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

daanelson /plug_and_play_image_translation:bc7ddf2d

Input

file

Image to edit (instead of generation prompt

integer

Number of time steps to invert the input image (if supplied)

Default: 999

string
Shift + Return to add a new line

Edit an image generated from this prompt (Input image is ignored if this is supplied

Default: ""

number

unconditional guidance scale. Note that a higher value encourages deviation from the source image (10 is the default for tranlsation from image 7.5 for text

Default: 10

number
(minimum: 0, maximum: 1)

Control the level of structure preservation. What timestep to stop Injecting the saved features into the translation diffusion process. (0 is first and 1 is final timestep meaning more preservation)

Default: 0.8

string
Shift + Return to add a new line

Text to Image prompts. A list of edit texts (separated by ;) an image will be output for each edit txt

Default: "a photo of a robot horse"

string
Shift + Return to add a new line

Control the level of deviation from the source image

Default: ""

number
(minimum: 0, maximum: 1)

Strength of the effect of the negative prompt (lower is stronger)

Default: 1

Output

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