You're looking at a specific version of this model. Jump to the model overview.
Input schema
The fields you can use to run this model with an API. If you don’t give a value for a field its default value will be used.
| Field | Type | Default value | Description |
|---|---|---|---|
| prompt |
string
|
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
|
|
| negative_prompt |
string
|
Longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality
|
Negative prompt - using compel, use +++ to increase words weight
|
| num_inference_steps |
integer
|
20
|
Steps to run denoising
|
| guidance_scale |
number
|
7
Min: 0.1 Max: 30 |
Scale for classifier-free guidance
|
| seed |
integer
|
Seed
|
|
| eta |
number
|
0
|
Controls the amount of noise that is added to the input data during the denoising diffusion process. Higher value -> more noise
|
| guess_mode |
boolean
|
False
|
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 |
boolean
|
False
|
Disable safety check. Use at your own risk!
|
| num_outputs |
integer
|
1
Min: 1 Max: 10 |
Number of images to generate
|
| max_width |
integer
|
512
|
Max width/Resolution of image
|
| max_height |
integer
|
512
|
Max height/Resolution of image
|
| scheduler |
string
(enum)
|
DDIM
Options: DDIM, DPMSolverMultistep, HeunDiscrete, K_EULER_ANCESTRAL, K_EULER, KLMS, PNDM, UniPCMultistep |
Choose a scheduler.
|
| lineart_image |
string
|
Control image for canny controlnet
|
|
| lineart_conditioning_scale |
number
|
1
|
Conditioning scale for canny controlnet
|
| scribble_image |
string
|
Control image for scribble controlnet
|
|
| scribble_conditioning_scale |
number
|
1
|
Conditioning scale for scribble controlnet
|
| tile_image |
string
|
Control image for tile controlnet
|
|
| tile_conditioning_scale |
number
|
1
|
Conditioning scale for tile controlnet
|
| brightness_image |
string
|
Control image for brightness controlnet
|
|
| brightness_conditioning_scale |
number
|
1
|
Conditioning scale for brightness controlnet
|
| inpainting_image |
string
|
Control image for inpainting controlnet
|
|
| mask_image |
string
|
mask image for inpainting controlnet
|
|
| inpainting_conditioning_scale |
number
|
1
|
Conditioning scale for brightness controlnet
|
| sorted_controlnets |
string
|
tile, inpainting, lineart
|
Comma seperated string of controlnet names, list of names: tile, inpainting, lineart,depth ,scribble , brightness /// example value: tile, inpainting, lineart
|
| ip_adapter_ckpt |
string
(enum)
|
ip-adapter_sd15.bin
Options: ip-adapter_sd15.bin, ip-adapter-plus_sd15.bin, ip-adapter-plus-face_sd15.bin |
IP Adapter checkpoint
|
| ip_adapter_image |
string
|
IP Adapter image
|
|
| ip_adapter_weight |
number
|
1
|
IP Adapter weight
|
| img2img_image |
string
|
Image2image image
|
|
| img2img_strength |
number
|
0.5
|
img2img strength, does not work when inpainting image is given, 0.1-same image, 0.99-complete destruction of image
|
| add_more_detail_lora_scale |
number
|
0.5
|
Scale/ weight of more_details lora, more scale = more details
|
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{'items': {'format': 'uri', 'type': 'string'},
'title': 'Output',
'type': 'array'}