tstramer/material-diffusion

Stable diffusion fork for generating tileable outputs using v1.5 model

Capabilities

1:14:33:416:99:162:33:2Seed

Cost

Community model (estimated from hardware time)

Input Parameters

Name	Type	Description	Default	Constraints
`guidance_scale`	number	Scale for classifier-free guidance	`7.5`	min: 1, max: 20
`height`	integer	Height of output image. Maximum size is 1024x768 or 768x1024 because of memory limits	`512`	1282563844485125766407047688328969601024
`init_image`	string(uri)	Inital image to generate variations of. Will be resized to the specified width and height	`—`	—
`mask`	string(uri)	Black and white image to use as mask for inpainting over init_image. Black pixels are inpainted and white pixels are preserved. Tends to work better with prompt strength of 0.5-0.7. Consider using https://replicate.com/andreasjansson/stable-diffusion-inpainting instead.	`—`	—
`num_inference_steps`	integer	Number of denoising steps	`50`	min: 1, max: 500
`num_outputs`	integer	Number of images to output. If the NSFW filter is triggered, you may get fewer outputs than this.	`1`	min: 1, max: 10
`prompt`	string	Input prompt	`""`	—
`prompt_strength`	number	Prompt strength when using init image. 1.0 corresponds to full destruction of information in init image	`0.8`	—
`scheduler`	string	Choose a scheduler. If you use an init image, PNDM will be used	`"K-LMS"`	DDIMK-LMSPNDM
`seed`	integer	Random seed. Leave blank to randomize the seed	`—`	—
`width`	integer	Width of output image. Maximum size is 1024x768 or 768x1024 because of memory limits	`512`	1282563844485125766407047688328969601024

guidance_scalenumber

Scale for classifier-free guidance

Default: 7.5min: 1, max: 20

heightinteger

Height of output image. Maximum size is 1024x768 or 768x1024 because of memory limits

Default: 512

1282563844485125766407047688328969601024

init_imagestring

Inital image to generate variations of. Will be resized to the specified width and height

maskstring

Black and white image to use as mask for inpainting over init_image. Black pixels are inpainted and white pixels are preserved. Tends to work better with prompt strength of 0.5-0.7. Consider using https://replicate.com/andreasjansson/stable-diffusion-inpainting instead.

num_inference_stepsinteger

Number of denoising steps

Default: 50min: 1, max: 500

num_outputsinteger

Number of images to output. If the NSFW filter is triggered, you may get fewer outputs than this.

Default: 1min: 1, max: 10

promptstring

Input prompt

Default: ""

prompt_strengthnumber

Prompt strength when using init image. 1.0 corresponds to full destruction of information in init image

Default: 0.8

schedulerstring

Choose a scheduler. If you use an init image, PNDM will be used

Default: "K-LMS"

DDIMK-LMSPNDM

seedinteger

Random seed. Leave blank to randomize the seed

widthinteger

Width of output image. Maximum size is 1024x768 or 768x1024 because of memory limits

Default: 512

1282563844485125766407047688328969601024

Version: a42692c54c0fUpdated: 7/25/20262.4M runs