Texture model (v3.0-20250812)
All supported parameters for texture_model when model_version is v3.0-20250812.
Endpoint
Parameters
Required parameters
type: This field must be set to texture_model.
original_model_task_id: The task_id of previous model, the model_version of previous task should be in (Turbo-v1.0-20250506 or over v2.0-20240919). Only the task IDs of the tasks which has model output can be used.
Note
1.x versions of text_to_model, image_to_model and multiview_to_model tasks are not supported.
texture_prompt: The structure can be seem below:
text: Atextvalue that directs the texture generation, mutually exclusive withimageandimages.image: Afileobject that directs the texture generation, mutually exclusive withtextandimages.images: Afilelist that directs the texture generation, mutually exclusive withtextandimage.style_image(Optional): Afileobject that allows you to provide a reference image to influence the artistic style of the generated model.
File object
file: Specifies the image input.
type: Indicates the file type. Although currently not validated, specifying the correct file type is strongly advised.file_token: The identifier you get from upload, please refer to part of Upload directly. Mutually exclusive withurlandobject.url: A direct URL to the image. Supports JPEG and PNG formats with a maximum size of 20MB. Mutually exclusive withfile_tokenandobject.object(Strongly Recommended): The information you get from upload, please refer to Upload in STS. Mutually exclusive withurlandfile_token.bucket: Normally it always will betripo-data.key: Theresource_urifrom returns.
Optional parameters
model_version: Should be set to v3.0-20250812.
texture: A bool value to enable texturing. The default value is true. Set false to only update the pbr texture while pbr=true.
pbr: A bool value to enable pbr. The default value is true. Set false to get a model without pbr.
texture_seed: An integer value chosed randomly if not set. This is the random seed for texture generation for model_version>=v2.0-20240919 or Turbo-v1.0-20250506. Using the same seed will produce identical textures. If you want a model with different textures, please use same model_seed and different texture_seed.
texture_alignment: A text value to determine the prioritization of texture alignment in the 3D model. The default value is original_image. All available values are:
original_image: Prioritizes visual fidelity to the source image. This option produces textures that closely resemble the original image but may result in minor 3D inconsistencies.geometry: Prioritizes 3D structural accuracy. This option ensures better alignment with the model’s geometry but may cause slight deviations from the original image appearance.
texture_quality: A text value to control the texture quality. Can be set to standard, detailed, or extreme. detailed provides high-resolution textures, resulting in more refined and realistic representation of intricate parts. extreme provides the highest texture resolution and visual fidelity. The default value is standard. Additional credits: standard 10, detailed 20, extreme 30.
Combination rules when texture_quality is detailed or extreme:
texture=false,pbr=false: Upscales the texture to 4K. PBR material will be removed. Only available forv3.0-20250812.texture=false,pbr=true: Generates PBR with the current texture.texture=true,pbr=false: Regenerates HD texture without PBR.texture=true,pbr=true: Regenerates HD texture with PBR.
WARNING
Setting texture_quality=standard with both texture=false and pbr=false is not allowed.
part_names: The text list of part names referred from Mesh segmentation, the default value will be all part names generated from segmentation.
compress: Specifies the compression type to apply to the texture. Available values are:
geometry: Applies geometry-based compression to optimize the output. By default we use meshopt compression
bake: A bool value. When set to true, bakes the model's textures, combining advanced material effects into the base textures. The default value is true.
Returns
task_id: The identifier for the successfully submitted task.