NVIDIA launches AI Blueprint for 3D image creation in Blender
NVIDIA has introduced a new AI Blueprint that enables users to generate images guided by 3D scenes using Blender.
This tool combines basic 3D scene design with depth mapping to help control image composition more precisely during AI generation. At the core of the process is FLUX.1-dev, an AI model developed by Black Forest Labs, which interprets the scene's spatial layout alongside text prompts to produce visuals that match the intended design.
Depth maps play a crucial role by providing the spatial context needed for the model to understand scene structure. This technique simplifies the process by removing the need for detailed textures or complex objects, instead relying on general spatial information. With the scenes rendered in 3D, users have the flexibility to move elements and adjust camera angles to suit their creative goals.
The Blueprint includes an NVIDIA NIM microservice that helps deploy the FLUX.1-dev model efficiently on RTX GPUs, using TensorRT for faster inference. It's packaged with an installer and comprehensive deployment instructions, making it accessible for AI artists looking to integrate generative tools into their workflow.
Beyond entry-level users, the Blueprint is also designed to accommodate advanced developers. It offers a customisable pipeline that can be modified for more sophisticated needs. NVIDIA provides supporting materials like sample assets, detailed documentation, and a preconfigured environment to help streamline experimentation and creation.
Optimised for NVIDIA RTX AI PCs and workstations, the solution benefits from the company's Blackwell architecture. The FLUX.1-dev model has been fine-tuned using TensorRT and quantised to FP4 precision, resulting in more than double the inference speed compared to traditional FP16 PyTorch implementations. There are also FP8 model versions tailored for GPUs based on the Ada Lovelace architecture, further expanding compatibility and performance.
Quantising to FP4 significantly reduces the model size, lowering memory requirements while maintaining high performance, cutting VRAM needs by more than half compared to FP16. Currently, NVIDIA offers ten NIM microservices across areas like image generation, natural language processing, speech AI, and computer vision. The company plans to continue building out its portfolio with more AI blueprints and services designed to accelerate creative and technical workflows.
Try Our AI Features
Explore what Daily8 AI can do for you:
Comments
No comments yet...
Related Articles
Techday NZ
2 days ago
- Techday NZ
Cloudera joins AI-RAN Alliance to boost AI in telecoms sector
Cloudera has joined the AI-RAN Alliance, a global consortium focused on integrating artificial intelligence into telecommunications infrastructure, with particular relevance for service providers in Australia and New Zealand. The AI-RAN Alliance, whose founding members include NVIDIA, also counts Dell, SoftBank, T-Mobile, KT and LG U+ among its participants. The group aims to address the integration of AI within current and emerging telecommunications networks and to standardise the use of AI for optimising shared infrastructure, accelerating edge AI application development, and providing reliable deployment models for AI in telecoms. Cloudera's entry into the alliance follows a period of growing interest among telecommunications providers in using AI to optimise network operations and reduce operational costs. Virtualisation and new infrastructure architectures are key drivers, and AI is seen as an important means of improving service efficiency and enabling new business opportunities for operators. The complexities associated with deploying AI at scale across distributed edge environments present significant challenges for the sector. Telecoms need to take an enterprise-wide approach to operationalise these technologies within the radio access network (RAN) if they are to unlock commercial benefits. As a member of the AI-RAN Alliance, Cloudera will participate in the 'Data for AI-RAN' working group, which is tasked with standardising data orchestration, large language model driven network automation, and hybrid-enabled MLOps across telecommunications and AI workloads. According to the company, this involvement will aim to align data and AI pipeline development with operational requirements, thereby supporting quicker innovation and the deployment of AI-native use cases. Cloudera will also support the Alliance's three stated objectives-AI-for-RAN, AI-and-RAN, and AI-on-RAN-and will work to accelerate the use of AI in real-world scenarios. Potential applications include service level agreement-driven network availability and real-time anomaly detection. The company plans to develop and evaluate reference architectures that telecoms operators can deploy in live environments, facilitating shorter development cycles and improving collaboration around model reusability. Another focus is demonstrating the use of Cloudera's platform for real-time decision-making at the network edge. This will involve enabling scalable preparation of training data and MLOps, as well as operationalising AI inference at scale, while maintaining governance and edge-to-core orchestration. Keir Garrett, Regional Vice President for Cloudera Australia and New Zealand, said, "Joining the AI-RAN Alliance enhances our ability to drive innovation and operational excellence for telecommunications providers across Australia and New Zealand. Leading telcos are already leveraging AI to optimise networks, improve engagement, and streamline operations, with edge computing enabling scalable transformation. Now, we're focused on guiding them through the next phase-unlocking greater value while future-proofing infrastructure. Just as smart highways enhance outdated roads, this shift ensures telcos meet growing user demand with speed, reliability, and adaptability-paving the way for the future of connectivity." Speaking about the company's contribution to the Alliance, Abhas Ricky, Chief Strategy Officer at Cloudera, commented, "Cloudera is proud to bring its data and AI expertise to the AI-RAN Alliance. The network is the heart of the telecom business, both in driving margin growth and in service transformation, and AI can unlock substantial value across those dimensions. Given our leadership in the domain - having powered data and AI automation strategies for hundreds of telecommunications providers around the world, we now look forward to accelerating innovation alongside fellow AI-RAN Alliance members and bringing our customers along. Our goal is to help define the data standards, orchestration models, and reference architectures that will power intelligent, adaptive, and AI-native networks of the future." Jemin Chung, Vice President Network Strategy at KT, said, "We are proud to collaborate with Cloudera and fellow AI-RAN Alliance members in the 'Data for AI-RAN' working group. As AI becomes increasingly central to next-generation networks, the ability to harness data securely and at scale will be a key differentiator. Through this initiative, we look forward to defining best practices that enable AI-centric RAN evolution and improve operational intelligence." Dr Alex Jinsung Choi, Principal Fellow, SoftBank's Research Institute of Advanced Technology, and Chair of the AI-RAN Alliance, said, "Cloudera is an incredible addition to the AI-RAN Alliance, which has grown rapidly as demand for improved AI access and success increases across the industry. The company's leadership in data and AI, combined with their extensive telecommunications footprint, will play a vital role in advancing our shared vision of intelligent, AI-native networks."
