danila013 / ghibli-easycontrol

Ghiblify your image – ChatGPT-level quality, 10× faster and cheaper.

  • Public
  • 3.2K runs
  • L40S

Input

input_image
string
Shift + Return to add a new line

Prompt for the image generation. Include trigger words 'Ghibli Studio style, Charming hand-drawn anime-style illustration'

Default: "Ghibli Studio style, Charming hand-drawn anime-style illustration"

*file

Input image to apply Ghibli style to.

number
(minimum: 0, maximum: 2)

Weight for the Ghibli LoRA

Default: 1

integer
(minimum: 1, maximum: 100)

Number of inference steps

Default: 25

number
(minimum: 1, maximum: 10)

Guidance scale

Default: 3.5

integer

Seed for reproducibility. -1 for random.

Default: -1

Output

output
Generated in

This output was created using a different version of the model, danila013/ghibli-easycontrol:f74e8ded.

Run time and cost

This model costs approximately $0.024 to run on Replicate, or 41 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 25 seconds. The predict time for this model varies significantly based on the inputs.

Readme

This model doesn't have a readme.