Stability Stable Image Ultra - ComfyUI Native Node Documentation
A node that generates high-quality images using Stability AI’s ultra stable diffusion model
The Stability Stable Image Ultra node uses Stability AI’s Stable Diffusion Ultra API to generate high-quality images. It supports both text-to-image and image-to-image generation, creating detailed and artistic visuals from text prompts.
Parameters
Required Parameters
Parameter | Type | Default | Description |
---|---|---|---|
prompt | string | "" | Text description of what you want to generate. Better results come from clear, descriptive prompts that specify elements, colors and themes. You can control word importance using (word:weight) format, where weight is 0-1. For example: The sky was (blue:0.3) and (green:0.8) makes the sky more green than blue. |
aspect_ratio | select | ”1:1” | Width to height ratio of output image |
style_preset | select | ”None” | Optional preset style for generated image |
seed | integer | 0 | Random seed for noise generation (0-4294967294) |
Optional Parameters
Parameter | Type | Default | Description |
---|---|---|---|
image | image | - | Input image for image-to-image generation |
negative_prompt | string | "" | Describes what you don’t want in the output image. This is an advanced feature |
image_denoise | float | 0.5 | Denoising strength for input image (0.0-1.0). 0.0 keeps input image unchanged, 1.0 is like having no input image |
Output
Output | Type | Description |
---|---|---|
IMAGE | image | Generated image |
Notes
- image_denoise has no effect when no input image is provided
- No preset style is applied when style_preset is “None”
- For image-to-image, input images are converted to the proper format before API submission
Source Code
[Node source code (Updated on 2025-05-03)]