FLUX.2 double-stream (MMDiT) block
Description
Image and text streams with externally supplied (shift, scale, gate) modulation triples, joint attention (txt first), and SwiGLU feed-forwards. Reference: Flux2TransformerBlock.
Usage
flux2_double_block(dim, num_attention_heads, attention_head_dim, mlp_ratio = 3,
eps = 1e-06, bias = FALSE)
Arguments
dim: Integer. Model dimension.num_attention_heads: Integer. Attention heads.attention_head_dim: Integer. Per-head dimension.mlp_ratio: Numeric. FF multiplier (FLUX.2: 3.0).eps: Numeric. Norm epsilon.bias: Logical.
Value
Module whose forward(hidden_states, encoder_hidden_states,
temb_mod_img, temb_mod_txt, image_rotary_emb) returns
list(encoder_hidden_states, hidden_states).