Updated Features (markdown)

AUTOMATIC1111 2023-01-15 22:41:51 +03:00
parent 1602280ec5
commit 277e75cafb

@ -174,6 +174,12 @@ Recommended parameters for upscaling:
| ![](images/sd-upscale-castle-original.png) | ![](images/sd-upscale-castle-realesrgan.png) | ![](images/sd-upscale-castle-esrgan-topaz-gigapixel.png) | ![](images/sd-upscale-castle-sd-upscale.png) |
| ![](images/sd-upscale-city-original.png) | ![](images/sd-upscale-city-realesrgan.png) | ![](images/sd-upscale-city-esrgan-topaz-gigapixel.png) | ![](images/sd-upscale-city-sd-upscale.png) |
# Infinite prompt length
Typing past standard 75 tokens that Stable Diffusion usually accepts increases prompt size limit from 75 to 150. Typing past that increases prompt size further. This is done by breaking the prompt into chunks of 75 tokens, processing each independently using CLIP's Transformers neural network, and then concatenating the result before feeding into the next component of stable diffusion, the Unet.
## BREAK keyword
Adding a `BREAK` keyword (must be uppercase) fills the current chunks with padding characters. Adding more text after `BREAK` text will start a new chunk.
# Attention/emphasis
Using `()` in the prompt increases the model's attention to enclosed words, and `[]` decreases it. You can combine multiple modifiers: