You're looking at a specific version of this model. Jump to the model overview.

lucataco /sandbox:648c89f4

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
image
string
Reference image for avatar generation
audio
string
Audio file to drive the avatar animation
prompt
string
Text prompt describing the scene
negative_prompt
string
Vibrant colors, overexposure, static, blurred details, subtitles, style, artwork, painting, still image,Overall gray, worst quality, low quality, JPEG compression residue, ugly, mutilated, extra fingers,Poorly drawn hands, poorly drawn faces, deformed, disfigured, malformed limbs, fused fingers,Still image, cluttered background, three legs, crowded background, walking backwards
Negative prompt to avoid unwanted elements
auto_adjust_dimensions
boolean
True
Automatically adjust width and height based on input image aspect ratio
width
integer
512

Min: 256

Max: 2048

Width of output video (used only if auto_adjust_dimensions is False)
height
integer
512

Min: 256

Max: 2048

Height of output video (used only if auto_adjust_dimensions is False)
transformer_variant
None
rec_vec
Transformer model variant to use
gpu_memory_mode
None
model_cpu_offload
GPU memory optimization mode
guidance_scale
number
6

Min: 1

Max: 10

Guidance scale for generation
num_inference_steps
integer
50

Min: 1

Max: 100

Number of inference steps
text_guide_scale
number
3

Min: 1

Max: 10

Text guidance scale
audio_guide_scale
number
5

Min: 1

Max: 10

Audio guidance scale
motion_frame
integer
24

Min: 1

Max: 50

Motion frame parameter
fps
integer
24

Min: 1

Max: 60

Frames per second for output video
overlap_window_length
integer
5

Min: 1

Max: 20

Overlap window length for long video generation
teacache_threshold
number
0

Max: 1

TeaCache threshold for acceleration (0 to disable)
num_skip_start_steps
integer
5

Max: 100

Number of start steps to skip for TeaCache
seed
integer
Random seed for reproducibility

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'}