You're looking at a specific version of this model. Jump to the model overview.
aisha-ai-official /projectil-v3:55ca6492
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)
|
ProjectIL-v3
Options: ProjectIL-v3 |
The model to use
|
| vae |
string
(enum)
|
default
Options: default, Liquid111, NeptuniaXL-VAE-ContrastSaturation, ProjectIL-v3 |
The VAE to use
|
| prompt_conjunction |
boolean
|
False
|
Force Compel conjunction syntax on prompt, separating linebreaks into different items on the Compel conjunction function
|
| prompt |
string
|
street, 1girl, dark-purple short hair, purple eyes, medium breasts, cleavage, casual clothes, smile
|
The prompt, uses Compel weighting syntax
|
| negative_prompt |
string
|
nsfw, naked
|
The negative prompt (for things you don't want), uses Compel weighting syntax
|
| negative_prompt_conjunction |
boolean
|
False
|
Force Compel conjunction syntax on prompt, separating linebreaks into different items on the Compel conjunction function
|
| 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
Max: 5 |
Amount to rescale CFG generated noise to avoid overexposed images, set to 0 or 1 to disable
|
| pag_scale |
number
|
0
Max: 50 |
PAG scale is similar to CFG but improves the result; set to 0 to disable
|
| clip_skip |
integer
|
0
|
How many CLIP layers to skip; 1 means no skip
|
| width |
integer
|
1024
Min: 1 Max: 4096 |
The width of the image
|
| height |
integer
|
1024
Min: 1 Max: 4096 |
The height of the image
|
| upscale |
string
(enum)
|
Original
Options: Original, x2, x4, x8 |
Upscale factor
|
| refiner |
boolean
|
False
|
Enable image refiner using model
|
| refiner_prompt |
string
|
|
The prompt of refiner (leave empty for default correct hands and details)
|
| refiner_strength |
number
|
0.4
Max: 1 |
Refiner strength (0.0 to 1.0)
|
| prepend_preprompt |
boolean
|
True
|
Prepend preprompt (Prompt: "masterpiece, best quality, absurdres," | Negative prompt: "low quality, bad quality, watermark,")
|
| scheduler |
string
(enum)
|
DPM++ 2M SDE Karras
Options: DPM++ 2M, DPM++ 2M Karras, DPM++ 2M SDE, DPM++ 2M SDE Karras, DPM++ 2M simple, DPM++ 2M exponential, DPM++ 2M beta, DPM++ 2M SDE simple, DPM++ 2M SDE exponential, DPM++ 2M SDE beta, UniPC, UniPC Karras, UniPC simple, UniPC exponential, UniPC beta, Heun, Heun Karras, Heun simple, Heun exponential, Heun beta, DDIM, DDIM Karras, DDIM simple, DDIM exponential, DDIM beta, DPM2 a, DPM2 a Karras, DPM2 a simple, DPM2 a exponential, DPM2 a beta, DPM SDE, DPM SDE Karras, DPM SDE simple, DPM SDE exponential, DPM SDE beta, DDPM, DDPM Karras, DDPM simple, DDPM exponential, DDPM beta, DPM++ SDE, DPM++ SDE Karras, DPM++ SDE simple, DPM++ SDE exponential, DPM++ SDE beta, LMS, LMS Karras, LMS simple, LMS exponential, LMS beta, Euler a, Euler a Karras, Euler a simple, Euler a exponential, Euler a beta, Euler, Euler Karras, Euler simple, Euler exponential, Euler beta, PNDM, PNDM Karras, PNDM simple, PNDM exponential, PNDM beta, DPM2, DPM2 Karras, DPM2 simple, DPM2 exponential, DPM2 beta, DEIS, DEIS Karras, DEIS simple, DEIS exponential, DEIS beta, CMStochasticIterativeScheduler, CMStochasticIterativeScheduler Karras, CMStochasticIterativeScheduler simple, CMStochasticIterativeScheduler