You're looking at a specific version of this model. Jump to the model overview.
enhance-replicate /flix1.4:9003aff7
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
|
Prompt for video generation, i.e. A formidable Roman warrior in ornate bronze armor strides through the grand Colosseum at dusk, torches flickering along the stone walls as the crowd roars, his crimson cape billowing with each step, portrayed in epic, cinematic grandeur.
|
|
| negative_prompt |
string
|
Bright tones, overexposed, static, blurred details, subtitles, style, works, paintings, images, static, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, misshapen limbs, fused fingers, still picture, messy background, three legs, many people in the background, walking backwards
|
Negative prompt
|
| height |
integer
|
480
|
None
|
| width |
integer
|
832
|
None
|
| num_frames |
integer
|
32
|
None
|
| num_inference_steps |
integer
|
15
|
None
|
| guidance_scale |
number
|
5
|
None
|
| fps |
integer
|
8
|
None
|
| ken_burns_effect |
None
|
none
|
Ken Burns effect to apply
|
| target_duration |
number
|
4
Min: 1 Max: 30 |
Target video duration in seconds
|
| enable_upscaling |
boolean
|
True
|
Enable GFPGAN upscaling for higher quality output
|
| upscaling_optimization |
None
|
balanced
|
Upscaling optimization level for speed vs quality trade-off
|
| lora_weight |
number
|
1
Max: 2 |
LoRA adapter weight (0.0 to 2.0)
|
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{'format': 'uri', 'title': 'Output', 'type': 'string'}