qr-code-controlnet

Simplify QR code creation using ControlNet user-friendly neural interface

Hold: 0

Required: 25,000 $wRAI

45.2k runs

Input

url

Link Url for QR Code.

prompt

Prompt for the model

qr_conditioning_scale

Conditioning scale for qr controlnet

num_outputs

Number of images to generate (minimum: 1; maximum: 2)

image_resolution

Resolution of image (smallest dimension)

scheduler

Choose a scheduler.

num_inference_steps

Steps to run denoising

guidance_scale

Scale for classifier-free guidance (minimum: 0.1; maximum: 5)

seed

Seed for random number generator. If empty, a random seed will be chosen.

eta

Controls the amount of noise that is added to the input data during the denoising diffusion process. Higher value -> more noise

negative_prompt

Negative prompt

guess_mode

In this mode, the ControlNet encoder will try best to recognize the content of the input image even if you remove all prompts. The `guidance_scale` between 3.0 and 5.0 is recommended.

disable_safety_check

Disable safety check. Use at your own risk!

Hold at least 25,000 wRAI to use this model

Multi AI platform is completely free, but most models are only accessible to wRAI token holders. If you have any questions, feel free to ask in our Telegram chat

Output

Input

eta

guidance_scale

1.9

image_resolution

768

negative_prompt

Longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality

num_inference_steps

num_outputs

prompt

cyberpunk

qr_conditioning_scale

1.3

scheduler

DDIM

seed

-1

url

multi-ai.pro

Output

Readme

Introducing the ControlNet QR Code Generator – a tool that uses ControlNet models twRAIned on stable diffusion 2.1. It lets you turn URLs into QR codes with images easily.

These models have learned from 150,000 pairs of QR codes and QR code artwork. This means you can make QR codes that look good and work well.

ControlNet is a special kind of neural network. It adds extra rules to how models work. It does this by copying the weights of the neural network into two copies: one that you can’t change and one that you can. The copy you can change learns from the conditions you give it. The other copy stays the same, keeping your model safe.

What to do if the QR code doesn't open my link?

Check the accuracy of the entered link. It should not contain any extra characters after the first or second-level domain.
Try entering a simpler prompt.
Decrease the guidance_scale.