NVIDIA DLI Generative AI with Diffusion Models Training Course
Key information
Upcoming sessions
Would you like to schedule this training on a specific date? Contact us by email or via the contact form.
Description of the training: NVIDIA DLI Generative AI with Diffusion Models Training Course
Diffusion models are the foundation of modern visual generative AI (Stable Diffusion, DALL·E, etc.). They learn to generate images or videos from random noise, guided by a text prompt. This official NVIDIA DLI course helps you understand and practise these models, with MFE-IT as your training partner.
What is the difference between LLMs and diffusion models?LLMs generate text from text (sequences of tokens). Diffusion models generate images/videos from text prompts. The two worlds are converging (multimodal). The MFE-IT training bridges LLMs, diffusion and multimodal agents.
What are the prerequisites for this training?A Python foundation and AI/ML literacy are required. Prior knowledge of PyTorch / TensorFlow and deep learning concepts are a plus. MFE-IT adapts the pace to the profile of the teams.
How long is this NVIDIA DLI Generative AI training at MFE-IT?The training lasts 1 day (7 hours), delivered remotely or on-site. Official NVIDIA DLI format, focused on labs and understanding diffusion models.
{"@context":"https://schema.org","@type":"FAQPage","mainEntity":[{"@type":"Question","name":"What are diffusion models?","acceptedAnswer":{"@type":"Answer","text":"Diffusion models are the foundation of modern visual generative AI (Stable Diffusion, DALL·E, etc.). They learn to generate images or videos from random noise, guided by a text prompt. This official NVIDIA DLI course helps you understand and practise these models, with MFE-IT as your training partner."}},{"@type":"Question","name":"What is the difference between LLMs and diffusion models?","acceptedAnswer":{"@type":"Answer","text":"LLMs generate text from text (sequences of tokens). Diffusion models generate images/videos from text prompts. The two worlds are converging (multimodal). The MFE-IT training bridges LLMs, diffusion and multimodal agents."}},{"@type":"Question","name":"What are the prerequisites for this training?","acceptedAnswer":{"@type":"Answer","text":"A Python foundation and AI/ML literacy are required. Prior knowledge of PyTorch / TensorFlow and deep learning concepts are a plus. MFE-IT adapts the pace to the profile of the teams."}},{"@type":"Question","name":"How long is this NVIDIA DLI Generative AI training at MFE-IT?","acceptedAnswer":{"@type":"Answer","text":"The training lasts 1 day (7 hours), delivered remotely or on-site. Official NVIDIA DLI format, focused on labs and understanding diffusion models."}}]} .elementor-accordion .elementor-tab-title .elementor-accordion-icon{margin-right:10px}.elementor-accordion .elementor-tab-title .elementor-accordion-icon + a,.elementor-accordion .elementor-tab-title .elementor-accordion-title{padding-left:4px}Good to know
Training delivered in French, original content in English. Our sessions are guaranteed from a single registrant, with no risk of postponement (except in cases of force majeure). A prior interview takes place between the participant and a company representative to fully take into account the participant’s profile (level, needs, professional context, challenges, etc.). Evaluation: during the training, the trainer assesses participants’ learning progress through quizzes, role-plays and practical exercises. Participants receive a certificate of achievement at the end of the training. This training is part of our catalogue. Discover our other AI training courses to fully harness the potential of machine learning, LLMs and generative AI.
Objectives of the training: NVIDIA DLI Generative AI with Diffusion Models Training Course
- By the end of this training:
- Understand the mathematical principles of diffusion models
- Train a diffusion model for image generation
- Apply text conditioning (text-to-image)
- Adapt pre-trained models with fine-tuning techniques
- Optimise generation on NVIDIA GPUs for real-time performance
Prerequisites of the training: NVIDIA DLI Generative AI with Diffusion Models Training Course
Experience in Python and a grasp of deep learning concepts (CNNs, model training). The NVIDIA DLI Fundamentals of Deep Learning training is strongly recommended. Because every participant is unique, a personalised interview with our expert allows us to design a training course perfectly aligned with their goals, level and professional challenges.
Target audience of the training: NVIDIA DLI Generative AI with Diffusion Models Training Course
AI developers, data scientists, computer vision researchers, tech creatives and professionals wishing to master AI image generation.
Detailed programme of the training: NVIDIA DLI Generative AI with Diffusion Models Training Course
Fundamentals of diffusion models
- Principles of the diffusion process: from noise to image
- U-Net architecture and cross-attention
- Comparison with GANs and VAEs
- Lab: exploring a pre-trained diffusion model
Training a diffusion model
- Data preparation and training pipeline
- Noise scheduler and sampling strategies
- Quality evaluation: FID, IS
- Lab: training a diffusion model on GPU
Conditioned generation and text-to-image
- Text conditioning with CLIP
- Text-to-image generation and inpainting
- Stable Diffusion: architecture and usage
- Lab: generating text-guided images
Fine-tuning and deployment
- Fine-tuning with DreamBooth and LoRA
- Inference optimisation with TensorRT
- Production deployment on NVIDIA GPUs
- Final assessment for the NVIDIA DLI certificate
Course highlights
- Focuses on generative AI with diffusion models
- Covers the mathematical principles behind diffusion models
- Delivers a 100% hands-on, GPU-based learning experience
- Awards a recognised NVIDIA DLI certificate
FAQ
What are diffusion models?
Diffusion models are the foundation of modern visual generative AI (Stable Diffusion, DALL·E, etc.). They learn to generate images or videos from random noise, guided by a text prompt. This official NVIDIA DLI course helps you understand and practise these models, with MFE-IT as your training partner.
What is the difference between LLMs and diffusion models?
LLMs generate text from text (sequences of tokens). Diffusion models generate images/videos from text prompts. The two worlds are converging (multimodal). The MFE-IT training bridges LLMs, diffusion and multimodal agents.
What are the prerequisites for this training?
A Python foundation and AI/ML literacy are required. Prior knowledge of PyTorch / TensorFlow and deep learning concepts are a plus. MFE-IT adapts the pace to the profile of the teams.
How long is this NVIDIA DLI Generative AI training at MFE-IT?
The training lasts 1 day (7 hours), delivered remotely or on-site. Official NVIDIA DLI format, focused on labs and understanding diffusion models.