Pi zddlmZddlmZmZmZddddgdddd d f d ed ed ededeedededededefdZdS))List)FluxAutoencoder FluxDecoder FluxEncoder)r r gxz,C?g=U? resolutionch_inch_outch_basech_multsch_zn_layers_per_resample_block scale_factor shift_factorreturnc fd|D} t||| |||} t||tt| |dz||} t |||f| | S)a The image autoencoder for all current Flux diffusion models: - FLUX.1-dev - FLUX.1-schnell - FLUX.1-Canny-dev - FLUX.1-Depth-dev - FLUX.1-Fill-dev ch = number of channels (size of the channel dimension) Args: resolution (int): The height/width of the square input image. ch_in (int): The number of channels of the input image. ch_out (int): The number of channels of the output image. ch_base (int): The base number of channels. This gets multiplied by `ch_mult` values to get the number of inner channels during downsampling/upsampling. ch_mults (List[int]): The channel multiple per downsample/upsample block. This gets multiplied by `ch_base` to get the number of inner channels during downsampling/upsampling. ch_z (int): The number of latent channels (dimension of the latent vector `z`). n_layers_per_resample_block (int): Number of resnet layers per downsample/upsample block. scale_factor (float): Constant for scaling `z`. shift_factor (float): Constant for shifting `z`. Returns: FluxAutoencoder cg|]}|zSr).0multrs y/home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/torchtune/models/flux/_model_builders.py z&flux_1_autoencoder..0s4444$444)rrchannelsn_layers_per_down_blockrrr )rrr n_layers_per_up_blockrr) img_shapeencoderdecoder)rrlistreversedr) rrrrrrrrrr r$r%s ` rflux_1_autoencoderr( sJ54448444H  ;!! G hx(())9A=!!G *j1   rN) typingr"torchtune.models.flux._autoencoderrrrintfloatr(rrrr-s XXXXXXXXXX&,,'(  >>> > > > 3i >  >"%>>>>>>>>>r