Generative AI with Diffusion ModelsGAIDMNVNvidiaNV-GAIDM1.0<ul>
<li>Build a U-Net to generate images from pure noise</li><li>Improve the quality of generated images with the denoising diffusion process</li><li>Control the image output with context embeddings</li><li>Generate images from English text prompts using the Contrastive Language—Image Pretraining (CLIP) neural network</li></ul><ul>
<li>A basic understanding of Deep Learning Concepts.</li><li>Familiarity with a Deep Learning framework such as TensorFlow, PyTorch, or Keras. This course uses PyTorch.</li></ul><p><strong>From U-Net to Diffusion</strong>
</p>
<ul>
<li>Build a U-Net architecture.</li><li>Train a model to remove noise from an image.</li></ul><p><strong>Diffusion Models</strong>
</p>
<ul>
<li>Define the forward diffusion function.</li><li>Update the U-Net architecture to accommodate a timestep.</li><li>Define a reverse diffusion function.</li></ul><p><strong>Optimizations</strong>
</p>
<ul>
<li>Implement Group Normalization.</li><li>Implement GELU.</li><li>Implement Rearrange Pooling.</li><li>Implement Sinusoidal Position Embeddings.</li></ul><p><strong>Classifier-Free Diffusion Guidance </strong>
</p>
<ul>
<li>Add categorical embeddings to a U-Net.</li><li>Train a model with a Bernoulli mask.</li></ul><p><strong>CLIP</strong>
</p>
<ul>
<li>Learn how to use CLIP Encodings.</li><li>Use CLIP to create a text-to-image neural network.</li></ul>- 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- A basic understanding of Deep Learning Concepts.
- Familiarity with a Deep Learning framework such as TensorFlow, PyTorch, or Keras. This course uses PyTorch.From U-Net to Diffusion
- Build a U-Net architecture.
- Train a model to remove noise from an image.
Diffusion Models
- Define the forward diffusion function.
- Update the U-Net architecture to accommodate a timestep.
- Define a reverse diffusion function.
Optimizations
- Implement Group Normalization.
- Implement GELU.
- Implement Rearrange Pooling.
- Implement Sinusoidal Position Embeddings.
Classifier-Free Diffusion Guidance
- Add categorical embeddings to a U-Net.
- Train a model with a Bernoulli mask.
CLIP
- Learn how to use CLIP Encodings.
- Use CLIP to create a text-to-image neural network.1 day500.00500.00500.00500.00500.00420.00500.00690.00