ComfyUI Node
Karma KSampler Cycle
A ComfyUI node in KarmaNodes/Sampling with 40 inputs and 2 outputs.
Karma KSampler Cycle
- primary_model
- vae
- latent_image
- positive
- negative
- secondary_model
- upscale_model
- pos_additive
- neg_additive
- latent(s)
- vae
◄steps20►
◄seed0►
◄cfg8.00►
◄sampler_name▾►
◄scheduler▾►
◄starting_denoise1.00►
◄cycle_denoise0.50►
◄total_cycles2►
◄enable_denoise_scalingtrue►
◄denoise_min_threshold0.10►
◄enable_steps_scalingfalse►
◄steps_scaling_value5►
◄steps_adjustment_modedecrement►
◄steps_threshold_modeauto►
◄steps_manual_threshold5►
◄secondary_model_start_cycle2►
◄upscale_factor2.0►
◄upscale_methodbasic►
◄scale_sampling▾►
◄latent_upscale_methodlanczos►
◄enable_gradual_upscalingfalse►
◄gradual_upscale_steps3►
◄pos_add_strength0.25►
◄enable_pos_strength_scalingfalse►
◄pos_add_strength_cutoff2.00►
◄neg_add_strength0.25►
◄enable_neg_strength_scalingfalse►
◄neg_add_strength_cutoff2.00►
◄sharpen_strength0.00►
◄sharpen_radius2►
◄use_tiled_vaefalse►
CategoryKarmaNodes/Sampling
Inputs (40)
| Name | Type | Default | Description |
|---|---|---|---|
| primary_model | MODEL | — | |
| vae | VAE | — | |
| latent_image | LATENT | — | |
| positive | CONDITIONING | The main positive conditioning. | |
| negative | CONDITIONING | The main negative conditioning. | |
| steps | INT | 201–10000 | — |
| seed | INT | 00–18446744073709550000 | — |
| cfg | FLOAT | 8.000–100 | — |
| 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 | |
| starting_denoise | FLOAT | 1.000–1 | — |
| cycle_denoise | FLOAT | 0.500–1 | — |
| total_cycles | INT | 22–12 | — |
| enable_denoise_scaling | BOOLEAN | true | Enable automatic denoise strength scaling between cycles |
| denoise_min_threshold | FLOAT | 0.100.01–1 | Minimum denoise threshold to prevent going too low |
| enable_steps_scaling | BOOLEAN | false | Enable automatic steps adjustment between cycles |
| steps_scaling_value | INT | 51–50 | Amount to adjust steps by each cycle |
| steps_adjustment_mode | COMBO | decrement | Whether to decrease or increase steps each cycle |
| steps_threshold_mode | COMBO | auto | Auto calculates threshold based on initial steps, manual uses fixed value |
| steps_manual_threshold | INT | 51–200 | Manual threshold value (only used when threshold mode is manual) |
| secondary_model_start_cycle | INT | 21–12 | Cycle at which to switch to secondary model (if provided) |
| upscale_factor | FLOAT | 2.00.1–8 | — |
| upscale_method | COMBO | basic | basic = PIL image upscale, model = upscale model, latent = direct latent space resize (fastest, no VAE decode/encode) |
| scale_sampling | COMBO | Resampling method for image upscaling | |
| latent_upscale_method | COMBO | lanczos | Resampling method for latent space upscaling |
| enable_gradual_upscaling | BOOLEAN | false | Enable gradual upscaling with multiple intermediate steps |
| gradual_upscale_steps | INT | 31–10 | Number of gradual upscaling steps (only used when gradual upscaling is enabled) |
| pos_add_strength | FLOAT | 0.250.01–1 | — |
| enable_pos_strength_scaling | BOOLEAN | false | Enable positive strength scaling between cycles |
| pos_add_strength_cutoff | FLOAT | 2.000.01–10 | — |
| neg_add_strength | FLOAT | 0.250.01–1 | — |
| enable_neg_strength_scaling | BOOLEAN | false | Enable negative strength scaling between cycles |
| neg_add_strength_cutoff | FLOAT | 2.000.01–10 | — |
| sharpen_strength | FLOAT | 0.000–10 | — |
| sharpen_radius | INT | 21–12 | — |
| use_tiled_vae | BOOLEAN | false | Use tiled VAE processing for large images |
| secondary_modelopt | MODEL | Optional secondary model to switch to at specified cycle | |
| upscale_modelopt | UPSCALE_MODEL | — | |
| pos_additiveopt | CONDITIONING | Additional positive conditioning to blend in. | |
| neg_additiveopt | CONDITIONING | Additional negative conditioning to blend in. |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| latent(s) | LATENT | — |
| vae | VAE | — |