Nodes/AsymFLUX2/AsymFLUX2 Apply Adapter
ComfyUI Node

AsymFLUX2 Apply Adapter

Turns a stock FLUX.2-klein-base-9B MODEL into AsymFLUX.2. Drop the adapter (Lakonik/AsymFLUX.2-klein-9B diffusion_pytorch_model.safetensors, ~707 MB) into ComfyUI/models/loras/. Chain: Load Diffusion Model -> this node -> KSampler. Use AsymFLUX2 Empty Pixel Latent for the latent input, AsymFLUX2 Oklab Decode after the sampler.

By Nynxz·Created 3 months ago·Updated 3 months ago· 12
AsymFLUX2 Apply Adapter
  • model
  • model
adapter
shift17.0
adapter_strength1.00
orthogonal_guidance1.00
clamp_denoisedtrue
CategoryAsymFLUX2/loaders

Inputs (6)

NameTypeDefaultDescription
modelMODELFLUX.2-klein-base-9B from a stock Load Diffusion Model node.
adapterCOMBOAsymFLUX.2-klein adapter safetensors (in models/loras/).
shiftFLOAT17.00.1–100Flow shift (paper convention; converted to comfy mu = log(shift) internally).
adapter_strengthFLOAT1.00-2–2LoRA strength applied to the rank-256 LoRA. 1.0 = full strength.
orthogonal_guidanceFLOAT1.000–2AsymFlow orthogonal CFG bias strength. 1.0 = upstream demo default. 0.0 = standard CFG.
clamp_denoisedBOOLEANtruePer-step Oklab gamut clamp on the x0 estimate. Prevents color drift across the sampling loop. Disable if using uni_pc — see README.

Outputs (1)

NameTypeDescription
modelMODEL