My solution has been to left click , select “inspect element” to open the browsers HTML window.
Then zoom out the generator as far as it goes , and scroll down so the entire image gallery (or a part of it at least) is rendered within the browser.
The ctrl+c copy the HTML and paste it in notepad++ , and use regular expressions to sort out the image prompts (and image source links) from the HTML code
Not exactly a good fix , but it gets the job done at least.
Big ask.
Personally , I’d be overjoyed to just have embeddings available on the site.
It is good that you ask :)!
Read this: https://arxiv.org/abs/2406.02965
The tldr:
Negatives should be ‘things that appear in the image’ .
If you prompt a picture of a cat , then ‘cat’ or ‘pet’ can be useful items to place in the negative prompt.
Best elimination with adjective words is with 16.7% delay , by writing \[ : neg1 neg2 neg3 :0.167 \] instead of neg1 neg2 neg3
Best elimination for noun words is with 30% delay , by writing “\[ : neg1 neg2 neg3 :0.3 \]” in the negative prompt instead of "neg1 neg2 neg3 "
Cool!
I appreciate you took the time to write a sincere question.
Kinda rude for people to downvote you.
Simple and cool.
Florence 2 image captioning sounds interesting to use.
Do people know of any other image-to-text models (apart from CLIP) ?
Wow , yeah I found a demo here: https://huggingface.co/spaces/Qwen/Qwen2.5
A whole host of LLM models seems to be released. Thanks for the tip!
I’ll see if I can turn them into something useful 👍
That’s good to know. I’ll try them out. Thanks.
Hmm. I mean the FLUX model looks good
, so there must maybe be some magic with the T5 ?
I have no clue, so any insights are welcome.
T5 Huggingface: https://huggingface.co/docs/transformers/model_doc/t5
T5 paper : https://arxiv.org/pdf/1910.10683
Any suggestions on what LLM i ought to use instead of T5?
Good find! Fixed. It was well appreciated.
Fair enough
I get it. I hope you don’t interpret this as arguing against results etc.
What I want to say is ,
If implemented correctly , same seed does give the same result for output for a given prompt.
If there is variation , then something in the pipeline must be approximating things.
This may be good (for performance) , or it may be bad.
You are 100% correct in highlighting this issue to the dev.
Though its not a legal document , or a science paper.
Just a guide to explain seeds to newbies.
Omitting non-essential information , for the sake of making the concept clearer , can be good too.
Perchance dev is correct here Allo ;
the same seed will generate the exact same picture.
If you see variety , it will be due to factors outside the SD model. That stuff happens.
But it’s good that you fact check stuff.
Do you know where I can find documemtation on the perchance API?
Specifically createPerchanceTree ?
I need to know which functions there are , and what inputs/outputs they take.
Thanks! I appreciate the support. Helps a lot to know where to start looking ( ; v ;)b!
New stuff
Paper: https://arxiv.org/abs/2303.03032
Takes only a few seconds to calculate.
Most similiar suffix tokens : "vfx "
most similiar prefix tokens : “imperi-”
New stuff
Paper: https://arxiv.org/abs/2303.03032
Takes only a few seconds to calculate.
Most similiar suffix tokens : "vfx "
most similiar prefix tokens : “imperi-”
I count casualty_rate = number_shot / (number_shot + number_subdued)
Which in this case is 22/64 = 34% casualty rate for civilians
and 98/131 = 75% casualty rate for police
That is good to hear!
I think Lemmy has trouble with the filesize tho