exponential, CMStochasticIterativeScheduler beta, CogVideoXDDIMScheduler, CogVideoXDDIMScheduler Karras, CogVideoXDDIMScheduler simple, CogVideoXDDIMScheduler exponential, CogVideoXDDIMScheduler beta, CogVideoXDPMScheduler, CogVideoXDPMScheduler Karras, CogVideoXDPMScheduler simple, CogVideoXDPMScheduler exponential, CogVideoXDPMScheduler beta, CosineDPMSolverMultistepScheduler, CosineDPMSolverMultistepScheduler Karras, CosineDPMSolverMultistepScheduler simple, CosineDPMSolverMultistepScheduler exponential, CosineDPMSolverMultistepScheduler beta, DDIMInverseScheduler, DDIMInverseScheduler Karras, DDIMInverseScheduler simple, DDIMInverseScheduler exponential, DDIMInverseScheduler beta, EDMDPMSolverMultistepScheduler, EDMDPMSolverMultistepScheduler Karras, EDMDPMSolverMultistepScheduler simple, EDMDPMSolverMultistepScheduler exponential, EDMDPMSolverMultistepScheduler beta, EDMEulerScheduler, EDMEulerScheduler Karras, EDMEulerScheduler simple, EDMEulerScheduler exponential, EDMEulerScheduler beta, FlowMatchEulerDiscreteScheduler, FlowMatchEulerDiscreteScheduler Karras, FlowMatchEulerDiscreteScheduler simple, FlowMatchEulerDiscreteScheduler exponential, FlowMatchEulerDiscreteScheduler beta, FlowMatchHeunDiscreteScheduler, FlowMatchHeunDiscreteScheduler Karras, FlowMatchHeunDiscreteScheduler simple, FlowMatchHeunDiscreteScheduler exponential, FlowMatchHeunDiscreteScheduler beta, IPNDMScheduler, IPNDMScheduler Karras, IPNDMScheduler simple, IPNDMScheduler exponential, IPNDMScheduler beta, KarrasVeScheduler, KarrasVeScheduler Karras, KarrasVeScheduler simple, KarrasVeScheduler exponential, KarrasVeScheduler beta, LCMScheduler, LCMScheduler Karras, LCMScheduler simple, LCMScheduler exponential, LCMScheduler beta, RePaintScheduler, RePaintScheduler Karras, RePaintScheduler simple, RePaintScheduler exponential, RePaintScheduler beta, ScoreSdeVeScheduler, ScoreSdeVeScheduler Karras, ScoreSdeVeScheduler simple, ScoreSdeVeScheduler exponential, ScoreSdeVeScheduler beta, TCDScheduler, TCDScheduler Karras, TCDScheduler simple, TCDScheduler exponential, TCDScheduler beta, VQDiffusionScheduler, VQDiffusionScheduler Karras, VQDiffusionScheduler simple, VQDiffusionScheduler exponential, VQDiffusionScheduler beta |
The scheduler to use
|
| steps |
integer
|
30
Min: 1 Max: 100 |
Number of steps when generating
|
| seed |
integer
|
-1
|
The seed for generation; set to -1 for random seed
|
| adetailer_face |
boolean
|
False
|
Use ADetailer face_yolov9c.pt
|
| adetailer_face_prompt |
string
|
|
ADetailer face prompt (if blank, will use the image prompt)
|
| adetailer_face_negative_prompt |
string
|
|
ADetailer face negative prompt (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
|
|
ADetailer hand prompt (if blank, will use: detailed hands, realistic anatomy, well-defined fingers, natural pose, soft shadows, high resolution, intricate details)
|
| adetailer_hand_negative_prompt |
string
|
|
ADetailer hand negative prompt (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
|
|
ADetailer person prompt (if blank, will use: best quality, detailed, realistic shadows)
|
| adetailer_person_negative_prompt |
string
|
|
ADetailer person negative prompt (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'}