The Stability Stable Image Ultra node allows you to use Stability AI’s Stable Image Ultra model to create high-quality, detailed image content through text prompts or reference images. In this guide, we will show you how to set up workflows for both text-to-image and image-to-image generation using this node.
To use the API nodes, you need to ensure that you are logged in properly and using a permitted network environment. Please refer to the API Nodes Overview section of the documentation to understand the specific requirements for using the API nodes.
If you find missing nodes when loading the workflow file below, it may be due to the following situations:
  1. You are not using the latest Development (Nightly) version of ComfyUI.
  2. You are using the Stable (Release) version or Desktop version of ComfyUI (which does not include the latest feature updates).
  3. You are using the latest Commit version of ComfyUI, but some nodes failed to import during startup.
Please make sure you have successfully updated ComfyUI to the latest Development (Nightly) version. See: How to Update ComfyUI section to learn how to update ComfyUI.

​
Stability AI Stable Image Ultra Text-to-Image Workflow

​
1. Workflow File Download

The workflow information is included in the metadata of the image below. Please download and drag it into ComfyUI to load the corresponding workflow. Stability AI Stable Image Ultra Text-to-Image Workflow

​
2. Complete the Workflow Execution Step by Step

Stability AI Stable Image Ultra Text-to-Image Step Guide You can follow the numbered steps in the image to complete the basic text-to-image workflow:
  1. (Optional) Modify the 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.
  2. (Optional) Select the 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.
  3. Click the Run button or use the shortcut Ctrl(cmd) + Enter to execute the image generation.
  4. After the API returns the result, you can view the generated image in the Save Image node, and the image will also be saved to the ComfyUI/output/ directory.

​
3. Additional Notes

  • Prompt: The prompt is one of the most important parameters in the generation process. Detailed, clear descriptions will lead to better results. It can include elements like scene, subject, colors, lighting, and style.
  • Style Preset: Provides multiple preset styles such as cinematic, anime, digital art, etc., which can quickly define the overall style of the image.
  • Negative Prompt: Used to specify elements you don’t want to appear in the generated image, helping avoid common issues like extra limbs or distorted faces.
  • Seed Parameter: Can be used to reproduce or fine-tune generation results, helpful for iteration during the creative process.
  • Currently, the 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.

​
Stability AI Stable Image Ultra Image-to-Image Workflow

​
1. Workflow File Download

The workflow information is included in the metadata of the image below. Please download and drag it into ComfyUI to load the corresponding workflow. Stability Stable Image Ultra Image-to-Image Workflow Download the image below which we will use as input Stability Stable Image Ultra Image-to-Image Workflow Input Image

​
2. Complete the Workflow Execution Step by Step

Stability Stable Image Ultra Image-to-Image Step Guide You can follow the numbered steps in the image to complete the image-to-image workflow:
  1. Load a reference image through the Load Image node, which will serve as the basis for generation.
  2. (Optional) Modify the prompt parameter in the Stability Stable Image Ultra node to describe elements you want to change or enhance in the reference image.
  3. (Optional) Adjust the image_denoise parameter (range 0.0-1.0) to control the degree of modification to the original image:
    • Values closer to 0.0 will make the generated image more similar to the input reference image
    • Values closer to 1.0 will make the generated image more like pure text-to-image generation
  4. (Optional) You can also set style_preset and other parameters to further control the generation effect.
  5. Click the Run button or use the shortcut Ctrl(cmd) + Enter to execute the image generation.
  6. After the API returns the result, you can view the generated image in the Save Image node, and the image will also be saved to the ComfyUI/output/ directory.

​
3. Additional Notes

Image Denoise: This parameter determines how much of the original image’s features are preserved during generation, and is the most crucial adjustment parameter in image-to-image mode. The image below shows the effects of different denoising strengths Stability Stable Image Ultra Image-to-Image Denoise Explanation
  • Reference Image Selection: Choosing images with clear subjects and good composition usually leads to better results.
  • Prompt Tips: In image-to-image mode, prompts should focus more on what you want to change or enhance, rather than describing all elements already present in the image.
You can refer to the documentation below for detailed parameter settings and more information about the corresponding nodes

Stability Stable Image Ultra Node Documentation

Stability Stable Image Ultra API Node Documentation