Model input

prompt

Input prompt

negative_prompt

Input Negative Prompt

image

Click to select a file to input

Input image for img2img or inpaint mode

mask

Click to select a file to input

Input mask for inpaint mode. Black areas will be preserved, white areas will be inpainted.

width

Width of output image

height

Height of output image

scheduler

num_inference_steps

Number of denoising steps (minimum: 1; maximum: 500)

guidance_scale

Scale for classifier-free guidance (minimum: 1; maximum: 50)

prompt_strength

Prompt strength when using img2img / inpaint. 1.0 corresponds to full destruction of information in image

seed

Random seed. Leave blank to randomize the seed

refine

Which refine style to use

high_noise_frac

For expert_ensemble_refiner, the fraction of noise to use

refine_steps

For base_image_refiner, the number of steps to refine, defaults to num_inference_steps

lora_scale

LoRA additive scale. Only applicable on trained models.

Text-to-image

logo-swift

Create logos with AI in just one minute

0.9k

Model result

Download