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

voodoohop /flux-dance:930c4edd

Input

string
Shift + Return to add a new line

Style prefix to prepend to each prompt

Default: "angular, academic art, cubism, an abstract drawing by Svetoslav Roerich, abstract illusionism, concept art, angular, broken-stained-glass, concrete poetry, anton semono. black and white, granular, abstract, hand drawings,grainy, dmysticism, sacred symbology, blueprint"

string
Shift + Return to add a new line

Narrative prompts, one per line. Each line defines a prompt for a certain time in the sequence.

Default: "Silhouettes of valleys \nSilhouettes of hills"

file

Audio file to drive interpolation (optional)

integer

Width of the generated image

Default: 512

integer

Height of the generated image

Default: 512

integer

Random seed

Default: 42

integer

Number of interpolation steps between seeds (ignored if audio_file is provided)

Default: 4

number

Controls how much the audio amplitude affects the image variation (0-1)

Default: 0.3

number

Smoothing factor for audio (0-1, higher = more smoothing)

Default: 0.8

string

Type of audio loudness measurement to use

Default: "peak"

integer

Frames per second for the video

Default: 10

string

Format of the output image

Default: "png"

boolean

Interpolate between prompts instead of switching between them

Default: true

string

Which model to use for generation

Default: "flux"

number
(minimum: 1, maximum: 20)

Guidance scale for Stable Diffusion model (higher = more adherence to prompt, ignored for FLUX)

Default: 7.5

Output

No output yet! Press "Submit" to start a prediction.