zf-kbot/md-me-qwen-prism
Run zf-kbot/md-me-qwen-prism 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 |
|---|---|---|---|
| task |
None
|
image_prompt_enhance
|
Task type.
|
| prompt |
string
|
|
User prompt or text.
|
| custom_task_prompt |
string
|
|
Optional system prompt override for the selected task.
|
| input_image |
string
|
Input image for image prompt enhancement or image-to-prompt tasks.
|
|
| language |
None
|
auto
|
Output language.
|
| max_tokens |
integer
|
768
Min: 128 Max: 2048 |
Maximum output tokens.
|
| temperature |
number
|
0.4
Max: 1.2 |
Sampling temperature.
|
| top_p |
number
|
0.9
Min: 0.1 Max: 1 |
Top-p sampling.
|
| enable_mtp |
boolean
|
True
|
Enable native MTP speculative decoding. Server restarts if changed.
|
| spec_draft_n_max |
integer
|
1
Min: 1 Max: 8 |
Maximum MTP draft tokens.
|
| spec_draft_n_min |
integer
|
1
Min: 1 Max: 8 |
Minimum MTP draft tokens.
|
| enable_reasoning |
boolean
|
False
|
Enable Qwen thinking/reasoning mode.
|
| include_reason |
boolean
|
False
|
Compatibility flag. Output remains plain text.
|
{
"type": "object",
"title": "Input",
"properties": {
"task": {
"enum": [
"image_prompt_enhance",
"qwen_image_prompt_enhance",
"image_to_prompt",
"ig",
"text_optimize",
"text_nsfw_detect"
],
"type": "string",
"title": "task",
"description": "Task type.",
"default": "image_prompt_enhance",
"x-order": 0
},
"top_p": {
"type": "number",
"title": "Top P",
"default": 0.9,
"maximum": 1,
"minimum": 0.1,
"x-order": 7,
"description": "Top-p sampling."
},
"prompt": {
"type": "string",
"title": "Prompt",
"default": "",
"x-order": 1,
"description": "User prompt or text."
},
"language": {
"enum": [
"en",
"zh",
"auto"
],
"type": "string",
"title": "language",
"description": "Output language.",
"default": "auto",
"x-order": 4
},
"enable_mtp": {
"type": "boolean",
"title": "Enable Mtp",
"default": true,
"x-order": 8,
"description": "Enable native MTP speculative decoding. Server restarts if changed."
},
"max_tokens": {
"type": "integer",
"title": "Max Tokens",
"default": 768,
"maximum": 2048,
"minimum": 128,
"x-order": 5,
"description": "Maximum output tokens."
},
"input_image": {
"type": "string",
"title": "Input Image",
"format": "uri",
"x-order": 3,
"nullable": true,
"description": "Input image for image prompt enhancement or image-to-prompt tasks."
},
"temperature": {
"type": "number",
"title": "Temperature",
"default": 0.4,
"maximum": 1.2,
"minimum": 0,
"x-order": 6,
"description": "Sampling temperature."
},
"include_reason": {
"type": "boolean",
"title": "Include Reason",
"default": false,
"x-order": 12,
"description": "Compatibility flag. Output remains plain text."
},
"enable_reasoning": {
"type": "boolean",
"title": "Enable Reasoning",
"default": false,
"x-order": 11,
"description": "Enable Qwen thinking/reasoning mode."
},
"spec_draft_n_max": {
"type": "integer",
"title": "Spec Draft N Max",
"default": 1,
"maximum": 8,
"minimum": 1,
"x-order": 9,
"description": "Maximum MTP draft tokens."
},
"spec_draft_n_min": {
"type": "integer",
"title": "Spec Draft N Min",
"default": 1,
"maximum": 8,
"minimum": 1,
"x-order": 10,
"description": "Minimum MTP draft tokens."
},
"custom_task_prompt": {
"type": "string",
"title": "Custom Task Prompt",
"default": "",
"x-order": 2,
"description": "Optional system prompt override for the selected task."
}
}
}
Output schema
The shape of the response you’ll get when you run this model with an API.
{
"type": "string",
"title": "Output"
}