mirror of
https://github.com/AUTOMATIC1111/stable-diffusion-webui.git
synced 2025-04-05 12:09:00 +08:00
create composable diffusion section
parent
245799ce1d
commit
ed37e7f089
16
Features.md
16
Features.md
@ -366,6 +366,22 @@ A convenience option to partially render your image at a lower resolution, upsca
|
||||
|  |  |
|
||||
|  |  |
|
||||
|
||||
# Composable Diffusion
|
||||
|
||||
A method to allow the combination of multiple prompts.
|
||||
combine prompts using an uppercase AND
|
||||
|
||||
a cat AND a dog
|
||||
|
||||
Supports weights for prompts: `a cat :1.2 AND a dog AND a penguin :2.2`
|
||||
The default weight value is 1.
|
||||
It can be quite useful for combining multiple embeddings to your result: `creature_embedding in the woods:0.7 AND arcane_embedding:0.5 AND glitch_embedding:0.2`
|
||||
|
||||
Using a value lower than 0.1 will barely have an effect. `a cat AND a dog:0.03` will produce basically the same output as `a cat`
|
||||
|
||||
This could be handy for generating fine-tuned recursive variations, by continuing to append more prompts to your total. `creature_embedding on log AND frog:0.13 AND yellow eyes:0.08`
|
||||
|
||||
|
||||
# Interrupt
|
||||
|
||||
Press the Interrupt button to stop current processing.
|
||||
|
Loading…
x
Reference in New Issue
Block a user