fermatresearch/high-resolution-controlnet-tile

UPDATE: new upscaling algorithm for a much improved image quality. Fermat.app open-source implementation of an efficient ControlNet 1.1 tile for high-quality upscales. Increase the creativity to encourage hallucination.

Input

Configure the inputs for the AI model.

Hdr

HDR improvement over the original image

Seed

Image

Control image for scribble controlnet

Steps

100

Steps

format

Format of the output.

Prompt

Prompt for the model

scheduler

Choose a scheduler.

Creativity

0.1

Denoising strength. 1 means total destruction of the original image

Guess Mode

Enable

In this mode, the ControlNet encoder will try best to recognize the content of the input image even if you remove all prompts.

resolution

Image resolution

Resemblance

Conditioning scale for controlnet

Guidance Scale

Scale for classifier-free guidance, should be 0.

Negative Prompt

Negative prompt

Lora Details Strength

-5

Strength of the image's details

Lora Sharpness Strength

-5

Strength of the image's sharpness. We don't recommend values above 2.

Output

The generated output will appear here.

No output yet

Click "Generate" to create an output.