You're looking at a specific version of this model. Jump to the model overview.

chenxwh /omnigen:af66691a

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
prompt
string
a photo of an astronaut riding a horse on mars
Input prompt. For multi-modal to image generation with one or more input images, the placeholder in the prompt should be in the format of <img><|image_*|></img> (for the first image, the placeholder is <|image_1|>, for the second image, the the placeholder is <|image_2|>). Refer to examples for more details
img1
string
Input image 1. Optional
img2
string
Input image 2. Optional
img3
string
Input image 3. Optional
width
integer
1024

Min: 128

Max: 2048

Width of the output image
height
integer
1024

Min: 128

Max: 2048

Height of the output image
inference_steps
integer
50

Min: 1

Max: 100

Number of denoising steps
guidance_scale
number
2.5

Min: 1

Max: 5

Classifier-free guidance scale for text prompt
img_guidance_scale
number
1.6

Min: 1

Max: 2

Classifier-free guidance scale for images
seed
integer
Random seed. Leave blank to randomize the seed
max_input_image_size
integer
1024

Min: 128

Max: 2048

maximum input image size
separate_cfg_infer
boolean
True
Whether to use separate inference process for different guidance. This will reduce the memory cost.
offload_model
boolean
False
Offload model to CPU, which will significantly reduce the memory cost but slow down the generation speed. You can cancel separate_cfg_infer and set offload_model=True. If both separate_cfg_infer and offload_model are True, further reduce the memory, but slowest generation
use_input_image_size_as_output
boolean
False
Automatically adjust the output image size to be same as input image size. For editing and controlnet task, it can make sure the output image has the same size as input image leading to better performance

Output schema

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

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