kelvincai522 / photomaker-v1-lightning

Photomaker V1 optimized with Lightning 8steps

  • Public
  • 563 runs
Iterate in playground

Input

file
Preview
input_image

The input image, for example a photo of your face.

Default: "https://replicate.delivery/pbxt/KFRc9kyW6lLALePRbphzLaZnMyqjYUH8Tles73OvOVfXUcj8/yangmi_1.jpg"

file

Additional input image (optional)

file

Additional input image (optional)

file

Additional input image (optional)

string
Shift + Return to add a new line

Prompt. Example: 'a photo of a man/woman img'. The phrase 'img' is the trigger word.

Default: "score_9 score_8_up score_7_up anime img 1girl masterpiece very_aesthetic hi_res absurd_res superabsurd_res"

string

Style template. The style template will add a style-specific prompt and negative prompt to the user's prompt.

Default: "(No style)"

string
Shift + Return to add a new line

Negative Prompt. The negative prompt should NOT contain the trigger word.

Default: "score_1 score_2 score_3 worst_quality bad_quality jpeg_artifacts source_cartoon 3d censor+ monochrome blurry lowres watermark text low_res oversaturated crappy_art low_quality blurry bad_anatomy extra_digits fewer_digits simple_background very_displeasing watermark signature"

integer
(minimum: 1, maximum: 100)

Number of sample steps

Default: 16

number
(minimum: 15, maximum: 50)

Style strength (%)

Default: 15

integer
(minimum: 1, maximum: 4)

Number of output images

Default: 1

number
(minimum: 1, maximum: 10)

Guidance scale. A guidance scale of 1 corresponds to doing no classifier free guidance.

Default: 5

integer
(minimum: 0, maximum: 2147483647)

Seed. Leave blank to use a random number

Output

output
Generated in

This output was created using a different version of the model, kelvincai522/photomaker-v1-lightning:0ccd19c5.

Run time and cost

This model costs approximately $0.18 to run on Replicate, or 5 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia L40S GPU hardware. Predictions typically complete within 4 minutes.

Readme

Inference optimized with Lightning 8steps, Stable Fast, and dynamic quantized int8