afiaka87 / ldm-autoedit

  • Public
  • 1.5K runs
  • T4

Input

string
Shift + Return to add a new line

(required) Text to use for the model's prediction.

Default: ""

file

(optional) an existing image you want to edit

string
Shift + Return to add a new line

(optional) Negate the model's prediction for this text from the model's prediction for the target text.

Default: ""

integer
(minimum: 0, maximum: 9)

Number between 0 and 9 representing the aesthetic rating. Will initialize the prompt CLIP embed with the respective aesthetic embed.

Default: 9

number
(minimum: 0, maximum: 1)

Weight of the aesthetic embedding in the average prompt embedding.

Default: 0.5

integer
(minimum: 1, maximum: 32)

Batch size.

Default: 1

integer

Target width

Default: 256

integer

Target height

Default: 256

integer
(minimum: 1, maximum: 30)

Number of iterations to run the model for.

Default: 10

number
(minimum: 0.1)

size of noise blur at the start of editing (larger = coarser changes)

Default: 5

number
(minimum: 0.1, maximum: 5)

size of noise blur at the end of editing (smaller = editing fine details)

Default: 0.1

number
(minimum: 0.05, maximum: 1)

how much of the image to replace at the start of editing (1 = inpaint the entire image)

Default: 0.6

number
(minimum: 0.1, maximum: 1)

how much of the image to replace at the end of editing

Default: 0.5

number
(minimum: -10, maximum: 100)

Controls how much the image should look like the prompt

Default: 5

integer
(minimum: -1)

(optional) Seed for the random number generator.

Default: -1

Output

outputoutputoutputoutputoutputoutputoutputoutput
Generated in

Run time and cost

This model runs on Nvidia T4 GPU hardware. We don't yet have enough runs of this model to provide performance information.

Readme

Model description

Intended use

Ethical considerations

Caveats and recommendations