VAEDecoder<T>
Models & Types · AiDotNet.Diffusion.VAE
Convolutional decoder for VAE that reconstructs images from latent space.
Inheritance: LayerBase<T> → VAEDecoder<T>
Implements: IShapeContract
For Beginners
The VAE decoder is like an intelligent image decompressor.
What it does step by step:
- Takes a compressed latent (e.g., 64x64x4)
- Post-quant conv: Expands channels (4 -> 512)
- Middle blocks: Extra processing at the bottleneck
- UpBlocks: Progressively doubles resolution while decreasing channels
- Block 1: 512 channels, 64x64 -> 64x64 (no upsample at start)
- Block 2: 512 channels, 64x64 -> 128x128
- Block 3: 256 channels, 128x128 -> 256x256
- Block 4: 128 channels, 256x256 -> 512x512
- Output: Produces 3-channel RGB image with tanh activation
The result is a high-resolution image reconstructed from the compressed latent.
How It Works
This implements the decoder portion of a VAE following the Stable Diffusion architecture:
- Post-quant convolution to expand latent channels
- Middle blocks at the bottleneck
- Multiple UpBlocks with transposed conv upsampling and ResBlocks
- Output convolution to produce final image channels
Constructors
| Constructor | Summary |
|---|---|
VAEDecoder(int outputChannels, int latentChannels, int baseChannels, int[] channelMults, int numResBlocks, int numGroups, int outputSpatialSize) |
Initializes a new instance of the VAEDecoder class. |
Properties
| Property | Summary |
|---|---|
bool SupportsTraining { get; } |
|
int LatentChannels { get; } |
Gets the number of latent channels. |
int OutputChannels { get; } |
Gets the number of output channels. |
int UpsampleFactor { get; } |
Gets the upsampling factor (spatial expansion from input to output). |
Methods
| Method | Summary |
|---|---|
IReadOnlyList<ILayer<T>> GetSubLayers() |
|
IReadOnlyList<OutputAxisContract> OutputAxesFor(int inputRank) |
|
ValueTask<Tensor<T>> ForwardAsync(Tensor<T> input, CancellationToken cancellationToken) |
Async overload of Forward — routes through the compile host’s PredictAsync. |
void InvalidateCompiledPlans() |
Bumps the structure-version so the next Forward drops stale plans. |
void ResetState() |
Resets the internal state of the decoder. |
void UpdateParameters(T learningRate) |
Updates all learnable parameters using gradient descent. |