Nodes/ComfyUI-ZImagePowerNodes/❌[DEPRECATED] Z-Sampler Turbo ^G2 (Laboratory)
ComfyUI Node

❌[DEPRECATED] Z-Sampler Turbo ^G2 (Laboratory)

Efficiently denoises the latent image, specifically tuned for the "Z-Image Turbo" model. This node allows direct modification of internal parameters in the zsample_turbo_core(...) method, and was used during development for testing and calibration.

By martin-rizzo·Created 7 months ago·Updated a day ago· 346
❌[DEPRECATED] Z-Sampler Turbo ^G2 (Laboratory)
  • model
  • positive
  • latent_input
  • divider1
  • divider2
  • divider3
  • divider4
  • latent_output
seed1
steps8
denoise1.00
initial_noise_bias_level1.0
initial_noise_overdose0.2
noise_est_sample_sizeimage_size
extra_noise_freq132
extra_noise_scale17.5
extra_noise_freq264
extra_noise_scale23.7
extra_noise_freq3512
extra_noise_scale31.0
scramble_left_count0
scramble_top_count0
scramble_right_count0
scramble_bottom_count0
stage2_preproc_steps0
sigma_preset_namebravo
sigma1_off0.000
sigma2_off0.000
sigma3_off0.000
sigma4_off0.000
sigma5_off0.000
sigma6_off0.000
sigma7_off0.000
sigma8_off0.000
sigma9_off0.000
sigma10_off0.000
Category⚡Z-Image/__deprecated

Inputs (35)

NameTypeDefaultDescription
modelMODELThe model used for generating the latent images.
positiveCONDITIONINGThe conditioning used to guide the generation process toward the desired content.
latent_inputLATENTThe initial latent image to be modified; typically an 'Empty Latent' for text-to-image or an encoded image for img2img.
seedINT11–18446744073709550000The seed used for the random noise generator, ensuring the same result is produced with the same value.
stepsINT83–20The number of iterations to be performed during the sampling process.
denoiseFLOAT1.000–1The amount of denoising applied, lower values will maintain the structure of the initial image allowing for image to image sampling.
divider1ZIPN_SEPARATOR
initial_noise_bias_levelFLOAT1.00–10The level of adjustament from the calculated noise bias to apply before the first denoising step. (0.0 means no noise bias adjustment; 1.0 means using the calculated noise bias).
initial_noise_overdoseFLOAT0.2-1–1The amount of over-amplitude in the initial noise generation. (negative values ​​will reduce any excessive amplitude).
noise_est_sample_sizeCOMBOimage_sizeThe size of the latent image used to calculate the initial noise. The smaller the image size, the faster the calculation of the first step.
divider2ZIPN_SEPARATOR
extra_noise_freq1INT320–1024The frequency at which extra noise is injected into the latent during the first stage. A value of 1024 means noise in injected into every pixel, a value of 512 means noise is injected every second pixel, with intermediate pixels being interpolated.
extra_noise_scale1FLOAT7.50–50The amount of noise to be injected into the latent image during the first stage. A value of 0 means that no noise will be injected.
extra_noise_freq2INT640–1024The frequency at which extra noise is injected into the latent during the second stage. A value of 1024 means noise in injected into every pixel, a value of 512 means noise is injected every second pixel, with intermediate pixels being interpolated.
extra_noise_scale2FLOAT3.70–50The amount of noise to be injected into the latent image during the second stage. A value of 0 means that no noise will be injected.
extra_noise_freq3INT5120–1024The frequency at which extra noise is injected into the latent during the third stage. A value of 1024 means noise in injected into every pixel, a value of 512 means noise is injected every second pixel, with intermediate pixels being interpolated.
extra_noise_scale3FLOAT1.00–50The amount of noise to be injected into the latent image during the third stage. A value of 0 means that no noise will be injected.
divider3ZIPN_SEPARATOR
scramble_left_countINT0-16–16Number of times to scramble the latent image with left side fragments. A value of 0 means no scrambling will be done, while negative values enable random flipping.
scramble_top_countINT0-16–16Number of times to scramble the latent image with top side fragments. A value of 0 means no scrambling will be done, while negative values enable random flipping.
scramble_right_countINT0-16–16Number of times to scramble the latent image with right side fragments. A value of 0 means no scrambling will be done, while negative values enable random flipping.
scramble_bottom_countINT0-16–16Number of times to scramble the latent image with bottom side fragments. A value of 0 means no scrambling will be done, while negative values enable random flipping.
stage2_preproc_stepsINT00–3Number of extra steps to perform as pre-processing in the second stage, this can improve coherence and reduce hallucination.
divider4ZIPN_SEPARATOR
sigma_preset_nameCOMBObravoThe set of predefined sigma values that are used during the denoise process.
sigma1_offFLOAT0.000-1–1Offset that will be applied to the value of sigma1.
sigma2_offFLOAT0.000-1–1Offset that will be applied to the value of sigma2.
sigma3_offFLOAT0.000-1–1Offset that will be applied to the value of sigma3.
sigma4_offFLOAT0.000-1–1Offset that will be applied to the value of sigma4.
sigma5_offFLOAT0.000-1–1Offset that will be applied to the value of sigma5.
sigma6_offFLOAT0.000-1–1Offset that will be applied to the value of sigma6.
sigma7_offFLOAT0.000-1–1Offset that will be applied to the value of sigma7.
sigma8_offFLOAT0.000-1–1Offset that will be applied to the value of sigma8.
sigma9_offFLOAT0.000-1–1Offset that will be applied to the value of sigma9.
sigma10_offFLOAT0.000-1–1Offset that will be applied to the value of sigma10.

Outputs (1)

NameTypeDescription
latent_outputLATENTThe resulting denoised latent image, ready for decoding by a VAE or passed to another node for further processing.