Techday NZ
4 days ago
- Techday NZ
Illumio & NVIDIA partner to boost Zero Trust for critical infrastructure
Illumio has announced a strategic integration with NVIDIA aimed at helping organisations secure critical infrastructure and improve their Zero Trust maturity by bringing together breach containment capabilities with the NVIDIA BlueField networking platform. The integration allows critical infrastructure organisations to deploy Illumio directly on NVIDIA BlueField, giving security teams comprehensive visibility into network dependencies and enabling precise security controls at both the host and network levels. With this collaboration, organisations can benefit from deep visibility into network traffic and enhanced protection of critical assets. The solution leverages NVIDIA BlueField Data Processing Units (DPUs) as enforcement points for Zero Trust, thereby simplifying the protection of operational technology (OT) and information technology (IT) systems while helping organisations ensure operational continuity and meet compliance standards. In the future, Illumio's platform will also allow organisations to use its AI-driven insights to identify risks and attacker behaviours, enabling rapid threat detection within Industrial Control Systems (ICS) and OT environments. The collaboration is positioned against the backdrop of growing cyber threats and heightened global regulatory expectations for critical infrastructure. According to Illumio, the integration delivers several key benefits, including enhanced visibility and policy enforcement for traffic within and between IT and OT networks. Using Illumio's labelling architecture, organisations can visualise all traffic to and from OT systems equipped with NVIDIA BlueField to better understand system communications across the infrastructure. The integration also promises rapid deployment of Zero Trust segmentation in OT and ICS settings, designed to reduce complexity, limit lateral movement risks, and contain potential breaches. Additional benefits cited include improved compliance and operational resilience, as organisations can identify assets, monitor traffic, and enforce security policies across converged IT/OT environments without impacting system performance or requiring major architectural changes. The combined solution is intended to provide consistent and reliable microsegmentation across varying environments while maintaining uptime and resilience. Todd Palmer, Senior Vice President of Global Partner Sales and Alliances at Illumio, stated, "The integration between Illumio and NVIDIA will significantly strengthen security for cyber-physical systems and bring us closer to achieving our vision of a world without cyber disasters. Critical infrastructure is under threat like never before. Together with NVIDIA, we're making it easier for organizations to protect critical systems, ensure operational continuity, and meet stringent compliance requirements in an increasingly complex landscape." Ofir Arkin, Senior Distinguished Architect for Cybersecurity at NVIDIA, said, "Cyber risks against critical infrastructure are more sophisticated and disruptive than ever, and lateral movement remains a key factor in successful attacks. Integrating the Illumio and NVIDIA BlueField platforms enables organizations to enhance visibility and control across IT and OT networks, reduce risk, contain attacks, and strengthen operational resilience." Illumio was named as a leader in The Forrester Wave: Microsegmentation Solutions, Q3 2024. The company is part of the NVIDIA partner ecosystem, offering a platform built on an AI security graph that includes Illumio Insights for AI-driven cloud detection and response, as well as Illumio Segmentation aimed at facilitating Zero Trust strategies. The partnership targets organisations responsible for critical infrastructure, which face increasing operational risks from sophisticated cyber threats. The converged approach to IT and OT security seeks to enable these organisations to identify risks, contain threats before they spread, and comply with regulatory requirements across complex operational environments.
National Business Review
5 days ago
- National Business Review
Meridian ends billing software project in favour of Kraken
Electricity generator and retailer Meridian has abandoned its in-house retail billing platform Flux in favour of the Kraken platform provided by UK-based Octopus Energy Group. In a statement to the NZX Meridian said 53 jobs would go at Flux, reducing its workforce from 121 to 68. Remaining staff
