POST
/
adetailer
{
  "image_b64": "<string>",
  "num_objects_inpainted": 123,
  "num_objects_detected": 123,
  "num_removed_for_safety": 123
}

Body

application/json
init_image
string | null

base64-encoded image to modify. Resolution must be supported by inpainting_base_model: sdxl: 640x1536, 768x1344, 832x1216, 896x1152, 1024x1024, 1152x896, 1216x832, 1344x768, 1536x640, 1664x2432, 2048x2048, 2432x1664; sd15: 384x704, 448x576, 512x512, 512x704, 512x768, 512x832, 576x448, 576x768, 576x768, 576x1024, 640x512, 640x640, 640x768, 704x384, 704x1216, 768x512, 768x576, 768x1024, 832x512, 896x896, 1024x576, 1024x768, 1024x1024, 1024x1536, 1216x704, 1536x1024.

init_image_url
string | null

If given, download init_image from this URL.

image_encoding
enum<string>

Define which encoding process should be applied before returning the modified image.

Available options:
jpeg,
png
prompt
string | null
negative_prompt
string | null
sampler
enum<string>

The schedulers available for image generation.

Available options:
PNDM,
LMS,
KLMS,
DDIM,
DDPM,
HEUN,
K_HEUN,
K_EULER,
K_EULER_ANCESTRAL,
DPM_SOLVER_MULTISTEP,
DPM_PLUS_PLUS_2M_KARRAS,
DPM_SINGLE,
DPM_2,
DPM_2_ANCESTRAL,
DPM_PLUS_PLUS_SDE_KARRAS,
UNI_PC,
LCM
steps
integer
default: 20
inpainting_base_model
enum<string> | null

The base model to be used for inpainting. Typically should match the model used to generate init_image.

Available options:
sdxl,
sd15
checkpoint
string | null

Name of a checkpoint to use for inpainting.

loras
object | null

A dict mapping the name of a LoRA to apply to its weight.

use_refiner
boolean
default: false
style_preset
string
default: base
strength
number
default: 0.9
cfg_scale
number
default: 7.5

Floating-point number represeting how closely to adhere to prompt description. Must be a positive number no greater than 50.0.

seed

Integer number or list of integers representing the seeds of random generators. Fixing random seed is useful when attempting to generate a specific image. Must be greater than 0 and less than 2^32.

mask_dilation
integer
default: 4

A mask is created for each inpainted area in the image. Mask Dilation allows you to expand the size of the mask while maintaining its shape. This technique is typically used to reduce artifacts near borders in the mask. This parameter is the size, in pixels, of the dilation kernel to apply. Defaults to 4. Must be greater than or equal to 0 and recommended to be less than 64.

mask_blur
integer
default: 4

A mask is created for each inpainted area in the image. After dilation (see mask_dilation parameter), the mask is blurred. This technique is typically used to smoothly blend the inpainted area with the original image. This option specifies the radius, in pixels, of the gaussian blur kernel. The higher the value, the wider the blur. Defaults to 4. Must be greater than or equal to 0 and recommended to be less than 64.

mask_padding
integer
default: 32

Each inpainted area is passed to the image-to-image generator with some surrounding context. The contextual area is created by padding the area occupied by the blurred, dilated mask. This technique improves inpainting quality, and the contextual area is not modified. This parameter specifies the amount of padding, in pixels, to apply around the processed mask. When the computed padding goes off the edge of the image, the padded area is slid towards the center of the image. Must be greater than or equal to 0 and recommended to be less than 10% the size of an inpainting mask.

max_num_detections
integer | null

Inpaint at most this many objects, starting with the most confident matches.

confidence
number
default: 0.3

Inpainted areas are determined using a detector. This setting adjusts the sensitivity of the detector (lower considers more image fragments for inpainting).

detector
enum<string>
required

Detection model to use. Configures whether e.g. faces or hands or people are targeted for after-detailing.

Available options:
face_yolov8n,
hand_yolov8n,
face_full_mediapipe,
face_short_mediapipe,
face_mesh_mediapipe,
eyes_mesh_mediapipe
union_masks
boolean
default: false

When true, create a single mask by unioning the mask for each detected object together, then send a single inpainting request to the backing model.

Response

200 - application/json
image_b64
string | null
required

The modified image or None if it was removed for safety.

num_objects_inpainted
integer
required

The number of objects that were successfully inpainted.

num_objects_detected
integer
required

The number of objects that were successfully detected.

num_removed_for_safety
integer
required

Number of inpainting requests that violated the OctoAI Terms of Service.

Was this page helpful?

Generate SVD AnimationsRemove Background