Nodes/comfyui-watdafox-nodes/BF Parameters Simple (watdafox)
ComfyUI Node

BF Parameters Simple (watdafox)

Seed, steps, cfg, two denoise values, done

By postosh·Created 9 months ago·Updated 8 months ago· 0
BF Parameters Simple (watdafox)
    • seed
    • steps
    • cfg
    • sampler
    • scheduler
    • dt_scheduler
    • denoise1
    • denoise2
    • str_sampler
    • str_scheduler
    seed0
    steps30
    cfg7.0
    sampler
    scheduler
    dt_scheduler
    denoise10.20
    denoise20.40

    BF Parameters Simple is the trimmed-down member of this pack's parameter-pack family: one seed, one steps, one cfg, one sampler, one scheduler, one detailer scheduler, and two denoise values. Where the full BF Parameters node triplicates everything for base/upscale/detail passes, this one trusts that most people really just need the base pass settings plus a couple of denoise strengths.

    That "two denoise values" design is the tell. Defaults are denoise1 at 0.2 and denoise2 at 0.4 - the classic low-denoise strengths for an upscale-ish second pass and a face/detail pass. You're meant to wire one into your main sampler and the other into your detailer (FaceDetailer-style) sampler, with a single sampler/scheduler pair shared across both. It's the "I don't want three control panels, I want one clean widget" philosophy, and for a huge chunk of workflows it's honestly the right amount of configuration.

    How it works

    The required inputs are seed (with control_after_generate), steps, cfg, sampler (all 44 samplers), scheduler (the standard 9), dt_scheduler (the extended detailer list - AYS SDXL, OSS FLUX, and friends), denoise1, denoise2. Outputs mirror every input and add str_sampler/str_scheduler as string versions for logging. That's the whole thing - no upscale group, no per-pass cfg. If you need per-pass sampler choices or three sets of everything, step up to the full BF Parameters node instead.

    The dt_scheduler input is the detail worth knowing about: unlike the plain scheduler, it's fed from ComfyUI's detailer-aware scheduler list, so you can hand your detail pass an Align Your Steps schedule that a stock KSampler dropdown won't even show you.

    What you'll set

    • seed - your base seed; the control_after_generate flag handles rerolling.
    • denoise1 (0.2) and denoise2 (0.4) - the two strengths that define your two-pass behavior.
    • sampler / scheduler / dt_scheduler - the shared and detailer schedules.

    Wire sampler/scheduler/denoise1 into your base sampler and sampler/dt_scheduler/denoise2 into the detailer pass. Category: watdafox/parameter.

    Install

    cd ComfyUI/custom_nodes
    git clone https://github.com/OhSeongHyeon/comfyui-watdafox-nodes.git
    

    Restart ComfyUI, or ComfyUI Manager → "comfyui-watdafox-nodes". No pip dependencies, no model downloads.

    When this is the right pick

    If your workflow is base → one refinement pass and you keep fiddling with two denoise sliders, this is the sweet spot - minimal surface, the settings you actually touch. It's the one I'd reach for over the full BF Parameters unless I genuinely needed a separate upscale cfg/steps/sampler block. Just remember it's a value router, not a loader: it changes nothing until you wire its outputs into samplers that actually run.

    Categorywatdafox/parameter

    Inputs (8)

    NameTypeDefaultDescription
    seedINT00–18446744073709550000
    stepsINT301–1000
    cfgFLOAT7.00–100
    samplerCOMBO44 options: euler, euler_cfg_pp, euler_ancestral, euler_ancestral_cfg_pp, heun, heunpp2, +38
    schedulerCOMBO9 options: simple, sgm_uniform, karras, exponential, ddim_uniform, beta, +3
    dt_schedulerCOMBO17 options: simple, sgm_uniform, karras, exponential, ddim_uniform, beta, +11
    denoise1FLOAT0.200–1
    denoise2FLOAT0.400–1

    Outputs (10)

    NameTypeDescription
    seedINT
    stepsINT
    cfgFLOAT
    samplereuler,euler_cfg_pp,euler_ancestral,euler_ancestral_cfg_pp,heun,heunpp2,exp_heun_2_x0,exp_heun_2_x0_sde,dpm_2,dpm_2_ancestral,lms,dpm_fast,dpm_adaptive,dpmpp_2s_ancestral,dpmpp_2s_ancestral_cfg_pp,dpmpp_sde,dpmpp_sde_gpu,dpmpp_2m,dpmpp_2m_cfg_pp,dpmpp_2m_sde,dpmpp_2m_sde_gpu,dpmpp_2m_sde_heun,dpmpp_2m_sde_heun_gpu,dpmpp_3m_sde,dpmpp_3m_sde_gpu,ddpm,lcm,ipndm,ipndm_v,deis,res_multistep,res_multistep_cfg_pp,res_multistep_ancestral,res_multistep_ancestral_cfg_pp,gradient_estimation,gradient_estimation_cfg_pp,er_sde,seeds_2,seeds_3,sa_solver,sa_solver_pece,ddim,uni_pc,uni_pc_bh2
    schedulersimple,sgm_uniform,karras,exponential,ddim_uniform,beta,normal,linear_quadratic,kl_optimal
    dt_schedulersimple,sgm_uniform,karras,exponential,ddim_uniform,beta,normal,linear_quadratic,kl_optimal,AYS SDXL,AYS SD1,AYS SVD,GITS[coeff=1.2],LTXV[default],OSS FLUX,OSS Wan,OSS Chroma
    denoise1FLOAT
    denoise2FLOAT
    str_samplerSTRING
    str_schedulerSTRING