You're looking at a specific version of this model. Jump to the model overview.
zsxkib /mimic-motion:2e7f79ed
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 |
|---|---|---|---|
| motion_video |
string
|
Reference video file containing the motion to be mimicked
|
|
| appearance_image |
string
|
Reference image file for the appearance of the generated video
|
|
| resolution |
integer
|
576
Min: 64 Max: 1024 |
Height of the output video in pixels. Width is automatically calculated.
|
| chunk_size |
integer
|
16
Min: 2 |
Number of frames to generate in each processing chunk
|
| frames_overlap |
integer
|
6
|
Number of overlapping frames between chunks for smoother transitions
|
| denoising_steps |
integer
|
25
Min: 1 Max: 100 |
Number of denoising steps in the diffusion process. More steps can improve quality but increase processing time.
|
| noise_strength |
number
|
0
Max: 1 |
Strength of noise augmentation. Higher values add more variation but may reduce coherence with the reference.
|
| guidance_scale |
number
|
2
Min: 0.1 Max: 10 |
Strength of guidance towards the reference. Higher values adhere more closely to the reference but may reduce creativity.
|
| sample_stride |
integer
|
2
Min: 1 |
Interval for sampling frames from the reference video. Higher values skip more frames.
|
| output_frames_per_second |
integer
|
15
Min: 1 Max: 60 |
Frames per second of the output video. Affects playback speed.
|
| seed |
integer
|
Random seed. Leave blank to randomize the seed
|
|
| use_fp16 |
boolean
|
True
|
Use half-precision floating point (float16). Faster but slightly less accurate than float32.
|
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'}