
zylim0702/yun-3d-2.1
Run zylim0702/yun-3d-2.1 with an API
Use one of our client libraries to get started quickly. Clicking on a library will take you to the Playground tab where you can tweak different inputs, see the results, and copy the corresponding code to use in your own project.
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 |
---|---|---|---|
image |
string
|
Input image for 3D generation
|
|
mode |
None
|
textured
|
Generation mode: 'shape_only' for 3D shape only, 'textured' for shape + texture
|
num_inference_steps |
integer
|
30
Min: 1 Max: 100 |
Number of denoising steps for shape generation
|
guidance_scale |
number
|
7.5
Min: 1 Max: 20 |
Guidance scale for shape generation
|
seed |
integer
|
1234
Max: 2147483647 |
Random seed for reproducible generation
|
octree_resolution |
integer
|
256
Min: 16 Max: 512 |
Octree resolution for shape generation
|
num_chunks |
integer
|
200000
Min: 1000 Max: 5000000 |
Number of chunks for processing
|
remove_background |
boolean
|
True
|
Automatically remove background from input image
|
max_num_view |
integer
|
8
Min: 6 Max: 9 |
Maximum number of views for texture generation
|
texture_resolution |
None
|
768
|
Resolution for texture generation
|
simplify_mesh |
boolean
|
False
|
Simplify the generated mesh to reduce face count
|
target_face_count |
integer
|
10000
Min: 100 Max: 1000000 |
Target number of faces after simplification
|
output_format |
None
|
glb
|
Output file format
|
{
"type": "object",
"title": "Input",
"required": [
"image"
],
"properties": {
"mode": {
"enum": [
"shape_only",
"textured"
],
"type": "string",
"title": "mode",
"description": "Generation mode: 'shape_only' for 3D shape only, 'textured' for shape + texture",
"default": "textured",
"x-order": 1
},
"seed": {
"type": "integer",
"title": "Seed",
"default": 1234,
"maximum": 2147483647,
"minimum": 0,
"x-order": 4,
"description": "Random seed for reproducible generation"
},
"image": {
"type": "string",
"title": "Image",
"format": "uri",
"x-order": 0,
"description": "Input image for 3D generation"
},
"num_chunks": {
"type": "integer",
"title": "Num Chunks",
"default": 200000,
"maximum": 5000000,
"minimum": 1000,
"x-order": 6,
"description": "Number of chunks for processing"
},
"max_num_view": {
"type": "integer",
"title": "Max Num View",
"default": 8,
"maximum": 9,
"minimum": 6,
"x-order": 8,
"description": "Maximum number of views for texture generation"
},
"output_format": {
"enum": [
"glb",
"obj",
"ply",
"stl"
],
"type": "string",
"title": "output_format",
"description": "Output file format",
"default": "glb",
"x-order": 12
},
"simplify_mesh": {
"type": "boolean",
"title": "Simplify Mesh",
"default": false,
"x-order": 10,
"description": "Simplify the generated mesh to reduce face count"
},
"guidance_scale": {
"type": "number",
"title": "Guidance Scale",
"default": 7.5,
"maximum": 20,
"minimum": 1,
"x-order": 3,
"description": "Guidance scale for shape generation"
},
"octree_resolution": {
"type": "integer",
"title": "Octree Resolution",
"default": 256,
"maximum": 512,
"minimum": 16,
"x-order": 5,
"description": "Octree resolution for shape generation"
},
"remove_background": {
"type": "boolean",
"title": "Remove Background",
"default": true,
"x-order": 7,
"description": "Automatically remove background from input image"
},
"target_face_count": {
"type": "integer",
"title": "Target Face Count",
"default": 10000,
"maximum": 1000000,
"minimum": 100,
"x-order": 11,
"description": "Target number of faces after simplification"
},
"texture_resolution": {
"enum": [
512,
768
],
"type": "integer",
"title": "texture_resolution",
"description": "Resolution for texture generation",
"default": 768,
"x-order": 9
},
"num_inference_steps": {
"type": "integer",
"title": "Num Inference Steps",
"default": 30,
"maximum": 100,
"minimum": 1,
"x-order": 2,
"description": "Number of denoising steps for shape generation"
}
}
}
Output schema
The shape of the response you’ll get when you run this model with an API.
{
"title": "Output"
}