You're looking at a specific version of this model. Jump to the model overview.
voodoohop /flux-dance:3a2feefc
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 |
|---|---|---|---|
| style_prefix |
string
|
A painting by paul klee, intricate details of
|
Style prefix to prepend to each prompt
|
| prompt |
string
|
A beautiful landscape
|
Prompt for generated image
|
| narrative |
string
|
A painting of a moth
A painting of a killer dragonfly
Two fishes talking to eachother in deep sea
|
Narrative prompts, one per line. Each line defines a prompt for a certain time in the sequence.
|
| width |
integer
|
1024
|
Width of the generated image
|
| height |
integer
|
1024
|
Height of the generated image
|
| seed |
integer
|
42
|
Random seed for interpolation (seed+1 will be used as the second seed)
|
| interpolation_steps |
integer
|
4
|
Number of interpolation steps between seeds (ignored if audio_file is provided)
|
| variation_strength |
number
|
0.3
|
Controls the amount of variation between frames (0-1)
|
| audio_file |
string
|
Audio file to drive interpolation (optional)
|
|
| audio_smoothing |
number
|
0.8
|
Smoothing factor for audio (0-1, higher = more smoothing)
|
| audio_loudness_type |
string
(enum)
|
peak
Options: peak, rms |
Type of audio loudness measurement to use
|
| create_video |
boolean
|
True
|
Create a video from the interpolated images
|
| fps |
integer
|
10
|
Frames per second for the video
|
| output_format |
string
(enum)
|
png
Options: webp, jpg, png |
Format of the output image
|
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'}