Runs the Anima DiT with an fp32 residual stream, modulation, q / k norms, RoPE, embedder and head around the block GEMMs (bf16, INT8 or fp8). No weight is…

Anima loader nodes for ComfyUI. AnimaAdapterLoader auto-detects LoRA, HydraLoRA multi-head with live σ-conditional and FeRA-style FEI-conditional routing, ChimeraHydra dual-pool routing (per-Linear content router + network-level FreqRouter on FEI+σ), and LoReFT residual-stream edits. AnimaFeraLoader handles FeRA (Yin et al., arXiv:2511.17979) — both the author-faithful networks.methods.fera format and the plan2 stacked_experts_global_fei format with global router on the latent's spectral energy + independent stacked experts per Linear. AnimaSoftTokensLoader handles SoftREPA-parameterization soft tokens (Lee et al., arXiv:2503.08250) — per-layer × per-timestep-bucket learned tokens spliced into the crossattn embedding inside the first n_layers DiT blocks. Three single-purpose nodes; chain via the MODEL socket.

Anima Adapter Loader

model

Runs the Anima DiT with an fp32 residual stream, modulation, q / k norms, RoPE, embedder and head around the block GEMMs (bf16, INT8 or fp8). No weight is reloaded. Anima Adapter Loader applies the same patch through its stream input.

Anima fp32 Stream

Inputs (1)

Outputs (1)