[Stable Diffusion] Prompt Sharing and Learning Thread

[Fuchsschweif]

I activate the hiresfix again and use the same settings, meaning 40hires steps and 0.3 denoising with ultrasharp upscaler.

Ok, let's see what I get out of this. I take my picture from above that I like (this one) , extract the png info and send it to text2image:

I add 4x ultrasharp in the highres upscaler menu, set hires steps to 40, denoiser to 0.3:



Again, a coooompletely different result. (And the quality is also pretty blurry.)

 

[Fuchsschweif]

(And the quality is also pretty blurry.)

Re-running the exact same thing with increased "Upscale by" slider from 1 to 2 (I think the previous one was blurry because 1 meant = same resolution?), I got this:




So already way better in terms of sharpness, although I am not 100% satisfied with the result.

But funny that it did now recreate 1:1 the same picture.

Although the seed is still from the previous picture.

Why does SD not recreate from the seed, I don't get it

 

[Jimwalrus]

Re-running the exact same thing with increased "Upscale by" slider from 1 to 2 (I think the previous one was blurry because 1 meant = same resolution?), I got this:

View attachment 3002841


So already way better in terms of sharpness, although I am not 100% satisfied with the result.

But funny that it did now recreate 1:1 the same picture.

Although the seed is still from the previous picture.

Why does SD not recreate from the seed, I don't get it

Double check the prompts, even removing a space or de-pluralising a word (and especially fixing a typo) can completely change the generated image.
If you've got X-Tensors enabled that can make an image vary a tiny amount between otherwise identical parameters, but not this much.

Anyway, now keep that seed and see what more/less gen steps, more/less hires steps, different denoising strengths, different Samplers, different Upscalers etc do.
You can automate this using Scripts>X/Y/Z Plotter - see the tutorial linked on pg1 of this thread - and get some side-by-side comparisons.

It will help you find your style too.

 

[Mr-Fox]

As the eminent Jim said. Nothing I have said is with intention of being condescending, only to help. You are new here and I don't know what your skill is or knowledge. I keep also other people in mind when I post tips or any tutorials or examples.
Please don't missunderstand our intentions.

I'm testing your matrix image. Pretty cool concept. It had variation seed in extra activated. This will ofc give variations..
My first image didn't match yours so I deactivated the variation seed. Now it's very similair to yours.



Clipskip 2 is not a problem. It's fine to use if it's needed. Try first without and then with clipskip 2 to see the effect.
It can fix things but it can also make things worse it depends on what you are generating and what you are generating with such as checkpoint and or loras etc. If they have been trained with clipskip 2 then it's better to use this ofc and the creator often say this on civit if this is the case.

Here's without clipskip 2


For hiresfix, the upscaler has a big effect on the final result so try others also. I suggested Ultrasharp because of the images you had posted, Anime oriented. Ultrasharp gives soft edges and smoothness. I'm very fond of NMKD Superscale since I mostly create images with photo realism. It gives crisp edges and fine details. I also use NMKD Face a lot.

You must be registered to see the links

You must be registered to see the links

With Ultrasharp


Now I saw that you had set the multiplier to 1, this means that you did not upscale. Set it over 1 to upscale. I would recommend at least 1.5 but I always use 2.
For demonstration only this is NMKD Superscale with multiplier 1.5 .

Also don't use so high cfg, unless it is for a very specific purpose. Too high cfg will make the image "burnt" or "overcooked".
I have set it to 8. I also increased the amount of steps. Each step gives sd a chance to refine the image more. Higher number is better to a point. You get diminishing return over 40.
A very high amount of steps can cause loss of details, such as nipples for example.

 

[Sepheyer]

 

[Jimwalrus]

There we go, the Variation seed in the Extras options is the smoking gun for not getting consistent results with a given seed, especially if it's set to random (-1)

It's one of those options that's easy to set and forget it's still on.

 

[Jimwalrus]

View attachment 3002902

A1111 plebs looking at ComfyUI:

 

[Fuchsschweif]

There we go, the Variation seed in the Extras options is the smoking gun for not getting consistent results with a given seed, especially if it's set to random (-1)

I'm testing your matrix image. Pretty cool concept. It had variation seed in extra activated. This will ofc give variations..
My first image didn't match yours so I deactivated the variation seed. Now it's very similair to yours.

I had extras thicked off when I tried to re-create from the seed, as you can see in my shared settings here.

The extras thing is probably baked into the PNG because that's how I got there. However, when trying to recreate from the seed, I thicked it off and only used the seed, so this isn't causing the issue.

Double check the prompts, even removing a space or de-pluralising a word (and especially fixing a typo) can completely change the generated image.

I didn't touch the prompts at all either :/

Anyway, now keep that seed and see what more/less gen steps, more/less hires steps, different denoising strengths, different Samplers, different Upscalers etc do.

But I want to re-create the picture from my original seed! SD created a completely new image and then re-created new generations based on that one instead of the OG seed used in the first place - I don't get it.

