TRStart creating
Menu

Stable Diffusion with LoRAs

Run Any Stable Diffusion model with customizable LoRA weights.

Input

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

URL or HuggingFace ID of the base model to generate the image.

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

URL of image to use for image to image/inpainting.

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

The URL of the IC Light model background image to use for the image generation. Make sure to use a background compatible with the model.

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

The URL of the IC Light model image to use for the image generation.

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

Number of images to generate in one request. Note that the higher the batch size, the longer it will take to generate the images.

Additional settings

URL or HuggingFace ID of the custom U-Net model to use for the image generation.

The variant of the model to use for huggingface models, e.g. 'fp16'.

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).

If set to true, the prompt weighting syntax will be used. Additionally, this will lift the 77 token limit by averaging embeddings.

Tips and requirements

The amount of noise to add to noise image for image. Only used if the image_url is provided. 1.0 is complete noise and values near 0 are minimal noise.

The LoRAs to use for the image generation. You can use any number of LoRAs and they will be merged together to generate the final image.

Tips and requirements

The embeddings to use for the image generation. Only a single embedding is supported at the moment. The embeddings will be used to map the tokens in the prompt to the embedding weights.

Tips and requirements

The control nets to use for the image generation. You can use any number of control nets and they will be applied to the image at the specified timesteps.

If set to true, the controlnet will be applied to only the conditional predictions.

IP adapters for image generation. A non-empty list requires image_encoder_path.

Tips and requirements

Hugging Face ID or HTTPS URL of the image encoder; required when ip_adapter is non-empty. Choose an encoder compatible with the IP-Adapter weights. For h94/IP-Adapter SDXL weights, use h94/IP-Adapter with image_encoder_subfolder='sdxl_models/image_encoder'; for SD1.5 weights, use image_encoder_subfolder='models/image_encoder'.

Subfolder containing the image encoder weights in image_encoder_path.

The weight name of the image encoder model to use for the image generation.

The URL of the IC Light model to use for the image generation.

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

Tips and requirements

Increasing the amount of steps tells Stable Diffusion that it should take more steps to generate your final result which can increase the amount of detail in your image.

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.

Skips part of the image generation process, leading to slightly different results. This means the image renders faster, too.

Scheduler / sampler to use for the image denoising process.

The type of prediction to use for the image generation. The epsilon is the default.

Whether to set the rescale_betas_snr_zero option or not for the sampler

The format of the generated image.

The size of the tiles to be used for the image generation.

The size of the tiles to be used for the image generation.

The stride of the tiles to be used for the image generation.

The stride of the tiles to be used for the image generation.

The eta value to be used for the image generation.

If set to true, the latents will be saved for debugging.

If set to true, the latents will be saved for debugging per pass.

Some published inputs are not in this form.

  • Timesteps: Nested object inputs are not supported yet. It is not sent.
  • Sigmas: Nested object inputs are not supported yet. It is not sent.
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 Stable Diffusion with LoRAs

Getting started

Use a compatible base and adapter for a particular character or style. Image-to-image and inpaint are separate operations.

Review your result

Check subject consistency and unwanted style spillover; inspect repaired edges when using inpaint.

Inputs and settings

The default operation requires model_name and prompt. Add compatible loras and keep the base model fixed when comparing adapter weights.

Use image_url in image-to-image; supply the source and mask_url for inpaint. noise_strength belongs to those image operations, not the default text mode.

We use analytics cookies. Privacy policy