ComfyUI Node
Stable Diffusion Latent Upscaler
A ComfyUI node in Runware/Image/runware with 16 inputs and 1 output.
Stable Diffusion Latent Upscaler
- image
- image
◄upscaleFactor(default)►
◄settings.CFGScalefalse►
◄settings.CFGScale_value3.00►
◄settings.clipSkipfalse►
◄settings.clipSkip_value0►
◄settings.negativePrompt►
◄settings.positivePrompt►
◄settings.seedfalse►
◄settings.seed_value0►
◄settings.stepsfalse►
◄settings.steps_value20►
◄ttlfalse►
◄ttl_value60►
◄outputFormatJPG►
◄outputQuality95►
CategoryRunware/Image/runware
Inputs (16)
| Name | Type | Default | Description |
|---|---|---|---|
| image | IMAGE | — | |
| upscaleFactoropt | COMBO | (default) | Factor by which to upscale the generated image. A value of 2 doubles width and height. |
| settings.CFGScaleopt | BOOLEAN | false | Enable to set settings.CFGScale. Off uses the model's default. |
| settings.CFGScale_valueopt | FLOAT | 3.003–12 | Guidance scale representing how closely the output will resemble the prompt. Higher values produce results more aligned with the prompt. |
| settings.clipSkipopt | BOOLEAN | false | Enable to set settings.clipSkip. Off uses the model's default. |
| settings.clipSkip_valueopt | INT | 00–2 | Number of layers to skip in the CLIP model. |
| settings.negativePromptopt | STRING | Prompt to guide what to exclude from generation. Ignored when guidance is disabled (CFGScale ≤ 1). | |
| settings.positivePromptopt | STRING | Text prompt describing elements to include in the generated output. | |
| settings.seedopt | BOOLEAN | false | Enable to set settings.seed. Off uses the model's default. |
| settings.seed_valueopt | INT | 00–9223372036854776000 | Random seed for reproducible generation. When not provided, a random seed is generated in the unsigned 32-bit range. |
| settings.stepsopt | BOOLEAN | false | Enable to set settings.steps. Off uses the model's default. |
| settings.steps_valueopt | INT | 2020–60 | Total number of denoising steps. Higher values generally produce more detailed results but take longer. |
| ttlopt | BOOLEAN | false | Enable to set ttl. Off uses the model's default. |
| ttl_valueopt | INT | 60 | Time-to-live (TTL) in seconds for generated content. Only applies when `outputType` is `URL`. |
| outputFormatopt | COMBO | JPG | File format for the generated image. |
| outputQualityopt | INT | 9520–99 | Compression quality of the output. Higher values preserve quality but increase file size. |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| image | IMAGE | — |