Wrapped RubyAI

Input

prompt

Your text prompt.

negative

(optional) Negate the model's prediction for this text from the model's prediction for the target text.

init_image

Click to select a file to input

(optional) Initial image to use for the model's prediction. If provided alongside a mask, the image will be inpainted instead.

mask

Click to select a file to input

a mask image for inpainting an init_image. white pixels = keep, black pixels = discard. resized to width = image width/8, height = image height/8

guidance_scale

Classifier-free guidance scale. Higher values will result in more guidance toward caption, with diminishing returns. Try values between 1.0 and 40.0. In general, going above 5.0 will introduce some artifacting. (minimum: -20; maximum: 100)

steps

Number of diffusion steps to run. Due to PLMS sampling, using more than 100 steps is unnecessary and may simply produce the exact same output. (minimum: 15; maximum: 250)

batch_size

Batch size. (higher = slower) (minimum: 1; maximum: 16)

width

Target width

height

Target height

init_skip_fraction

Fraction of sampling steps to skip when using an init image. Defaults to 0.0 if init_image is not specified and 0.5 if init_image is specified. (maximum: 1)

aesthetic_rating

Aesthetic rating (1-9) - embed to use.

aesthetic_weight

Aesthetic weight (0-1). How much to guide towards the aesthetic embed vs the prompt embed.

seed

Seed for random number generator. If empty, a random seed will be chosen.

intermediate_outputs

Whether to return intermediate outputs. Enable to visualize the diffusion process and/or debug the model. May slow down inference.

Hold at least 15,000 wRAI to use this model

Multi AI platform is completely free, but most models are only accessible to wRAI token holders. If you have any questions, feel free to ask in our Telegram chat

Output

erlich

Readme