zf-kbot/md-me-video-edit-1
Public
19
runs
Run zf-kbot/md-me-video-edit-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 |
|---|---|---|---|
| video |
string
|
Input video file
|
|
| mode |
None
|
hd
|
Editing mode
|
| prompt |
string
|
Optional prompt. Leave empty to use the README/run_script default prompt for the selected mode.
|
|
| duration_seconds |
number
|
4
|
Seconds of the input video to process. The model internally aligns this to 8k+1 frames.
|
| resolution |
None
|
720p
|
Output resolution preset. Preserves the input aspect ratio and aligns to LTX requirements.
|
| fps |
number
|
24
|
Output FPS
|
| seed |
integer
|
-1
|
Seed. Use -1 to use the README/script default seed for the selected mode.
|
| lora_strength |
number
|
1
|
IC-LoRA strength
|
| two_stage |
boolean
|
False
|
Enable two-stage refinement. Default is off, matching the README single-stage flow.
|
| sigma_profile |
None
|
workflow
|
Sigma schedule profile
|
| streaming_prefetch_count |
integer
|
0
|
Layer streaming prefetch count. Use 0 to disable streaming.
|
| disable_white_mask |
boolean
|
False
|
Disable the default full-white conditioning mask
|
| video_conditioning_strength |
number
|
1
|
Reference video conditioning strength
|
{
"type": "object",
"title": "Input",
"required": [
"video"
],
"properties": {
"fps": {
"type": "number",
"title": "Fps",
"default": 24,
"x-order": 5,
"description": "Output FPS"
},
"mode": {
"enum": [
"restoration",
"hd",
"watermark_rm",
"subtitle_rm"
],
"type": "string",
"title": "mode",
"description": "Editing mode",
"default": "hd",
"x-order": 1
},
"seed": {
"type": "integer",
"title": "Seed",
"default": -1,
"x-order": 6,
"description": "Seed. Use -1 to use the README/script default seed for the selected mode."
},
"video": {
"type": "string",
"title": "Video",
"format": "uri",
"x-order": 0,
"description": "Input video file"
},
"prompt": {
"type": "string",
"title": "Prompt",
"x-order": 2,
"nullable": true,
"description": "Optional prompt. Leave empty to use the README/run_script default prompt for the selected mode."
},
"two_stage": {
"type": "boolean",
"title": "Two Stage",
"default": false,
"x-order": 8,
"description": "Enable two-stage refinement. Default is off, matching the README single-stage flow."
},
"resolution": {
"enum": [
"640p",
"720p",
"1080p"
],
"type": "string",
"title": "resolution",
"description": "Output resolution preset. Preserves the input aspect ratio and aligns to LTX requirements.",
"default": "720p",
"x-order": 4
},
"lora_strength": {
"type": "number",
"title": "Lora Strength",
"default": 1,
"x-order": 7,
"description": "IC-LoRA strength"
},
"sigma_profile": {
"enum": [
"workflow",
"distilled"
],
"type": "string",
"title": "sigma_profile",
"description": "Sigma schedule profile",
"default": "workflow",
"x-order": 9
},
"duration_seconds": {
"type": "number",
"title": "Duration Seconds",
"default": 4,
"x-order": 3,
"description": "Seconds of the input video to process. The model internally aligns this to 8k+1 frames."
},
"disable_white_mask": {
"type": "boolean",
"title": "Disable White Mask",
"default": false,
"x-order": 11,
"description": "Disable the default full-white conditioning mask"
},
"streaming_prefetch_count": {
"type": "integer",
"title": "Streaming Prefetch Count",
"default": 0,
"x-order": 10,
"description": "Layer streaming prefetch count. Use 0 to disable streaming."
},
"video_conditioning_strength": {
"type": "number",
"title": "Video Conditioning Strength",
"default": 1,
"x-order": 12,
"description": "Reference video conditioning strength"
}
}
}
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{
"type": "string",
"title": "Output",
"format": "uri"
}