Generative AI with Diffusion Models (NV-GEN-AI-DM)
- Course Code GK847006
- Duration 1 day
Course Delivery
Course Delivery
This course is available in the following formats:
-
Company Event
Event at company
-
Virtual Learning
Learning that is virtual
Request this course in a different delivery format.
Course Overview
TopTake a deeper dive into denoising diffusion models, which are a popular choice for text-to-image pipelines.
Thanks to improvements in computing power and scientific theory, generative AI is more accessible than ever before. Generative AI plays a significant role across industries due to its numerous applications, such as creative content generation, data augmentation, simulation and planning, anomaly detection, drug discovery, personalized recommendations, and more. In this course, learners will take a deeper dive into denoising diffusion models, which are a popular choice for text-to-image pipelines.
Virtual Learning
This interactive training can be taken from any location, your office or home and is delivered by a trainer. This training does not have any delegates in the class with the instructor, since all delegates are virtually connected. Virtual delegates do not travel to this course, Global Knowledge will send you all the information needed before the start of the course and you can test the logins.
Course Schedule
TopCourse Objectives
Top- Build a U-Net to generate images from pure noise
- Improve the quality of generated images with the denoising diffusion process
- Control the image output with context embeddings
- Generate images from English text prompts using the Contrastive Language—Image
- Pretraining (CLIP) neural network
Course Content
TopModule 1: From U-Net to Diffusion
- Build a U-Net architecture.
- Train a model to remove noise from an image.
Module 2:Diffusion Models
- Define the forward diffusion function.
- Update the U-Net architecture to accommodate a timestep.
- Define a reverse diffusion function.
Module 3: Optimizations · Implement Group Normalization.
- Implement GELU.
- Implement Rearrange Pooling.
- Implement Sinusoidal Position Embeddings.
Module 4: Classifier-Free Diffusion Guidance
- Add categorical embeddings to a U-Net.
- Train a model with a Bernoulli mask.
Module 5: CLIP
- Learn how to use CLIP Encodings.
- Use CLIP to create a text-to-image neural network.
