Blog
Replicate
STABLE

ControlNet x Realistic Vision v5

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

Inputs
Prompt
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
Add More Detail Lora Scale
Scale/ weight of more_details lora, more scale = more details, disabled on 0
Brightness Conditioning Scale
Conditioning scale for brightness controlnet
Brightness Image
Control image for brightness controlnet
Color Temprature Slider Lora Weight
disabled on 0
Detail Tweaker Lora Weight
disabled on 0
Disable Safety Check
Disable safety check. Use at your own risk!
Epi Noise Offset Lora Weight
disabled on 0
Eta
Controls the amount of noise that is added to the input data during the denoising diffusion process. Higher value -> more noise
Film Grain Lora Weight
disabled on 0
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.
Guidance Scale
Scale for classifier-free guidance
Img2Img Image
Image2image image
Img2Img Strength
img2img strength, does not work when inpainting image is given, 0.1-same image, 0.99-complete destruction of image
Inpainting Conditioning Scale
Conditioning scale for inpaint controlnet
Inpainting Image
Control image for inpainting controlnet
Inpainting Strength
inpainting strength
Int Kwargs
ip_adapter_ckpt
IP Adapter checkpoint
Ip Adapter Image
IP Adapter image
Ip Adapter Weight
IP Adapter weight
Lineart Conditioning Scale
Conditioning scale for canny controlnet
Lineart Image
Control image for canny controlnet
Mask Image
mask image for inpainting controlnet
Max Height
Max height/Resolution of image
Max Width
Max width/Resolution of image
Negative Auto Mask Text
// seperated list of objects you dont want to mask - 'hairs // eyes // cloth'
Negative Prompt
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
Num Inference Steps
Steps to run denoising
Num Outputs
Number of images to generate
Output Index
If output is a list, which element to use
Positive Auto Mask Text
// 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'
scheduler
Choose a scheduler.
Scribble Conditioning Scale
Conditioning scale for scribble controlnet
Scribble Image
Control image for scribble controlnet
Seed
Seed
Sorted Controlnets
Comma seperated string of controlnet names, list of names: tile, inpainting, lineart,depth ,scribble , brightness /// example value: tile, inpainting, lineart
Tile Conditioning Scale
Conditioning scale for tile controlnet
Tile Image
Control image for tile controlnet
Outputs
Urls
URLs of the images