fofr/latent-consistency-model

Super-fast, 0.6s per image. LCM with img2img, large batching and canny controlnet

Input

Configure the inputs for the AI model.

Seed

Random seed. Leave blank to randomize the seed

Image

Input image for img2img

Width

100

Width of output image. Lower if out of memory

Height

100

Height of output image. Lower if out of memory

Prompt

For multiple prompts, enter each on a new line.

Num Images

Number of images per prompt

Control Image

Image for controlnet conditioning

Guidance Scale

Scale for classifier-free guidance

Archive Outputs

Enable

Option to archive the output images

Prompt Strength

Prompt strength when using img2img. 1.0 corresponds to full destruction of information in image

sizing_strategy

Decide how to resize images – use width/height, resize based on input image or control image

Lcm Origin Steps

100

Canny Low Threshold

255

Canny low threshold

Num Inference Steps

Number of denoising steps. Recommend 1 to 8 steps.

Canny High Threshold

255

Canny high threshold

Control Guidance End

Controlnet end

Control Guidance Start

Controlnet start

Disable Safety Checker

Enable

Disable safety checker for generated images. This feature is only available through the API

Controlnet Conditioning Scale

0.1

Controlnet conditioning scale

Output

The generated output will appear here.

No output yet

Click "Generate" to create an output.