ComfyUI Node
⚡| Z-Sampler Turbo ^G2 (Simple)
Simplified version of Z-Sampler Turbo (second generation), offering a streamlined interface for quick and easy use while retaining all of its features and capabilities. It takes a Z-Image Turbo model, an initial latent image, and prompt/conditioning to produce a denoised latent output, which can then be decoded into the final image.
⚡| Z-Sampler Turbo ^G2 (Simple)
- latent_input
- model
- positive
- divider
- positive_stg2
- positive_stg3
- latent_output
◄seed1►
◄steps8►
◄ibias0.0►
◄turbo_creativityfalse►
◄old_schedulerfalse►
◄noise_injectionfalse►
◄alternative_refinerfalse►
Category⚡Z-Image
Inputs (13)
| Name | Type | Default | Description |
|---|---|---|---|
| latent_input | LATENT | The initial latent image to be denoised; usually an 'Empty Latent' for text-to-image tasks or an encoded image for image-to-image processing. | |
| model | MODEL | The Z-Image Turbo model used for denoising the latent image. | |
| positive | CONDITIONING | The main prompt/conditioning used to guide the generation process toward the desired content. | |
| seed | INT | 11–18446744073709550000 | The seed used for the random noise generator, ensuring the same result is produced with the same value. |
| steps | INT | 83–20 | Number of iterations to perform during the denoising process. |
| ibias | FLOAT | 0.0-1–1 | Custom adjustment for the intensity noise bias. Usually kept at 0.0; used to fine-tune 'brightness'. Note that its effect depends heavily on the prompt and image style, so it may not always act as a simple brightness control. Adjust it within the positive or negative range until it seems right to you. |
| divider | ZIPN_SEPARATOR | — | |
| turbo_creativity | BOOLEAN | false | Enables turbo creativity. This scrambles the image to boost diversity in compositions while maintaining the general style and tone color. Be aware that this may lead to hallucinations. |
| old_scheduler | BOOLEAN | false | Enables the legacy scheduler with a different set of sigmas. Although the new scheduler is optimized for general quality, this old version may produce better results in specific cases. |
| noise_injection | BOOLEAN | false | Enables noise injection in the final stage. This can enhance fine details and realism, but may also generate artificial-looking color spots in smooth areas. |
| alternative_refiner | BOOLEAN | false | Enables an alternative refiner using the DPM++ SDE sampler during the final stage. This enhances contrast and sharpness in fine details but increases overall processing time. |
| positive_stg2opt | CONDITIONING | This input is optional and can remain disconnected. It allows specifying a different prompt/conditioning for the second stage of the denoising process. | |
| positive_stg3opt | CONDITIONING | This input is optional and can remain disconnected. It allows specifying a different prompt/conditioning for the third stage of the denoising process. |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| latent_output | LATENT | The resulting denoised latent image, ready for decoding by a VAE or passed to another node for further processing. |