ComfyUI Node
đź’€Prepack Ksampler
Run KSampler and then decode with VAE in a single node.
đź’€Prepack Ksampler
- model
- positive
- negative
- vae
- latent_image
- image
- info
â—„seed0â–ş
â—„steps20â–ş
â—„cfg8.0â–ş
â—„sampler_nameâ–ľâ–ş
â—„schedulerâ–ľâ–ş
â—„denoise1.00â–ş
Categoryđź’€Prepack
Inputs (11)
| Name | Type | Default | Description |
|---|---|---|---|
| model | MODEL | The model used for denoising the input latent. | |
| positive | CONDITIONING | Positive conditioning (CFG target). | |
| negative | CONDITIONING | Negative conditioning (CFG target to avoid). | |
| vae | VAE | The VAE model used for decoding the latent to image. | |
| latent_image | LATENT | The input latent to denoise (from VAE Encode or Empty Latent Image). | |
| seed | INT | 00–18446744073709550000 | The random seed used for creating the noise. |
| steps | INT | 201–10000 | The number of steps used in the denoising process. |
| cfg | FLOAT | 8.00–100 | The Classifier-Free Guidance scale. |
| sampler_name | COMBO | The algorithm used when sampling. | |
| scheduler | COMBO | The noise schedule applied during sampling. | |
| denoise | FLOAT | 1.000–1 | Relative denoising strength: 1.0 = full denoise; <1.0 = partial denoise (img2img). |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| image | IMAGE | Decoded image tensor (NCHW, float32, range 0..1). |
| info | STRING | Sampling process information including model, prompts, parameters, and status. |