ComfyUI Node
TBG Dual Model KSampler (Inpaint Split Aware)
A ComfyUI node in TBG/Sampler with 20 inputs and 1 output.
TBG Dual Model KSampler (Inpaint Split Aware)
- model_high
- model_low
- positive_high
- negative_high
- positive_low
- negative_low
- latent_image
- output
◄noise_seed0►
◄cfg_high1.0►
◄cfg_low1.0►
◄sampler_name▾►
◄scheduler▾►
◄steps_high20►
◄steps_low9►
◄denoise1.00►
◄model_crossover_sigma_strength0.50►
◄low_sigma_alignment1.00►
◄inpaint_end0►
◄smoother_sharper0.00►
◄detail_enhancer0.00►
CategoryTBG/Sampler
Inputs (20)
| Name | Type | Default | Description |
|---|---|---|---|
| model_high | MODEL | First model for high sigma phase. IMPORTANT: Both model_high and model_low must use the same or compatible latent spaces and VAE models. Compatible pairs: Flux + ZImages, Qwen + WAN. Incompatible models will produce corrupted outputs due to latent space mismatch. | |
| model_low | MODEL | Second model for low sigma phase. IMPORTANT: Must be latent space compatible with model_high (same VAE, same latent dimensions). Compatible pairs: Flux + ZImages, Qwen + WAN. Using incompatible models will fail or produce artifacts. | |
| noise_seed | INT | 00–18446744073709550000 | — |
| cfg_high | FLOAT | 1.00–100 | — |
| cfg_low | FLOAT | 1.00–100 | — |
| positive_high | CONDITIONING | — | |
| negative_high | CONDITIONING | — | |
| positive_low | CONDITIONING | — | |
| negative_low | CONDITIONING | — | |
| 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 | |
| steps_high | INT | 201–2048 | Total steps used to generate the high model's sigma schedule. This is the full step count for a typical generation, not the actual steps executed. The sigma_split_value determines which portion of this schedule is used. Example: FLUX 20 steps with split=0.5 might execute ~10 high-sigma steps. |
| steps_low | INT | 91–2048 | Total steps used to generate the low model's sigma schedule. This is the full step count for a typical generation, not the actual steps executed. The sigma_split_value determines which portion of this schedule is used. Example: Z-image 10 steps with split=0.5 might execute ~5 low-sigma steps. |
| denoise | FLOAT | 1.000–1 | — |
| model_crossover_sigma_strength | FLOAT | 0.500–1 | Controls the sigma strength where sampling switches from the high model to the low model.” |
| low_sigma_alignment | FLOAT | 1.000–5 | Shifts the lower sigma values up or down to better synchronize sampling between models. Default is 1, which works best in most cases. |
| inpaint_end | INT | 0-50–0 | Step number from the end after which inpainting is skipped. For example, with 20 total steps, setting -10 means inpainting runs only from step 1 to 10. |
| smoother_sharper | FLOAT | 0.00-1–1 | Dual-stage adaptive sharpening. At high sigma (early steps), adds structured noise for detail invention. At low sigma (late steps), applies high-pass edge sharpening. Positive values sharpen and add details. Negative values soften and blur. Zero disables sharpening. Higher absolute values create stronger effects. |
| detail_enhancer | FLOAT | 0.00-1–1 | Substep evaluation for detail control. Positive values (0.1-1.0): lookahead to next sigma, adds coherent details and refinement, reduces variation. Negative values (-0.1 to -1.0): lookback to previous sigma, adds creative variation and texture complexity. Zero = disabled (single pass, fastest). Performance cost: 2x slower on affected steps. |
| latent_imageopt | LATENT | — |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| output | LATENT | — |