fofr
/
illusions
Create illusions with img2img and masking support
- Public
- 48.4K runs
-
L40S
- GitHub
Run fofr/illusions with an API
Input schema
seedinteger
imageuri
Optional img2img
widthinteger
- Default
- 768
heightinteger
- Default
- 768
promptstring
- Default
- "a painting of a 19th century town"
mask_imageuri
Optional mask for inpainting
num_outputsinteger
Number of outputs
- Default
- 1
- Minimum
- 1
- Maximum
- 4
control_imageuri
Control image
controlnet_endnumber
When controlnet conditioning ends
- Default
- 1
- Maximum
- 1
guidance_scalenumber
Scale for classifier-free guidance
- Default
- 7.5
- Minimum
- 0.1
- Maximum
- 30
negative_promptstring
The negative prompt to guide image generation.
- Default
- "ugly, disfigured, low quality, blurry, nsfw"
prompt_strengthnumber
Prompt strength when using img2img / inpaint. 1.0 corresponds to full destruction of information in image
- Default
- 0.8
- Maximum
- 1
sizing_strategystring
Decide how to resize images – use width/height, resize based on input image or control image
- Default
- "width/height"
controlnet_startnumber
When controlnet conditioning starts
- Maximum
- 1
num_inference_stepsinteger
Number of diffusion steps
- Default
- 40
- Minimum
- 20
- Maximum
- 100
controlnet_conditioning_scalenumber
How strong the controlnet conditioning is
- Default
- 0.75
- Maximum
- 4
Output schema
- Type
- uri[]