okgodoit-repos/mindprint-zimage-base
Mindprint DiT seamless-tiling — Z-Image-Base (6B, full CFG, 32 steps) via toroidal-RoPE + circular-VAE. Tier-1 quality/owned-pattern lane.
Run okgodoit-repos/mindprint-zimage-base 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 |
|---|---|---|---|
| prompt |
string
|
seamless repeating art deco geometric pattern, gold and navy, textile print
|
Input prompt
|
| negative_prompt |
string
|
|
Things to avoid (only used if the model supports CFG)
|
| width |
None
|
1024
|
Output width (multiple of 16).
|
| height |
None
|
1024
|
Output height (multiple of 16).
|
| num_inference_steps |
integer
|
0
Max: 40 |
Denoising steps (0 = model default).
|
| guidance_scale |
number
|
-1
Min: -1 Max: 8 |
CFG scale (<0 = model default).
|
| seed |
integer
|
-1
|
Random seed. Use -1 (default) to randomize.
|
| tiling |
None
|
enable
|
Master tiling switch.
|
| tile_x |
boolean
|
True
|
Wrap horizontally (left<->right).
|
| tile_y |
boolean
|
True
|
Wrap vertically (top<->bottom).
|
| rope_mode |
None
|
default
|
Tiling enforcement. 'all0' = fully periodic (forces a wrapping all-over "
"pattern regardless of prompt — recommended). 'high' = preserves coarse "
"composition (may seam on scene-y prompts). 'default' uses the baked default.
|
| num_outputs |
integer
|
1
Min: 1 Max: 4 |
Number of images to generate
|
| pattern_collection_id |
integer
|
-1
|
Pattern collection ID
|
| metadata |
string
|
|
Opaque metadata passed through to the webhook
|
{
"type": "object",
"title": "Input",
"properties": {
"seed": {
"type": "integer",
"title": "Seed",
"default": -1,
"x-order": 6,
"description": "Random seed. Use -1 (default) to randomize."
},
"width": {
"enum": [
512,
768,
1024,
1152,
1280,
1536
],
"type": "integer",
"title": "width",
"description": "Output width (multiple of 16).",
"default": 1024,
"x-order": 2
},
"height": {
"enum": [
512,
768,
1024,
1152,
1280,
1536
],
"type": "integer",
"title": "height",
"description": "Output height (multiple of 16).",
"default": 1024,
"x-order": 3
},
"prompt": {
"type": "string",
"title": "Prompt",
"default": "seamless repeating art deco geometric pattern, gold and navy, textile print",
"x-order": 0,
"description": "Input prompt"
},
"tile_x": {
"type": "boolean",
"title": "Tile X",
"default": true,
"x-order": 8,
"description": "Wrap horizontally (left<->right)."
},
"tile_y": {
"type": "boolean",
"title": "Tile Y",
"default": true,
"x-order": 9,
"description": "Wrap vertically (top<->bottom)."
},
"tiling": {
"enum": [
"enable",
"disable"
],
"type": "string",
"title": "tiling",
"description": "Master tiling switch.",
"default": "enable",
"x-order": 7
},
"metadata": {
"type": "string",
"title": "Metadata",
"default": "",
"x-order": 13,
"description": "Opaque metadata passed through to the webhook"
},
"rope_mode": {
"enum": [
"default",
"all0",
"high"
],
"type": "string",
"title": "rope_mode",
"description": "Tiling enforcement. 'all0' = fully periodic (forces a wrapping all-over \"\n \"pattern regardless of prompt \u2014 recommended). 'high' = preserves coarse \"\n \"composition (may seam on scene-y prompts). 'default' uses the baked default.",
"default": "default",
"x-order": 10
},
"num_outputs": {
"type": "integer",
"title": "Num Outputs",
"default": 1,
"maximum": 4,
"minimum": 1,
"x-order": 11,
"description": "Number of images to generate"
},
"guidance_scale": {
"type": "number",
"title": "Guidance Scale",
"default": -1,
"maximum": 8,
"minimum": -1,
"x-order": 5,
"description": "CFG scale (<0 = model default)."
},
"negative_prompt": {
"type": "string",
"title": "Negative Prompt",
"default": "",
"x-order": 1,
"description": "Things to avoid (only used if the model supports CFG)"
},
"num_inference_steps": {
"type": "integer",
"title": "Num Inference Steps",
"default": 0,
"maximum": 40,
"minimum": 0,
"x-order": 4,
"description": "Denoising steps (0 = model default)."
},
"pattern_collection_id": {
"type": "integer",
"title": "Pattern Collection Id",
"default": -1,
"x-order": 12,
"description": "Pattern collection ID"
}
}
}
Output schema
The shape of the response you’ll get when you run this model with an API.
{
"type": "array",
"items": {
"type": "string",
"format": "uri"
},
"title": "Output"
}