- Jan 24, 2020
- 1,401
- 3,793
- Sep 15, 2021
- 895
- 3,303
Not quite. In SD, the braces are 0.1 additions.
So "plump" is plump at 1 strength.
"(plump)" is plump at 1.1 strength.
"((((plump))))" is plump at 1.4 strength.
"(plump:1.2)" is plump at either 1.2, 1.21 or 1.3 (it depends who you ask!)
"big tits" is big and tits SEPARATELY at strength 1. SD sort of realises they are together, especially with commas before & after, but not reliably.
"(big tits)" is big tits at strength 1.1 - the braces help SD lump them together as a single token.
So your example of "(apples), oranges, ((carrots))" is actually apples at 1.1, oranges at 1 and carrots at 1.2.
- Sep 15, 2021
- 895
- 3,303
There we are - definitive. Thanks.
But remember, it only multiplies it by 110% of the previous total, it doesn't add 100% to the previous total
- Dec 31, 2016
- 316
- 708
I don't have prompt for easy c/p atm, but i believe part of it was "<something>, upper body shot closeup:1.5, <something more>".
So not only is this slightly confusing to a reader, is the intention to apply the weight to just "closeup" or everything between the commas.
The same "confusion" can apply to the parser too, i haven't been digging around in that so see how it works in detail, but i have had a fair bit of dealings with other parsers and they are all "fragile" at best so as a general rule you don't want to push the limits. So simply wrapping everything that's intended to be weighted is a much simpler option for everyone involved.
It wouldn't surprise me if :1.5 outside of parenthesis doesn't actually weight given that the behaviour of the "editor" is to apply both () and :1.1 in the same action. But the parser in a1111 is different that comfy and i'm sure other "frontends" can have their own parser so despite all of them being SD, some behaviour might not be completely consistent
That's why I wrote "importance-ratio", to undermine that it's not an absolute ratio
The point was that putting everything into parantheses is pointless as everything gets the same multiplier and therefore importance.
- Sep 15, 2021
- 895
- 3,303
Ah, OK. Wasn't clear - if anything it did seem like you were implying a strength ratio of 1:2:3That's why I wrote "importance-ratio", to undermine that it's not an absolute ratio
The point was that putting everything into parantheses is pointless as everything gets the same multiplier and therefore importance.
But yes, if you weight everything equally it will basically treat everything the same. Unless it feels like fucking you around that day...
Another rabbit hole to go into is prompt order - there's a huge debate as to whether the prompts should be in strict order of importance, or whether it's just the first 75 tokens are equal, then the next 75 and so on.
- Jan 24, 2020
- 1,401
- 3,793
Yes I have also read that the order has an importance ranking effect. If anyone else than just me feel the need to read up on prompting, I often come back to this guide:
You must be registered to see the links
BTW, fudge I was wrong about ( ) [ ] syntax. Impossible..
- Sep 15, 2021
- 895
- 3,303
The magic word there being "Should"
If it's there, and written in a way that it's understandable. And it hasn't been superseded in the last 12 months or so.
This is all cutting edge and mostly open source, so don't expect documentation to be good!
- Dec 31, 2016
- 316
- 708
Example was requested so i guess this might work.
I added () to the prompt, first just for the closeup, then for the face lighting as well.
This does seem to suggest that the weighting isn't applied when it's not wrapped in (), or at the very least, not applied correctly.
Granted, the prompt gets "altered" by adding this but i don't think the changes are random enough as they seem to follow the intention in the prompt
I added () to the prompt, first just for the closeup, then for the face lighting as well.
This does seem to suggest that the weighting isn't applied when it's not wrapped in (), or at the very least, not applied correctly.
Granted, the prompt gets "altered" by adding this but i don't think the changes are random enough as they seem to follow the intention in the prompt
- Dec 31, 2016
- 316
- 708
So i went through the parser code and found the weight handling, then ran the prompt through with and without the ()
Without the () the whole prompt is assigned a weight of 1.0, meaning the :1.5 and :1.4 is ignored as weighting and more considered "part of the text" along with the word infront, so "closeup:1.5" is seemingly treated as one belonging together.
With () the weighting is done more as expected and those two sections get their 1.5 and 1.4 weighting, rest is assigned 1.0
Just to test how things are handled i ran this as well:
Without the () the whole prompt is assigned a weight of 1.0, meaning the :1.5 and :1.4 is ignored as weighting and more considered "part of the text" along with the word infront, so "closeup:1.5" is seemingly treated as one belonging together.
Python:
[['1 girl in a black matrix coat, standing on a rooftop, upper body shot closeup:1.5, cinematic shot, golden sidelight on her face:1.4, foggy atmosphere, neon glowing in the back, rainy day, cloudy, cyberpunk cityscape in the back, blade runner style, cyberpunk style, serious look, rough and moody atmosphere, gritty style, photoshooting', 1.0]]With () the weighting is done more as expected and those two sections get their 1.5 and 1.4 weighting, rest is assigned 1.0
Python:
[['1 girl in a black matrix coat, standing on a rooftop, ', 1.0], ['upper body shot closeup', 1.5], [', cinematic shot, ', 1.0], ['golden sidelight on her face', 1.4], [', foggy atmosphere, neon glowing in the back, rainy day, cloudy, cyberpunk cityscape in the back, blade runner style, cyberpunk style, serious look, rough and moody atmosphere, gritty style, photoshooting', 1.0]]Just to test how things are handled i ran this as well:
(This) (is:1.1) ((a)) ((test:1.1)) (prompt:1.2)
Python:
[
['This', 1.1],
[' ', 1.0],
['is', 1.1],
[' ', 1.0],
['a', 1.2100000000000002],
[' ', 1.0],
['test', 1.2100000000000002],
[' ', 1.0],
['prompt', 1.2]
]- Jan 24, 2020
- 1,401
- 3,793
Another way to keep the pose and composition is to use openposer in controlnet. I thought I should just mention this.
You need to install controlnet ofc. Load the original image in controlnet and select openpose, choose "open pose full " and then press "preprocessor" (small explosion cymbol). This will detect the image and create a pose, you can adjust it in the editor if you need. Then press "send pose to controlnet" . Now you can generate image after image and change the background, the clothes or what ever you want while the pose reamains the same.
The image I generated with this pose:
Or something different..
Link for the editor:
You need to install controlnet ofc. Load the original image in controlnet and select openpose, choose "open pose full " and then press "preprocessor" (small explosion cymbol). This will detect the image and create a pose, you can adjust it in the editor if you need. Then press "send pose to controlnet" . Now you can generate image after image and change the background, the clothes or what ever you want while the pose reamains the same.
The image I generated with this pose:
Or something different..
Link for the editor:
You must be registered to see the links
Last edited:
Interesting, thanks!
It makes sense in terms that it makes it easier to isolate desired parts of a prompt. So one could write:
A city with a park (and tall skyscrapers:1.5), and since the whole part is put in parantheses, SD doesn't have to take the whole prompt until the comma into consideration.
I found a website stating that adding + or - (also multiple times possible, like "forest++++") would add or subtract importance to a word, but a little simple test with "trees++++, buildings--" and vice versa didn't prove that.
- Dec 21, 2020
- 1,528
- 3,598