Nodes/comfyui-sdnq-splited/SDNQ Sampler V2
ComfyUI Node

SDNQ Sampler V2

Generate images using SDNQ models. Connect SDNQ Model Loader to provide the model.

By ussoewwin·Created 8 months ago·Updated 8 months ago· 3
SDNQ Sampler V2
  • model
  • latent_image
  • image
prompt
negative_promptblurry, low quality, distorted, deformed, ugly, bad anatomy, bad hands, text, watermark, signature
steps25
cfg7.0
seed0
schedulerDPMSolverMultistepScheduler
denoise1.00
Categorysampling/SDNQ

Inputs (9)

NameTypeDefaultDescription
modelMODELSDNQ model pipeline from SDNQ Model Loader node
promptSTRINGText description of the image to generate. Be descriptive for best results.
negative_promptSTRINGblurry, low quality, distorted, deformed, ugly, bad anatomy, bad hands, text, watermark, signatureWhat to avoid in the image. Default includes common quality issues. Clear this for no negative prompt. Note: FLUX-schnell (cfg=0) ignores negative prompts.
stepsINT251–150Number of denoising steps. More steps = better quality but slower. 20-30 is typical for most models.
cfgFLOAT7.00–30Guidance scale - how closely to follow the prompt. Higher = more literal. FLUX-schnell uses 0.0, FLUX-dev uses 3.5-7.0, SDXL uses 7.0-9.0.
latent_imageLATENTLatent image input. Width and height are extracted from this latent tensor.
seedINT00–18446744073709550000The random seed used for creating the noise. Seed=0 will randomize each run and update this field after generation.
schedulerCOMBODPMSolverMultistepScheduler⚠️ IMPORTANT: Use FlowMatchEulerDiscreteScheduler for FLUX/SD3/Qwen/Z-Image. Use DPMSolver/Euler/UniPC for SDXL/SD1.5. Wrong scheduler = broken images!
denoiseFLOAT1.000–1Denoising strength. 1.0 = full denoising, lower values = less denoising. ComfyUI standard parameter matching KSampler.

Outputs (1)

NameTypeDescription
imageIMAGE