usamaehsan/controlnet-x-ip-adapter-realistic-vision-v5

Inpainting || multi-controlnet || single-controlnet || ip-adapter || ip adapter face || ip adapter plus || No ip adapter

Input
Configure the inputs for the AI model.
0
100

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

Seed

Prompt - using compel, use +++ to increase words weight:: doc: https://github.com/damian0815/compel/tree/main/doc || https://invoke-ai.github.io/InvokeAI/features/PROMPTS/#attention-weighting

0
100

Max width/Resolution of image

Choose a scheduler.

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.

mask image for inpainting controlnet

0
100

Max height/Resolution of image

Control image for tile controlnet

1
10

Number of images to generate

Image2image image

Control image for canny controlnet

0.1
30

Scale for classifier-free guidance

Control image for scribble controlnet

IP Adapter checkpoint

Negative prompt - using compel, use +++ to increase words weight//// negative-embeddings available ///// FastNegativeV2 , boring_e621_v4 , verybadimagenegative_v1 || to use them, write their keyword in negative prompt

Control image for brightness controlnet

0
100

img2img strength, does not work when inpainting image is given, 0.1-same image, 0.99-complete destruction of image

Control image for inpainting controlnet

IP Adapter image

0
100

IP Adapter weight

Comma seperated string of controlnet names, list of names: tile, inpainting, lineart,depth ,scribble , brightness /// example value: tile, inpainting, lineart

0
100

inpainting strength

0
100

Steps to run denoising

Disable safety check. Use at your own risk!

0
100

disabled on 0

// seperated list of objects you dont want to mask - 'hairs // eyes // cloth'

// seperated list of objects for mask, AI will auto create mask of these objects, if mask text is given, mask image will not work - 'hairs // eyes // cloth'

0
100

Conditioning scale for tile controlnet

0
100

Scale/ weight of more_details lora, more scale = more details, disabled on 0

0
100

disabled on 0

0
100

Conditioning scale for canny controlnet

0
100

Conditioning scale for scribble controlnet

0
100

disabled on 0

0
100

Conditioning scale for brightness controlnet

0
100

Conditioning scale for inpaint controlnet

0
100

disabled on 0

Output
The generated output will appear here.

No output yet

Click "Generate" to create an output.

controlnet-x-ip-adapter-realistic-vision-v5 - ikalos.ai