Stability AI
Generate images from text descriptions using Stability AI models.
A versatile node capable of interfacing with StabilityAI API to perform various tasks such as removing the background, search-and-replace, and more.
Stability AIFast 3D
Image*File upload
Texture ResolutionSelect
Foreground RatioSlider
RemeshSelect
Vertex CountNumber
Modes
This node reconfigures itself depending on the selected mode — each mode has its own fields.
| Mode | What it does | Output |
|---|---|---|
| Replace Element | Search for an element in an image using a prompt, and replace it. | Image |
| Remove BG | Remove the background from an image using the StabilityAI API. | Image |
| Upscale Fast | Upscale an image using StabilityAI API | Image |
| Fast 3D | Generate a 3D model from an image using Stable Fast 3D. | — |
Replace Element
Search for an element in an image using a prompt, and replace it.
Stability AIReplace Element
Image*File upload
Prompt*Text
Search Prompt*Text
Negative PromptText
Grow MaskSlider
SeedNumber
Output FormatSelect
Style PresetSelect
Inputs
Each input can be typed in directly or connected to another node's output.
| Input | Type | Required | Description |
|---|---|---|---|
| Image | File upload | Required | An image containing content you wish to replace. Supported Formats: - jpeg - png - webp Validation Rules: - Every side must be at least 64 pixels - Total pixel count must be between 4,096 and 9,437,184 pixels - The aspect ratio must be between 1:2.5 and 2.5:1 |
| Prompt | Text | Required | What you wish to see in the output image. A strong, descriptive prompt that clearly defines elements, colors, and subjects will lead to better results. To control the weight of a given word use the format (word:weight), where word is the word you'd like to control the weight of and weight is a value between 0 and 1. For example: The sky was a crisp (blue:0.3) and (green:0.8) would convey a sky that was blue and green, but more green than blue. |
| Search Prompt | Text | Required | Short description of what to inpaint in the image. |
| Negative Prompt | Text | Optional | A blurb of text describing what you do not wish to see in the output image. This is an advanced feature. |
Settings
| Setting | Type | Default | Description |
|---|---|---|---|
| Grow Mask | Slider | 3 | Grows the edges of the mask outward in all directions by the specified number of pixels. The expanded area around the mask will be blurred, which can help smooth the transition between inpainted content and the original image. Try this parameter if you notice seams or rough edges around the inpainted content. > Note: Excessive growth may obscure fine details in the mask and/or merge nearby masked regions. Range: 0–20. |
| Seed | Number | 0 | A specific value that is used to guide the 'randomness' of the generation. (Omit this parameter or pass 0 to use a random seed.) Range: 0–4294967294. |
| Output Format | Select | png | Dictates the content-type of the generated image. |
| Style Preset | Select | enhance | Guides the image model towards a particular style. |
Output Format options
| Option | Default |
|---|---|
| jpeg | |
| png | ✓ |
| webp |
Style Preset options
| Option | Default |
|---|---|
| enhance | ✓ |
| anime | |
| photographic | |
| digital-art | |
| comic-book | |
| fantasy-art | |
| line-art | |
| analog-film | |
| neon-punk | |
| isometric | |
| low-poly | |
| origami | |
| modeling-compound | |
| cinematic | |
| 3d-model | |
| pixel-art | |
| tile-texture |
Output: Image
Remove BG
Remove the background from an image using the StabilityAI API.
Stability AIRemove BG
Image*File upload
Output FormatSelect
Inputs
Each input can be typed in directly or connected to another node's output.
| Input | Type | Required | Description |
|---|---|---|---|
| Image | File upload | Required | The image whose background you wish to remove. Supported Formats: - jpeg - png - webp Validation Rules: - Every side must be at least 64 pixels - Total pixel count must be between 4,096 and 4,194,304 pixels |
Settings
| Setting | Type | Default | Description |
|---|---|---|---|
| Output Format | Select | png | Dictates the content-type of the generated image. Options: png (default) · webp. |
Output: Image
Upscale Fast
Upscale an image using StabilityAI API
Stability AIUpscale Fast
Image*File upload
Output FormatSelect
Inputs
Each input can be typed in directly or connected to another node's output.
| Input | Type | Required | Description |
|---|---|---|---|
| Image | File upload | Required | The image you wish to upscale. Supported Formats: - jpeg - png - webp Validation Rules: - Width must be between 32 and 1,536 pixels - Height must be between 32 and 1,536 pixels - Total pixel count must be between 1,024 and 1,048,576 pixels |
Settings
| Setting | Type | Default | Description |
|---|---|---|---|
| Output Format | Select | png | Dictates the content-type of the generated image. |
Output Format options
| Option | Default |
|---|---|
| jpeg | |
| png | ✓ |
| webp |
Output: Image
Fast 3D
Generate a 3D model from an image using Stable Fast 3D.
Stability AIFast 3D
Image*File upload
Texture ResolutionSelect
Foreground RatioSlider
RemeshSelect
Vertex CountNumber
Inputs
Each input can be typed in directly or connected to another node's output.
| Input | Type | Required | Description |
|---|---|---|---|
| Image | File upload | Required | The image to generate a 3D model from. Supported Formats: - jpeg - png - webp Validation Rules: - Every side must be at least 64 pixels - Total pixel count must be between 4,096 and 4,194,304 pixels |
Settings
| Setting | Type | Default | Description |
|---|---|---|---|
| Texture Resolution | Select | 1024 | Determines the resolution of the textures used for both the albedo (color) map and the normal map. The resolution is specified in pixels, and a higher value corresponds to a higher level of detail in the textures, allowing for more intricate and precise rendering of surfaces. However, increasing the resolution also results in larger asset sizes, which may impact loading times and performance. 1024 is a good default value and rarely requires changing. |
| Foreground Ratio | Slider | 0.85 | Controls the amount of padding around the object to be processed within the frame. This ratio determines the relative size of the object compared to the total frame size. A higher ratio means less padding and a larger object, while a lower ratio increases the padding, effectively reducing the object’s size within the frame. This can be useful when a long and narrow object, such as a car or bus, is viewed from the front (the narrow side). Here, lowering the foreground ratio might help prevent the generated 3D assets from appearing squished or distorted. The default value of 0.85 is good for most objects. Range: 0.1–1. |
| Remesh | Select | none | Controls the remeshing algorithm used to generate the 3D model. The remeshing algorithm determines how the 3D model is constructed from the input image. The default value of "none" means that the model is generated without remeshing, which is suitable for most use cases. The "triangle" option generates a model with triangular faces, while the "quad" option generates a model with quadrilateral faces. The "quad" option is useful when the 3D model will be used in DCC tools such as Maya or Blender. |
| Vertex Count | Number | -1 | If specified, the result will have approximately this many vertices (and consequently fewer faces) in the simplified mesh. Setting this value to -1 (the default value) means that a limit is not set. Range: -1–20000. |
Texture Resolution options
| Option | Default |
|---|---|
| 512 | |
| 1024 | ✓ |
| 2048 |
Remesh options
| Option | Default |
|---|---|
| none | ✓ |
| triangle | |
| quad |