SDXL ControlNet Union

An efficent SDXL multi-controlnet text-to-image model.

Input

Fields marked * are required. Review the price before generating.

Prompt *

The prompt to use for generating the image. Be as descriptive as possible for best results.

Image Size

The size of the generated image. Leave it none to automatically infer from the control image.

Num Images

The number of images to generate.

Openpose Image

The URL of the control image.

Uploading a file needs an account. Create accountJPEG, PNG, WebP · up to 25 MB

Depth Image

The URL of the control image.

Uploading a file needs an account. Create accountJPEG, PNG, WebP · up to 25 MB

Teed Image

The URL of the control image.

Uploading a file needs an account. Create accountJPEG, PNG, WebP · up to 25 MB

Canny Image

The URL of the control image.

Uploading a file needs an account. Create accountJPEG, PNG, WebP · up to 25 MB

Normal Image

The URL of the control image.

Uploading a file needs an account. Create accountJPEG, PNG, WebP · up to 25 MB

Segmentation Image

The URL of the control image.

Uploading a file needs an account. Create accountJPEG, PNG, WebP · up to 25 MB

Additional settings

Controlnet Conditioning Scale

The scale of the controlnet conditioning.

Negative Prompt

Tips and requirements

The negative prompt to use. Use it to address details that you don't want in the image. This could be colors, objects, scenery and even the small details (e.g. moustache, blurry, low resolution).

Num Inference Steps

The number of inference steps to perform.

Seed

The same seed and the same prompt given to the same version of Stable Diffusion will output the same image every time.

Guidance scale (CFG)

Tips and requirements

The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you.

Loras

The list of LoRA weights to use.

Embeddings

The list of embeddings to use.

Enable Prompt Expansion

If set to true, the prompt will be expanded with additional prompts.

Format

The format of the generated image.

Openpose Preprocess

Whether to preprocess the openpose image.

Depth Preprocess

Whether to preprocess the depth image.

Teed Preprocess

Whether to preprocess the teed image.

Canny Preprocess

Whether to preprocess the canny image.

Normal Preprocess

Whether to preprocess the normal image.

Segmentation Preprocess

Whether to preprocess the segmentation image.

Price$0.60 / run

You sign up first. Your settings are kept.

API code for this input

Complete the required fields and fix input errors to see API code.

How to use SDXL ControlNet Union

Getting started

Combine structural controls for an SDXL scene with ControlNet Union. Begin with one control type so its effect is easy to judge.

Review your result

Check alignment between control maps and whether added controls conflict with one another.

Inputs and settings

Send prompt and the matching control URL, such as depth_image_url or canny_image_url.

Use the corresponding preprocess switch for that input. Different editing modes require their own image or mask fields.