StabilityStableImageSD_3_5Node - ComfyUI Built-in Node Documentation

This node generates images synchronously using Stability AI’s Stable Diffusion 3.5 model. It creates images based on text prompts and can also modify existing images when provided as input. The node supports various aspect ratios and style presets to customize the output.

Inputs

Parameter	Description	Data Type	Required	Range
`prompt`	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. (default: empty string)	STRING	Yes	-
`model`	The Stable Diffusion 3.5 model to use for generation.	COMBO	Yes	`sd3.5-large` `sd3.5-large-turbo` `sd3.5-medium`
`aspect_ratio`	Aspect ratio of generated image. (default: 1:1)	COMBO	Yes	`16:9` `1:1` `21:9` `2:3` `3:2` `4:5` `5:4` `9:16` `9:21`
`style_preset`	Optional desired style of generated image. Select “None” for no style preset.	COMBO	No	`3d-model` `analog-film` `anime` `cinematic` `comic-book` `digital-art` `enhance` `fantasy-art` `isometric` `line-art` `low-poly` `modeling-compound` `neon-punk` `origami` `photographic` `pixel-art` `tile-texture` `None`
`cfg_scale`	How strictly the diffusion process adheres to the prompt text (higher values keep your image closer to your prompt). (default: 4.0)	FLOAT	Yes	1.0 to 10.0
`seed`	The random seed used for creating the noise. (default: 0)	INT	Yes	0 to 4294967294
`image`	Optional input image for image-to-image generation. When provided, the node switches to image-to-image mode and the `aspect_ratio` parameter is ignored.	IMAGE	No	-
`negative_prompt`	Keywords of what you do not wish to see in the output image. This is an advanced feature. (default: empty string)	STRING	No	-
`image_denoise`	Denoise of input image; 0.0 yields image identical to input, 1.0 is as if no image was provided at all. (default: 0.5) This parameter is only used when an `image` is provided.	FLOAT	No	0.0 to 1.0

Note: When an image is provided, the node switches to image-to-image generation mode and the aspect_ratio parameter is automatically determined from the input image. When no image is provided, the image_denoise parameter is ignored.

Outputs

Output Name	Description	Data Type
`image`	The generated or modified image.	IMAGE

This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub

Source fingerprint (SHA-256): aa071616da3ff645dfbc885c84706324d555c18772d3cc0d603b5699a0e7dfff

​Inputs

​Outputs

Inputs

Outputs