Struct VaeDecoder 

pub struct VaeDecoder<T: Float> {
    pub post_quant_conv: Conv2d<T>,
    pub decoder: Decoder<T>,
    pub config: VaeDecoderConfig,
    /* private fields */
}

AutoencoderKL-style VAE decoder = post_quant_conv + Decoder.

The decoder pre-divides the latent by config.scaling_factor when using Self::decode_with_scaling, matching AutoencoderKL.decode(z).sample. Module::forward expects the latent already pre-divided (this matches the order of operations the SD pipeline performs externally).

Fields

post_quant_conv: Conv2d<T>

1x1 post-quant projection over the 4 latent channels.

decoder: Decoder<T>

The actual Decoder stack.

config: VaeDecoderConfig

Frozen config copy.

Implementations

impl<T: Float> VaeDecoder<T>

pub fn load_hf_state_dict( &mut self, hf_state: &StateDict<T>, strict: bool, ) -> FerrotorchResult<DropReport>

Load a HuggingFace AutoencoderKL state dict into this module.

Accepts both:

• post_quant_conv.* / decoder.* (bare-VAE layout, the normalised form the pin script produces)
• vae.post_quant_conv.* / vae.decoder.* (when bundled inside a full SD pipeline checkpoint)

Any other key (encoder, quant_conv, etc.) is recorded in the returned DropReport (or, in strict mode, surfaces as FerrotorchError::InvalidArgument).

Errors

Forwards whatever each sub-module’s load_state_dict returns (ShapeMismatch on a wrong-shape tensor, InvalidArgument in strict mode when a required tensor is missing). Strict mode will surface encoder.* / quant_conv.* / etc. as errors; callers with a full VAE checkpoint must pass strict=false.

impl<T: Float> VaeDecoder<T>

pub fn new(cfg: VaeDecoderConfig) -> FerrotorchResult<Self>

Build a randomly-initialized VaeDecoder.

Errors

Returns the underlying FerrotorchError on bad config dims.

pub fn decode_with_scaling( &self, latent: &Tensor<T>, ) -> FerrotorchResult<Tensor<T>>

Decode a latent with the SD scaling convention: image = decoder(post_quant_conv(z / scaling_factor)).

Errors

Returns FerrotorchError::ShapeMismatch when the input is not [B, latent_channels, H, W]. Propagates downstream op errors.

Trait Implementations

impl<T: Debug + Float> Debug for VaeDecoder<T>

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl<T: Float> Module<T> for VaeDecoder<T>

fn forward(&self, input: &Tensor<T>) -> FerrotorchResult<Tensor<T>>

Forward expects the post-scaled latent (the caller has already divided by scaling_factor).

fn parameters(&self) -> Vec<&Parameter<T>>

Iterate over all learnable parameters.

fn parameters_mut(&mut self) -> Vec<&mut Parameter<T>>

Iterate over all learnable parameters mutably.

fn named_parameters(&self) -> Vec<(String, &Parameter<T>)>

Named parameters for state dict serialization.

fn train(&mut self)

Set training mode. Affects dropout, batchnorm, etc.

fn eval(&mut self)

Set evaluation mode.

fn is_training(&self) -> bool

Whether the module is in training mode.

fn load_state_dict( &mut self, state: &StateDict<T>, strict: bool, ) -> FerrotorchResult<()>

Load parameters from a state dict.

fn to_device(&mut self, device: Device) -> Result<(), FerrotorchError>

Move all parameters and buffers to a device.

fn state_dict(&self) -> HashMap<String, Tensor<T>>

Export parameters and buffers as a state dict (torch parity).

fn buffers(&self) -> Vec<&Buffer<T>>

Iterate over all non-trainable buffers (e.g. running mean / variance in BatchNorm). Default returns empty — concrete modules with buffers override.

fn buffers_mut(&mut self) -> Vec<&mut Buffer<T>>

Mutable iteration over all buffers. Default returns empty.

fn named_buffers(&self) -> Vec<(String, &Buffer<T>)>

Named buffers (dot-separated paths for nested modules). Default returns empty.

fn as_any(&self) -> Option<&(dyn Any + 'static)>

Downcast hook for type-erased buffer-loader dispatch. (#984)

fn children(&self) -> Vec<&dyn Module<T>>

Direct child modules. Default returns empty (leaf module).

fn named_children(&self) -> Vec<(String, &dyn Module<T>)>

Direct child modules with their attribute names. Default returns empty.

fn modules(&self) -> Vec<&dyn Module<T>>

where Self: Sized,

All modules in this subtree, depth-first (self first, then each child’s descendants in order).

fn descendants_dyn(&self) -> Vec<&dyn Module<T>>

All strict descendants of self in depth-first order. Object-safe.

fn named_modules(&self) -> Vec<(String, &dyn Module<T>)>

where Self: Sized,

All modules in this subtree with dot-separated path names. The root is named ""; children paths are joined with ..

fn named_descendants_dyn(&self) -> Vec<(String, &dyn Module<T>)>

Strict descendants with dot-paths. Object-safe.

fn with_forward_hook( self, hook: Box<dyn Fn(&Tensor<T>, &Tensor<T>) + Send + Sync>, ) -> (HookedModule<Self, T>, HookHandle)

where Self: Sized,

Wrap this module in a HookedModule and register a forward hook. Returns the wrapper paired with a HookHandle that can be used to remove the hook later. The wrapper implements Module<T> itself, so it slots into any place the original module did. Mirrors torch.nn.Module.register_forward_hook.

fn with_forward_pre_hook( self, hook: Box<dyn Fn(&Tensor<T>) -> Result<Tensor<T>, FerrotorchError> + Send + Sync>, ) -> (HookedModule<Self, T>, HookHandle)

where Self: Sized,

Wrap this module in a HookedModule and register a forward pre-hook. See Self::with_forward_hook. Mirrors torch.nn.Module.register_forward_pre_hook.

fn with_backward_hook( self, hook: Box<dyn Fn(&Tensor<T>, &Tensor<T>) + Send + Sync>, ) -> (HookedModule<Self, T>, HookHandle)

where Self: Sized,

Wrap this module in a HookedModule and register a backward hook. See Self::with_forward_hook. Mirrors torch.nn.Module.register_backward_hook.

fn zero_grad(&self) -> Result<(), FerrotorchError>

Set the gradient of every parameter to None.

fn requires_grad_(&mut self, requires_grad: bool)

Toggle requires_grad on every parameter (freeze / unfreeze the module). Mirrors torch.nn.Module.requires_grad_.

fn apply_to_parameters(&mut self, f: &mut dyn FnMut(&mut Parameter<T>))

Apply a function to every parameter in this module. Mirrors torch.nn.Module.apply for the parameter case (true apply recurses over all submodules; the recursive form requires &mut dyn Module which conflicts with this trait’s &mut self borrow).