okaris
/
omni-zero
Omni-Zero: A diffusion pipeline for zero-shot stylized portrait creation.
Run okaris/omni-zero with an API
Input schema
seedinteger
Random seed for the model
- Default
- 42
imageuri
Base image for the model
modelstring
Model to use for the prediction
- Default
- "omni-zero"
promptstring
Prompt for the model
- Default
- "A person"
depth_imageuri
Depth image for the model
style_imageuri
Style image for the model
depth_strengthnumber
Depth image strength for the model, if not supplied the composition image will be used for depth
- Default
- 0.5
- Maximum
- 1
guidance_scalenumber
Guidance scale for the model
- Default
- 3
- Maximum
- 14
identity_imageuri
Identity image for the model
image_strengthnumber
Base image strength for the model
- Default
- 0.15
- Maximum
- 1
style_strengthnumber
Style image strength for the model
- Default
- 1
- Maximum
- 1
negative_promptstring
Negative prompt for the model
- Default
- "blurry, out of focus"
number_of_stepsinteger
Number of steps for the model
- Default
- 10
- Minimum
- 1
- Maximum
- 50
number_of_imagesinteger
Number of images to generate
- Default
- 1
- Minimum
- 1
- Maximum
- 4
composition_imageuri
Composition image for the model
identity_strengthnumber
Identity image strength for the model
- Default
- 1
- Maximum
- 1
composition_strengthnumber
Composition image strength for the model
- Default
- 1
- Maximum
- 1
Output schema
- Type
- uri[]