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!

Cool

New stuff

Paper: https://arxiv.org/abs/2303.03032

Takes only a few seconds to calculate.

Most similiar suffix tokens : "vfx cleanup |warcraft |defend |avatar |wall |blu |indigo |dfs |bluetooth |orian |alliance |defence |defenses |defense |guardians |descendants |navis |raid |avengersendgame "

most similiar prefix tokens : “imperi-blue-|bluec-|war-|blau-|veer-|blu-|vau-|bloo-|taun-|kavan-|kair-|storm-|anarch-|purple-|honor-|spartan-|swar-|raun-|andor-”

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

So its 64-131 between work done by bystanders vs. work done by police?

And casualty rate is actually lower for bystanders doing the work (with their guns) than the police?

I can’t speculate.

If you feel up for the task I’d suggest running prompts that use Euler a at 20 steps for a given seed using that model and see if results match images on the perchance site.

If they do , then we know the furry model = Pony diffusion

(Though IIRC the furry model on perchance existed before Pony Diffusion. )

Aha. So what you wanted to say was that “Starlight” and/or “Glimmer” are triggerwords for the furry model. Gotcha!

Those are both the furry model tho?

From what I know it is possible to bypass the keyword trigger by writing something like _anime or _1girl

Good idea!

I’d say yes

Add a little code snippet that explicitly selects the model.

If a new update is coming “quite soon”

, then that could be several months from now.

And if the new update means

by default replacing the current (three?) SD 1.5 models

with a single SD 1.5 model.

Why not use all of them? As in older models + the new one , via this system?

//—//

So what I mean by this is;

In the next update ,

The new SD 1.5 model could be available by default

, and if user writes (model:::anime) , (model:::photo) or (model:::anthro)

, then it uses the “older” SD 1.5 models.

Yeah , I understand the situation.

I appreciate you telling me model selection is within the top categories on civitai.

I didn’t know multiple models were being used.

Any chance you could allow a user to specify which model to generate with , to override switching models based on keywords?

Like for example writing (model:::Anime) in the prompt to use an anime model?