lucataco/omnigen2

OmniGen2: a powerful and efficient unified multimodal model

Public
1.5K runs

Run lucataco/omnigen2 with an API

Input schema

seedinteger

Random seed. Set to -1 for random seed

Default
-1
imageuri

Input image to edit

widthinteger

Width of output image

Default
1024
Minimum
256
Maximum
1024
heightinteger

Height of output image

Default
1024
Minimum
256
Maximum
1024
promptstring

Text prompt describing the desired image edit

Default
"Make the person smile"
image_2uri

Optional second input image for multi-image operations

image_3uri

Optional third input image for multi-image operations

schedulerstring

Scheduler to use

Default
"euler"
max_pixelsinteger

Maximum number of pixels in output

Default
1048576
Minimum
65536
Maximum
2359296
cfg_range_endnumber

CFG range end

Default
1
Maximum
1
cfg_range_startnumber

CFG range start

Maximum
1
negative_promptstring

Negative prompt to guide what should not be in the image

Default
"(((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"
num_inference_stepsinteger

Number of denoising steps

Default
50
Minimum
20
Maximum
100
text_guidance_scalenumber

Guidance scale for text prompt

Default
5
Minimum
1
Maximum
8
image_guidance_scalenumber

Guidance scale for input image. Higher values increase consistency with input image

Default
2
Minimum
1
Maximum
3
max_input_image_side_lengthinteger

Maximum input image side length

Default
2048
Minimum
256
Maximum
2048

Output schema

Type
uri