ComfyUI Node
Stable Diffusion 3
A ComfyUI node in Runware/Image/runware with 30 inputs and 1 output.
Stable Diffusion 3
- seedImage
- maskImage
- outpaint
- lora
- controlNet
- ultralytics
- watermark
- acceleratorOptions
- image
◄positivePrompt—►
◄width1024►
◄height1024►
◄negativePrompt►
◄seed0►
◄steps28►
◄scheduler(default)►
◄CFGScalefalse►
◄CFGScale_value0.00►
◄strengthfalse►
◄strength_value0.80►
◄maskMarginfalse►
◄maskMargin_value32►
◄clipSkipfalse►
◄clipSkip_value0►
◄numberResults1►
◄safetyfalse►
◄safety.checkContentfalse►
◄ttlfalse►
◄ttl_value60►
◄outputFormatJPG►
◄outputQuality95►
CategoryRunware/Image/runware
Inputs (30)
| Name | Type | Default | Description |
|---|---|---|---|
| positivePrompt | STRING | Text prompt describing elements to include in the generated output. | |
| width | INT | 1024128–2048 | Width of the generated media in pixels. |
| height | INT | 1024128–2048 | Height of the generated media in pixels. |
| seedImageopt | IMAGE | — | |
| maskImageopt | IMAGE | — | |
| outpaintopt | RUNWARE_OUTPAINT | — | |
| loraopt | RUNWARE_LORA | — | |
| controlNetopt | RUNWARE_CONTROLNET | — | |
| ultralyticsopt | RUNWARE_ULTRALYTICS | — | |
| watermarkopt | RUNWARE_WATERMARK | — | |
| acceleratorOptionsopt | RUNWARE_ACCELERATOROPTIONS | — | |
| negativePromptopt | STRING | Prompt to guide what to exclude from generation. Ignored when guidance is disabled (CFGScale ≤ 1). | |
| seedopt | INT | 00–9223372036854776000 | Random seed for reproducible generation. When not provided, a random seed is generated in the unsigned 32-bit range. |
| stepsopt | INT | 281–50 | Total number of denoising steps. Higher values generally produce more detailed results but take longer. |
| scheduleropt | COMBO | (default) | Scheduler to use for the diffusion process. |
| CFGScaleopt | BOOLEAN | false | Enable to set CFGScale. Off uses the model's default. |
| CFGScale_valueopt | FLOAT | 0.000–30 | Guidance scale representing how closely the output will resemble the prompt. Higher values produce results more aligned with the prompt. |
| strengthopt | BOOLEAN | false | Enable to set strength. This setting has usage rules in this model, so it is off unless you enable it. |
| strength_valueopt | FLOAT | 0.800–1 | Strength of the transformation. Lower values result in more influence from the original input. |
| maskMarginopt | BOOLEAN | false | Enable to set maskMargin. Off uses the model's default. |
| maskMargin_valueopt | INT | 3232–128 | Extra context pixels around the masked region during inpainting. The model zooms into the masked area with these additional pixels for better integration. |
| clipSkipopt | BOOLEAN | false | Enable to set clipSkip. Off uses the model's default. |
| clipSkip_valueopt | INT | 00–4 | Number of layers to skip in the CLIP model. |
| numberResultsopt | INT | 11–20 | Number of results to generate. Each result uses a different seed, producing variations of the same parameters. |
| safetyopt | BOOLEAN | false | Enable to set safety. Off uses the model's default. |
| safety.checkContentopt | BOOLEAN | false | Enable or disable content safety checking. |
| 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 | — |