You're looking at a specific version of this model. Jump to the model overview.
aisha-ai-official /fasercore-illustrious-v1:dec5cf4f
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)
|
FaserCore-Illustrious-v1
Options: FaserCore-Illustrious-v1 |
The model to use
|
vae |
string
(enum)
|
default
Options: default, Neptunia, FaserCore-Illustrious-v1 |
The VAE to use
|
prompt |
string
|
street, 1girl, dark-purple short hair, purple eyes, medium breasts, cleavage, casual clothes, smile, V
|
The prompt, uses Compel weighting syntax
|
negative_prompt |
string
|
nsfw, naked
|
The negative prompt (For things you don't want), uses Compel weighting syntax
|
cfg_scale |
number
|
7
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
|
1
Max: 5 |
The amount to rescale CFG generated noise to avoid generating overexposed images, set to 0 or 1 to disable
|
pag_scale |
number
|
0
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
|
1024
Min: 1 Max: 4096 |
The width of the image
|
height |
integer
|
1024
Min: 1 Max: 4096 |
The height of the image
|
prepend_preprompt |
boolean
|
True
|
Prepend preprompt (Prompt: "perfect quality, best quality, absolutely eye-catching, ambient occlusion, raytracing, " Negative prompt: "worst quality, comic, multiple views, bad quality, low quality, lowres, displeasing, very displeasing, bad anatomy, bad hands, scan artifacts, monochrome, greyscale, twitter username, jpeg artifacts, guro, extra digits, fewer digits, jaggy lines, unclear, bad_hands, bad_fingers, six_fingers, 6fingers, ")
|
scheduler |
string
(enum)
|
Euler a
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
|
30
Min: 1 Max: 100 |
The steps when generating
|
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
|
adetailer_face |
boolean
|
True
|
Use ADetailer face_yolov9c.pt
|
adetailer_face_prompt |
string
|
The prompt of ADetailer face (if blank, will use the image prompt)
|
|
adetailer_face_negative_prompt |
string
|
The negative prompt of ADetailer face (if blank, will use: blurry, deformed face, extra features, unrealistic skin texture, oversmoothed, low resolution, artifacts)
|
|
adetailer_hand |
boolean
|
False
|
Use ADetailer hand_yolov9c.pt
|
adetailer_hand_prompt |
string
|
The prompt of ADetailer hand (if blank, will use: detailed hands, realistic anatomy, well-defined fingers, natural pose, soft shadows, high resolution, intricate details)
|
|
adetailer_hand_negative_prompt |
string
|
The negative prompt of ADetailer hand (if blank, will use: extra fingers, fused or missing fingers, blurry, distorted, low detail, poorly drawn, unnatural proportions)
|
|
adetailer_person |
boolean
|
False
|
Use ADetailer person_yolov8m-seg.pt
|
adetailer_person_prompt |
string
|
The prompt of ADetailer person (if blank, will use: best quality, detailed, realistic shadows)
|
|
adetailer_person_negative_prompt |
string
|
The negative prompt of ADetailer person (if blank, will use: deformed, unrealistic proportions, extra limbs, blurred, low quality, distorted pose, exaggerated features)
|
Output schema
The shape of the response you’ll get when you run this model with an API.
{'items': {'format': 'uri', 'type': 'string'},
'title': 'Output',
'type': 'array'}