Anima FeRA loader (author-faithful — Yin et al., arXiv:2511.17979). Installs a single model-level forward_pre_hook that computes the per-step Frequency-Energy…

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

adapter

strength

Anima FeRA loader (author-faithful — Yin et al., arXiv:2511.17979). Installs a single model-level forward_pre_hook that computes the per-step Frequency-Energy Indicator and global router gates, plus per-Linear forward_hooks that add the gated stacked-expert correction. Mutually exclusive with HydraLoRA — for FEI-on-Hydra checkpoints, use AnimaAdapterLoader.

Name	Type	Default	Description
model	MODEL		—
adapter	COMBO		FeRA checkpoint — either author-faithful (networks.methods.fera; router.net.* + lora_unet_.lora_down/lora_up) or plan2 stacked_experts_global_fei (global_router.net. + lora_unet_.lora_downs.{i}.weight / .lora_ups.{i}.weight, typically named _moe.safetensors). Both use an independent-A stacked-expert layout with a single network-level FEI router.
strength	FLOAT	1.00-2–2	Scales the gated expert correction added to each adapted Linear (mirrors the training-side multiplier; 0 short-circuits to the frozen base).

Anima FeRA Loader

Inputs (3)

Outputs (1)