For hiresfix, the upscaler has a big effect on the final result so try others also. I suggested Ultrasharp because of the images you had posted, Anime oriented. Ultrasharp gives soft edges and smoothness. I'm very fond of NMKD Superscale since I mostly create images with photo realism. It gives crisp edges and fine details. I also use NMKD Face a lot.

Where do I drop them?

 

[Fuchsschweif]

As the eminent Jim said. Nothing I have said is with intention of being condescending, only to help. You are new here and I don't know what your skill is or knowledge. I keep also other people in mind when I post tips or any tutorials or examples.
Please don't missunderstand our intentions.

No don't worry, I just wanted to explain where I'm coming from so that you guys understand where I am at with understanding prompt engineering.

 

[Mr-Fox]

I had extras thicked off when I tried to re-create from the seed, as you can see in my shared settings here.

The extras thing is probably baked into the PNG because that's how I got there. However, when trying to recreate from the seed, I thicked it off and only used the seed, so this isn't causing the issue.




I didn't touch the prompts at all either :/



But I want to re-create the picture from my original seed! SD created a completely new image and then re-created new generations based on that one instead of the OG seed used in the first place - I don't get it.




Where do I drop them?

The extra was selected when I loaded your image from PNG Info. This is why it gave variations. Make sure it's not active.
After I deselected it, everything has been fine. 822547809 is the seed it had and the variations strength 0.2 .
If you load an image from PNG Info you will get all settings, including some that you might not want.
Normally when you set the seed, as long as you don't change the resolution or something major the image should not change drastically.

 

[Sepheyer]

Open Pose ControlNet - Did You Know?

So, ComfyUI has a feature where it can cycle thru the pose files either randomly or up/down the folder content. Done via primitives, you can grab the setup from here:

Spoiler: More

You don't have permission to view the spoiler content. Log in or register now.

So what?

The non-ControlNet posing is hit and miss, and so are body proportions, etc. You can address this via ControlNet's Open Pose but you have to (more like had to) pick the file manually which went against generating poses randomly. Now you can get CUI to just go thru all the pose files which can give you more variations than whatever the actual model comes with.

 

[Fuchsschweif]

The extra was selected when I loaded your image from PNG Info. This is why it gave variations. Make sure it's not active.
After I deselected it, everything has been fine. 822547809 is the seed it had and the variations strength 0.2 .
If you load an image from PNG Info you will get all settings, including some that you might not want.
Normally when you set the seed, as long as you don't change the resolution or something major the image should not change drastically.

I tried it again. Picked the OG picture in PNG info, send to text2image, removed the "extras" thick, picked an upscaler, and boom:



It's again creating the second image. WTF

 

[Fuchsschweif]

The extra was selected when I loaded your image from PNG Info. This is why it gave variations. Make sure it's not active.
After I deselected it, everything has been fine. 822547809 is the seed it had and the variations strength 0.2 .

Wait. I have a different seed. How did it spit out another seed on your end?

 

[Mr-Fox]

I tried it again. Picked the OG picture in PNG info, send to text2image, removed the "extras" thick, picked an upscaler, and boom:

View attachment 3002941

It's again creating the second image. WTF

Sometimes SD start to misbehave this is when we put him in the corner to think of what he did...
Try reboot SD and load your image again. If it's still the same then I don't know. We would need to trouble shoot it then.

 

[Mr-Fox]

Wait. I have a different seed. How did it spit out another seed on your end?

View attachment 3002949

This is the variation seed

 

[Fuchsschweif]

This is the variation seed

Why would it not show me the seed of the exact picture I put in?
And where did you get the correct seed then?

Edit: ah, saw it in the PNG info.

 

[Mr-Fox]

With NMDK with multiplier:2 28 sampling steps and 56 hiresteps denoising 0.3 and cfg 8

The left eye (her right), is a bit wonky but sd has typically difficulties with sideglanses etc

 

[me3]

What optimising settings are you using, is "rng" from cpu, gpu or nv?
Seed isn't 110% regardless of being the same value IF it's being fed through different things.
Old version of xformers wasn't deterministic, same is true for one of the sdp variations too i believe.

Though if you're throwing variation seed into the mix that'll really screw with things...

 

[Fuchsschweif]

The extra was selected when I loaded your image from PNG Info. This is why it gave variations. Make sure it's not active.
After I deselected it, everything has been fine. 822547809 is the seed it had and the variations strength 0.2 .

Okay both seed don't work for me

2549670335 is what automatically gets extracted from png info -> send to text2img.

That one results in our infamous second picture:



The other variation seed you shared ( 822547809 )doesn't work either, you can tell from the preview it's again creating something new:

 

[Fuchsschweif]

What optimising settings are you using, is "rng" from cpu, gpu or nv?

I have an nvidia card, should I switch to NV?

I think this isn't the root issue though. SD has no problem re-creating the same picture over and over again, it's just not the one from the seed..