ComfyUI Node
KSampler Refiner (Arctenox's Essentials)
Second-pass refiner / hi-res fix node. Typical hi-res fix workflow: 1. KSampler (Arctenox's Essentials) at 512x768, denoise=1.0 --> LATENT 2. KSampler Refiner, upscale_method=bilinear, scale_factor=1.5, denoise=0.45, same seed/sonar --> refined LATENT + IMAGE at 768x1152 Denoise guide: 0.30-0.50 Subtle hi-res fix (adds crisp detail, keeps composition) 0.50-0.70 Moderate rework (allows layout shifts) 0.70-1.00 Heavy rework (treats it almost like a fresh generation)
KSampler Refiner (Arctenox's Essentials)
- model
- positive
- negative
- latent
- vae
- model
- positive
- negative
- latent
- vae
- image
◄upscale_methodbilinear►
◄scale_factor1.50►
◄target_width0►
◄target_height0►
◄seed0►
◄sonar0►
◄steps20►
◄cfg4.00►
◄sampler_name▾►
◄scheduler▾►
◄denoise0.45►
◄vae_decodetrue►
CategoryArctenox Essentials/Sampling
Inputs (17)
| Name | Type | Default | Description |
|---|---|---|---|
| model | MODEL | — | |
| positive | CONDITIONING | — | |
| negative | CONDITIONING | — | |
| latent | LATENT | — | |
| upscale_method | COMBO | bilinear | Latent upscale interpolation method. 'None' skips upscaling. |
| scale_factor | FLOAT | 1.500.25–8 | Upscale multiplier. Ignored if target_width/height > 0. |
| target_width | INT | 00–8192 | Target pixel width after upscale. 0 = use scale_factor instead. |
| target_height | INT | 00–8192 | Target pixel height after upscale. 0 = use scale_factor instead. |
| seed | INT | 0-9223372036854776000–18446744073709550000 | Seed for refiner pass. Use the same seed as the main KSampler for consistency. |
| sonar | INT | 0-18446744073709550000–18446744073709550000 | Golden-ratio sonar offset. Match to main KSampler for coherent variation. |
| steps | INT | 201–10000 | Refiner sampling steps. |
| cfg | FLOAT | 4.000–100 | CFG scale for refiner pass. |
| sampler_name | COMBO | 44 options: euler, euler_cfg_pp, euler_ancestral, euler_ancestral_cfg_pp, heun, heunpp2, +38 | |
| scheduler | COMBO | 9 options: simple, sgm_uniform, karras, exponential, ddim_uniform, beta, +3 | |
| denoise | FLOAT | 0.450–1 | How much the refiner changes the latent. 0.3–0.5 = subtle hi-res fix (adds detail, preserves composition) 0.5–0.7 = moderate rework 0.7–1.0 = heavy rework (similar to full generation) |
| vae_decode | COMBO | true | Decode the refined latent to an IMAGE inside this node. |
| vaeopt | VAE | — |
Outputs (6)
| Name | Type | Description |
|---|---|---|
| model | MODEL | — |
| positive | CONDITIONING | — |
| negative | CONDITIONING | — |
| latent | LATENT | — |
| vae | VAE | — |
| image | IMAGE | — |