pnyompen/sd-controlnet-lora

SD1.5 Canny controlnet with LoRA support.

Input

Configure the inputs for the AI model.

Seed

Random seed. Leave blank to randomize the seed

Image

Input image for img2img or inpaint mode

Prompt

Input prompt

Img2Img

Enable

Use img2img pipeline, it will use the image input both as the control image and the base image.

Strength

When img2img is active, the denoising strength. 1 means total destruction of the input image.

Remove Bg

Enable

Remove background from the input image

scheduler

Lora Scale

LoRA additive scale. Only applicable on trained models.

Num Outputs

Number of images to output

Lora Weights

Replicate LoRA weights to use. Leave blank to use the default weights.

Guidance Scale

Scale for classifier-free guidance

Condition Scale

The bigger this number is, the more ControlNet interferes

Negative Prompt

Input Negative Prompt

Ip Adapter Scale

100

Scale for the IP Adapter

Num Inference Steps

500

Number of denoising steps

Auto Generate Caption

Enable

Use BLIP to generate captions for the input images

Generated Caption Weight

100

Weight for the generated caption

Output

The generated output will appear here.

Click "Generate" to create an output.