This article will introduce how to use the Stability AI Stable Image Ultra API node’s text-to-image and image-to-image capabilities in ComfyUI
prompt
parameter in the Stability AI Stable Image Ultra
node to input your desired image description. More detailed prompts often lead to better image quality. You can use the (word:weight)
format to control specific word weights, for example: The sky was crisp (blue:0.3) and (green:0.8)
indicates the sky is blue and green, but green is more prominent.style_preset
parameter to control the visual style of the image. Different preset styles will produce images with different stylistic characteristics, such as “cinematic”, “anime”, etc. Selecting “None” will not apply any specific style.Run
button or use the shortcut Ctrl(cmd) + Enter
to execute the image generation.Save Image
node, and the image will also be saved to the ComfyUI/output/
directory.Load Image
node is in “Bypass” mode. To enable it, refer to the step guide and right-click on the corresponding node to set “Mode” to “Always” to enable input, which will switch to image-to-image mode.Load Image
node, which will serve as the basis for generation.prompt
parameter in the Stability Stable Image Ultra
node to describe elements you want to change or enhance in the reference image.image_denoise
parameter (range 0.0-1.0) to control the degree of modification to the original image:
style_preset
and other parameters to further control the generation effect.Run
button or use the shortcut Ctrl(cmd) + Enter
to execute the image generation.Save Image
node, and the image will also be saved to the ComfyUI/output/
directory.