basicIn_Sampler
Pick your sampler once, wire it to every KSampler that needs it
- sampler
Every stock KSampler node in ComfyUI has its own sampler_name dropdown baked into it. That's fine with one sampler node in your graph; it gets annoying fast once you've got two or three (a base pass, a refiner pass, an upscale pass) and you want them all to agree, or you want to A/B test one sampler choice across your whole pipeline without clicking through every node individually. basicIn_Sampler pulls that dropdown out into its own standalone node - the README describes this exact pattern directly: "packages ComfyUI's built-in sampler input ports into a single port replacement, with functionality completely consistent with the official version."
What it is
One dropdown, sampler, listing all 44 of ComfyUI's built-in samplers - euler, euler_ancestral, the dpmpp_2m family, ddim, uni_pc, and the rest, exactly matching what you'd see in a stock KSampler. One output, also called sampler, typed to match that same list. Set it once, fan the output to as many samplers as your graph needs.
Which sampler to actually pick
This is a router, not an opinion - but the choice you route still matters, and it depends heavily on what kind of model you're running. For SD 1.5/SDXL-era checkpoints, dpmpp_2m (paired with a Karras scheduler) is still the safe default. For flow-matching models - Flux, Z-Image, Klein, Anima, and basically everything released since 2024 - the calculus flips: Karras schedules that used to help now actively hurt, and euler, euler_ancestral, or dpmpp_sde are the community's current defaults for that whole model family. Check what architecture you're actually running before assuming last year's "safe" sampler choice still applies.
Installing it
Search "ComfyUI-Apt_Preset" in ComfyUI Manager, or:
cd ComfyUI/custom_nodes
git clone https://github.com/cardenluo/ComfyUI-Apt_Preset.git
Run install.bat on Windows (pip install -r requirements.txt on Linux/Mac), restart ComfyUI. No models - it's a routing node over ComfyUI's own built-in sampler list.
Common issues
Because this node claims to be "completely consistent with the official version," if a sampler you expect to see is missing from the dropdown, the fault almost certainly isn't this node - it means your ComfyUI core install is on an older version than the one this list was built against, or a different node pack has overridden the sampler registry. Update ComfyUI core before assuming anything's wrong here. The other trap is more subtle: this node routes a name, not a guarantee that the destination sampler will behave sensibly with it - pairing an aggressive scheduler with a flow-matching model is still a mismatch even if the wiring is technically correct, and this node has no way to warn you about that. The sampler-scheduler pairing is on you.
Inputs (1)
| Name | Type | Default | Description |
|---|---|---|---|
| sampler | COMBO | 44 options: euler, euler_cfg_pp, euler_ancestral, euler_ancestral_cfg_pp, heun, heunpp2, +38 |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| sampler | euler,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 | — |