krunalmangroliya/omnigen2

Public
3 runs

Run krunalmangroliya/omnigen2 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
instruction
string
Instruction for the model
image_input_1
string
First input image
image_input_2
string
Second input image
image_input_3
string
Third input image
width_input
integer
1024
Width of the output image
height_input
integer
1024
Height of the output image
scheduler
None
euler
Scheduler to use
num_inference_steps
integer
50
Number of inference steps
negative_prompt
string
(((deformed))), blurry, over saturation, bad anatomy, disfigured, poorly drawn face, mutation, mutated, (extra_limb), (ugly), (poorly drawn hands), fused fingers, messy drawing, broken legs censor, censored, censor_bar
Negative prompt
guidance_scale_input
number
5
Text guidance scale
img_guidance_scale_input
number
2
Image guidance scale
cfg_range_start
number
0
CFG range start
cfg_range_end
number
1
CFG range end
num_images_per_prompt
integer
1
Number of images per prompt
max_input_image_side_length
integer
2048
Maximum input image side length
max_pixels
integer
1048576
Maximum pixels
seed_input
integer
-1
Seed for random number generation

Output schema

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

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