ComfyUI Node
Seed Variance Enhancer - Krea 2 Turbo
A ComfyUI node in advanced/conditioning with 12 inputs and 2 outputs.
Seed Variance Enhancer - Krea 2 Turbo
- conditioning
- conditioning
- diagnostics
◄randomize_percent50►
◄auto_strength_factor1.00►
◄strength20.0000►
◄noise_insert▾►
◄steps_switchover_percent25►
◄seed0►
◄mask_starts_at▾►
◄mask_percent0►
◄log_to_consolefalse►
◄noise_distribution▾►
◄granularity▾►
Categoryadvanced/conditioning
Inputs (12)
| Name | Type | Default | Description |
|---|---|---|---|
| conditioning | CONDITIONING | — | |
| randomize_percent | FLOAT | 501–100 | Percentage of embedding values (or tokens, see granularity) that receive noise. Higher = more diversity, less prompt adherence. |
| auto_strength_factor | FLOAT | 1.000–100 | If > 0, noise scale = measured embedding std * factor (recommended for Krea 2 Turbo). Try 0.5 subtle / 1.0 balanced / 3+ strong. Set to 0 to use the manual 'strength' field instead. |
| strength | FLOAT | 20.0000-4294967295–4294967295 | Absolute noise scale. Only used when auto_strength_factor is 0. |
| noise_insert | COMBO | Where the noisy embedding is used. 'beginning steps' perturbs the structure-deciding early steps, then restores the clean prompt. 'all steps' is strongest but worst for adherence/text. | |
| steps_switchover_percent | FLOAT | 251–99 | Where noisy/clean conditioning switch. Formula: (100/TOTAL_STEPS)*SWITCH_STEP. For 8-step Krea 2 Turbo: 25 ~ first 2 steps, 38 ~ first 3 steps. |
| seed | INT | 00–18446744073709550000 | IMPORTANT: set this to 'randomize' or 'increment' to get DIFFERENT variations each run. If left 'fixed', every generation gets the SAME embedding noise and outputs stay similar. |
| mask_starts_at | COMBO | Which end of the prompt is protected from noise. | |
| mask_percent | FLOAT | 00–99 | Percentage of the prompt protected from noise. 'beginning'+'50' protects the first half. |
| log_to_console | BOOLEAN | false | Also print the diagnostics to the ComfyUI console. The same text is always available on the 'diagnostics' STRING output. Version k2-1.2.0 (base: SVE 2.2). |
| noise_distribution | COMBO | Shape of the random noise. 'uniform' is the original behavior. 'gaussian' matches the bell-curve statistics of the embedding itself and tends to produce fewer broken outputs at the same strength. Both are power-matched: the same strength gives the same overall perturbation. | |
| granularity | COMBO | 'values' scatters noise across individual embedding values (original behavior). 'tokens' perturbs whole tokens at once, producing more semantic variations (subjects/props/composition shift together). randomize_percent then selects tokens instead of values. |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| conditioning | CONDITIONING | — |
| diagnostics | STRING | — |