You're looking at a specific version of this model. Jump to the model overview.

delta-lock /ponynai3:3d159562

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
model
string (enum)
tPonynai3_v65

Options:

hassakuXLHentai_v13, tPonynai3_v65, waiREALCN_v120

The model to use
vae
string (enum)
default

Options:

default, hassakuXLHentai_v13, tPonynai3_v65, waiREALCN_v120

The VAE to use
prompt
string
1girl
The prompt
image
string
The image for image to image or as the base for inpainting (Will be scaled then cropped to the set width and height)
mask
string
The mask for inpainting, white areas will be modified and black preserved (Will be scaled then cropped to the set width and height)
loras
string
The LoRAs to use, must be either a string with format "URL:Strength,URL:Strength,..." (Strength is optional, default to 1), or a JSON list dumped as a string containing key "url" (Required), "strength" (Optional, default to 1), and "civitai_token" (Optional, for downloading from CivitAI) (NOTICE: Will download the weights, might take a while if the LoRAs are huge or the download is slow, WILL CHARGE WHEN DOWNLOADING)
negative_prompt
string
animal, cat, dog, big breasts
The negative prompt (For things you don't want)
cfg_scale
number
5

Min: 1

Max: 50

CFG scale defines how much attention the model pays to the prompt when generating, set to 1 to disable
guidance_rescale
number
0.5

Max: 5

The amount to rescale CFG generated noise to avoid generating overexposed images, set to 0 or 1 to disable
pag_scale
number
3

Max: 50

PAG scale is similar to CFG but it literally makes the result better, it's compatible with CFG too, set to 0 to disable
clip_skip
integer
1

Min: 1

How many CLIP layers to skip, 1 is actually no skip, this is the behavior in A1111 so it's aligned to it
width
integer
1184

Min: 1

Max: 4096

The width of the image
height
integer
864

Min: 1

Max: 4096

The height of the image
prepend_preprompt
boolean
True
Prepend preprompt (Prompt: "score_9, score_8_up, score_7_up, " Negative prompt: "score_4, score_3, score_2, score_1, worst quality, bad hands, bad feet, ")
scheduler
string (enum)
DPM++ 2M SDE Karras

Options:

DPM++ 2M SDE Karras, UniPC, Heun, DDIM, DPM2 a, DPM2 a Karras, DPM SDE, DDPM, DPM++ SDE, DPM++ SDE Karras, LMS, LMS Karras, Euler a, Euler, PNDM, DPM2, DPM2 Karras, DEIS, DPM++ 2M, DPM++ 2M Karras, DPM++ 2M SDE

The scheduler to use
steps
integer
35

Min: 1

Max: 100

The steps when generating
strength
number
0.7

Max: 1

How much noise to add (For image to image and inpainting only, larger value indicates more noise added to the input image)
blur_factor
number
5
The factor to blur the inpainting mask for smoother transition between masked and unmasked
batch_size
integer
1

Min: 1

Max: 4

Number of images to generate (1-4), note if you set this to 4, some high resolution gens might fail because of not enough VRAM
seed
integer
-1
The seed used when generating, set to -1 for random seed

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'}