CEO Jensen Huang’s presentation on generative AI? From large language models to digital avatars, catch up on everything NVIDIA is doing in generative AI.

Edify Models for Visual Content Generation

Join NVIDIA Researcher Ming-Yu as he explains the key ideas behind Edify model design and its applications to image and 3D generation.

 

Coming Soon

NVIDIA Edify is Entering a New Dimension

Read about how NVIDIA Edify is enabling partners with new generative AI Tools for 3D modeling.