You're looking at a specific version of this model. Jump to the model overview.
enhance-replicate /flix2.2.14t2v:3d2b03f0
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
|
Text prompt for video generation
|
|
| negative_prompt |
string
|
色调艳丽，过曝，静态，细节模糊不清，字幕，风格，作品，画作，画面，静止，整体发灰，最差质量，低质量，JPEG压缩残留，丑陋的，残缺的，多余的手指，画得不好的手部，画得不好的脸部，畸形的，毁容的，形态畸形的肢体，手指融合，静止不动的画面，杂乱的背景，三条腿，背景人很多，倒着走
|
Negative prompt to avoid certain elements
|
| height |
integer
|
480
Min: 256 Max: 1024 |
Height of the video
|
| width |
integer
|
832
Min: 256 Max: 1024 |
Width of the video
|
| num_frames |
integer
|
25
Min: 16 Max: 200 |
Number of frames to generate
|
| guidance_scale |
number
|
4
Min: 1 Max: 20 |
Guidance scale for generation
|
| guidance_scale_2 |
number
|
3
Min: 1 Max: 20 |
Second guidance scale
|
| num_inference_steps |
integer
|
10
Min: 10 Max: 100 |
Number of inference steps
|
| fps |
integer
|
8
Min: 8 Max: 30 |
Frames per second for output video
|
| seed |
integer
|
Random seed for reproducibility
|
|
| lora_weight |
number
|
1
Max: 1 |
LoRA weight strength (0.0 to 1.0, 0.0 = no LoRA, 1.0 = full LoRA)
|
Output schema
The shape of the response you’ll get when you run this model with an API.
{'format': 'uri', 'title': 'Output', 'type': 'string'}