vae

package
v0.32.3 Latest Latest
Warning

This package is not in the latest version of its module.

Go to latest
Published: Jul 23, 2026 License: MIT Imports: 1 Imported by: 0

Documentation

Overview

Package vae provides shared utilities for VAE (Variational Autoencoder) operations.

Index

Constants

This section is empty.

Variables

This section is empty.

Functions

func DecodeTiled

func DecodeTiled(latents *mlx.Array, cfg *TilingConfig, decoder func(*mlx.Array) *mlx.Array) *mlx.Array

DecodeTiled decodes latents using tiled processing with overlap blending. This reduces memory usage for large images by processing in overlapping tiles.

Parameters:

  • latents: [1, H, W, C] latent tensor in NHWC format
  • cfg: tiling configuration (tile size and overlap)
  • decoder: function to decode a single tile [1, H, W, C] -> [1, H*scale, W*scale, 3]

Returns: [1, 3, H*scale, W*scale] decoded image in NCHW format

Types

type TilingConfig

type TilingConfig struct {
	TileSize int32 // Tile size in latent space (e.g., 64 latent → 512 pixels for 8x VAE)
	Overlap  int32 // Overlap in latent space (e.g., 16 latent = 25% of 64)
}

TilingConfig holds configuration for tiled VAE decoding. This is a general technique to reduce memory usage when decoding large latents.

func DefaultTilingConfig

func DefaultTilingConfig() *TilingConfig

DefaultTilingConfig returns reasonable defaults matching diffusers. tile_latent_min_size=64, tile_overlap_factor=0.25

Jump to

Keyboard shortcuts

? : This menu
/ : Search site
f or F : Jump to
y or Y : Canonical URL