Redo

The Rodin redo function is designed to re-generate 3D meshes from images based on new prompts or settings.

The request body should be wrapped in the FormData instead of plain JSON, while settings should be parsed to JSON.

Redo Rodin generation with new prompt and weights.

post

Authorizations

Body

promptstringrequired

reference_imagestringoptional

settingsobjectrequired

uuidstringrequired

Responses

application/json

cURL

JavaScript

Python

HTTP

cURL

curl -L \
  --request POST \
  --url '/api/task/rodin_update' \
  --header 'Authorization: Bearer JWT' \
  --header 'Content-Type: application/json' \
  --data '{
    "prompt": "text",
    "reference_image": "text",
    "settings": {
      "view_weights": [
        1
      ],
      "image_label": [
        "F"
      ],
      "condition_mode": "fuse",
      "bbox_condition": [
        1
      ],
      "bbox_condition_cfg": true,
      "bbox_condition_weight": 1,
      "voxel_condition": "text",
      "voxel_condition_cfg": true,
      "voxel_condition_weight": 1,
      "pcd_condition": [
        [
          1
        ]
      ],
      "pcd_condition_cfg": true,
      "pcd_condition_weight": 1,
      "pcd_condition_uncertainty": 1,
      "escore": 1,
      "seed": 1,
      "reference_scale": 1,
      "fast_texture": true,
      "inference_steps": 1,
      "guidance_scale": 1,
      "negative_prompt": "text",
      "rest_bias": 1,
      "image_mode": "recon",
      "enable_advance_option": true,
      "height": 1,
      "face_enhance": true,
      "allow_face_enhance": true,
      "default_face_enhance": true
    },
    "uuid": "text"
  }'

201

201

{
  "error": "OK",
  "job": {
    "uuids": [
      []
    ],
    "subscription_key": "text"
  }
}