jerray / realistic-vision-v5

  • Public
  • 70 runs

Run jerray/realistic-vision-v5 with an API

Use one of our client libraries to get started quickly. Clicking on a library will take you to the Playground tab where you can tweak different inputs, see the results, and copy the corresponding code to use in your own project.

Input schema

The fields you can use to run this model with an API. If you don't give a value for a field its default value will be used.

Field Type Default value Description
face_image
string
Input face image
control_image
string
Control image
prompt
string
a photo of an astronaut riding a horse on mars
Input prompt
negative_prompt
string
Specify things to not see in the output
clip_skip
integer
1

Min: 1

None
width
integer (enum)
512

Options:

128, 256, 384, 448, 512, 576, 640, 704, 768, 832, 896, 960, 1024

Width of output image. Maximum size is 1024x768 or 768x1024 because of memory limits
height
integer (enum)
512

Options:

128, 256, 384, 448, 512, 576, 640, 704, 768, 832, 896, 960, 1024

Height of output image. Maximum size is 1024x768 or 768x1024 because of memory limits
num_outputs
integer
1

Min: 1

Max: 4

Number of images to output.
num_inference_steps
integer
30

Min: 1

Max: 500

Number of denoising steps
guidance_scale
number
7.5

Min: 1

Max: 20

Scale for classifier-free guidance
scheduler
string (enum)
DPMSolverMultistep

Options:

PNDM, KLMS, DDIM, K_EULER, K_EULER_ANCESTRAL, DPMSolverMultistep, DPM++ SDE Karras, DPM++ 2M Karras

Choose a scheduler.
canny_low_threshold
integer
100

Min: 1

Max: 255

Canny line detection low threshold
canny_high_threshold
integer
200

Min: 1

Max: 255

Canny line detection high threshold
controlnet_conditioning_scale
number
1

Max: 2

Control Weight
control_guidance_start
number
0

Max: 1

The percentage of total steps at which the controlnet starts applying
control_guidance_end
number
1

Max: 1

The percentage of total steps at which the controlnet stops applying
resize_mode
string (enum)
fill

Options:

fill, crop, cover

fill - The image is resized to fill the given dimension. cover - The image keeps its aspect ratio and fills the given dimension. The image will be clipped to fit. crop - The image keeps its aspect ratio and scales to the target size.
seed
integer
Random seed. Leave blank to randomize the seed
lora_model
string (enum)

Options:

adventurers_v1, add_detail, thick_impasto_painting

An enumeration.
cross_attention_scale
number
0.8

Max: 1

A scale value of 0 is the same as not using your LoRA weights and you’re only using the base model weights, and a scale value of 1 means you’re only using the fully finetuned LoRA weights.
restore_face_upscale
integer
1

Min: 1

Max: 4

Restore face upscaling
restore_face_upsample
boolean
True
Restore face upsampling
restore_face_background_enhance
boolean
True
Restore face background enhance
codeformer_fidelity
number
0.7

Max: 1

Codeformer fidelity

Output schema

The shape of the response you’ll get when you run this model with an API.

Schema
{
  "type": "array",
  "items": {
    "type": "string",
    "format": "uri"
  },
  "title": "Output"
}