r""" Enable sliced VAE decoding. When this option is enabled, the VAE will split the input tensor in slices to compute decoding in sev

r""" Enable tiled VAE decoding. When this option is enabled, the VAE will split the input tensor into tiles to compute decoding and en

Forward process. Args: x: tensor of shape [..., dim] Returns: embedding: an embedding of `x` of shape [...,

The [`HunyuanDiT2DModel`] forward method. Args: hidden_states (`torch.Tensor` of shape `(batch size, dim, height, width)`):

Enables fused QKV projections. For self-attention modules, all projection matrices (i.e., query, key, value) are fused. For cross-att

Enables fused QKV projections. For self-attention modules, all projection matrices (i.e., query, key, value) are fused. For cross-att

Enables fused QKV projections. For self-attention modules, all projection matrices (i.e., query, key, value) are fused. For cross-att

Forward function for the noise scaling in the flow matching.

Sets the begin index for the scheduler. This function should be run from pipeline before the inference. Args: begin_inde

Disables custom attention processors and sets the default attention implementation.

Disables custom attention processors and sets the default attention implementation.

The index counter for current timestep. It will increase 1 after each scheduler step.

Disable QKV projection fusion if enabled. <Tip warning={true}> This API is 🧪 experimental. </Tip> Args:

Disables the fused QKV projection if enabled. <Tip warning={true}> This API is 🧪 experimental. </Tip>

Disables the fused QKV projection if enabled. <Tip warning={true}> This API is 🧪 experimental. </Tip>