[Stable Diffusion] Prompt Sharing and Learning Thread

[Sepheyer]

Apparently it's considered a "controversial topic, politics or religion" to be for protecting innocence. SMH
If someone took offence to what I said then you are part of the problem, clearly.

That snowflake fucking thing is getting out of hand with people not able to let the opposing view stand. I dunno what you wrote but whoever asked to delete what they disagree with is a filthy fag.

The only moderation action I support for this thread is giving a stern warning for not posting the prompt.

 

[Fuchsschweif]

I will provide an example for my other question about the pixels when I use low denoise values later, but I got a quick question inbetween: Often comfyui starts to become somewhat buggy and doesn't start the queue from the beginning, but rather from here..



I then have to completely close and restart comfyui. Sometimes, the queue button just stops working and can't render anything until I completely restart comfyui.

Any idea why? Is it possible to choose where to start rendering and that I sometimes accidentally clicked into nowhere? But clicking on any node seems not to set a starting point..

 

[me3]

I will provide an example for my other question about the pixels when I use low denoise values later, but I got a quick question inbetween: Often comfyui starts to become somewhat buggy and doesn't start the queue from the beginning, but rather from here..

View attachment 3318994

I then have to completely close and restart comfyui. Sometimes, the queue button just stops working and can't render anything until I completely restart comfyui.

Any idea why? Is it possible to choose where to start rendering and that I sometimes accidentally clicked into nowhere? But clicking on any node seems not to set a starting point..

Comfy "cache" the output from nodes, so if there's been no change in the earlier stages it just runs from the change ones.
Using your image as an example, if nothing changed for the first sampler it'll only start with the second one. It's very useful and time saving in most cases. Only times i've noticed it screws up is with some or the lora stack nodes and it doesn't pick up that their weights etc has been changed. (this might have been fixed, i haven't used it in a while)

 

[Fuchsschweif]

Comfy "cache" the output from nodes, so if there's been no change in the earlier stages it just runs from the change ones.
Using your image as an example, if nothing changed for the first sampler it'll only start with the second one. It's very useful and time saving in most cases. Only times i've noticed it screws up is with some or the lora stack nodes and it doesn't pick up that their weights etc has been changed. (this might have been fixed, i haven't used it in a while)

You mean because I picked "fixed" in the first sampler? This makes sense.. that it would run a new attempt if I switched to randomize.

 

[Sepheyer]

I will provide an example for my other question about the pixels when I use low denoise values later, but I got a quick question inbetween: Often comfyui starts to become somewhat buggy and doesn't start the queue from the beginning, but rather from here..

View attachment 3318994

I then have to completely close and restart comfyui. Sometimes, the queue button just stops working and can't render anything until I completely restart comfyui.

Any idea why? Is it possible to choose where to start rendering and that I sometimes accidentally clicked into nowhere? But clicking on any node seems not to set a starting point..

Exactly, what me3 said. I can only add: both your samplers have fixed seed, meaning CUI won't rerun if nothing changes. But if you change the seed on the first sampler to random, then CUI will render everytime you press the render button.

 

[Fuchsschweif]

Exactly, what me3 said. I can only add: both your samplers have fixed seed, meaning CUI won't rerun if nothing changes. But if you change the seed on the first sampler to random, then CUI will render everytime you press the render button.

Seems not to work. I just did this:



As you can see, both samplers are on "fixed". So I only wanted to refine from the position that the low res preview picture down there has. But when I hit queue promt, it starts to generate a completely new one and starts from the beginning. And sometimes it would just start at the 2nd sampler and skip to re-generate a new one.

 

[Sepheyer]

Assuming nothing else changed - and you didn't accidentally change the seed by clicking on the sampler (which is very easy to do) I am surprised at this behavior. It shouldn't act like this and yet it does.

Out of curiosity - how come the lanes to the second sampler are all white while the same lanes to the first sampler have the proper widget color?

 

[Fuchsschweif]

Out of curiosity - how come the lanes to the second sampler are all white while the same lanes to the first sampler have the proper widget color?

That was because I had clicked on the 2nd sampler, so it was marked and showed all connected cables in white.

 

[Fuchsschweif]

And here's the pixel problem.. I just increased the upscale from 2 to 3, set the denoise down to 0.40 (so that it sticks closer to the first low res generation) and increased the steps from 20 to 30.

This is what happens:

 

[Sepheyer]

And here's the pixel problem.. I just increased the upscale from 2 to 3, set the denoise down to 0.40 (so that it sticks closer to the first low res generation) and increased the steps from 20 to 30.

This is what happens:

View attachment 3319266

View attachment 3319267

Oh, I think this is easy. The latent upscale is meant to go to 2.0 max. So, you literally chain samplers to do 2x then 2x and then 2x again.

 

[Fuchsschweif]

Oh, I think this is easy. The latent upscale is meant to go to 2.0 max. So, you literally chain samplers to do 2x then 2x and then 2x again.

I don't think so, when I use 3x or even 4x I actually get higher resolutions, I just can't bring the denoise lower than 0.55.. otherwise I get this blurred pixelated look.

The latent upscale is just a multiplier of the original resolution as far as I understand it.

 

[Sepheyer]

I don't think so, when I use 3x or even 4x I actually get higher resolutions, I just can't bring the denoise lower than 0.55.. otherwise I get this blurred pixelated look.

I get the same blurred look. Strange-o. Hmm.

 

[Fuchsschweif]

I get the same blurred look. Strange-o. Hmm.

I am creating a 3x version with 0.55 denoise now and post the result then, you'll see it will be clear but higher res than the 2x I posted above..

"Funny" side note, this time Comfyui started right away with the process of upscaling, while it previously entirely generated the first picture new. Would be cool to know what determines this so that I have control over this, if anyone who's reading this knows the answer

 

[Sepheyer]

What I wrote below is incorrect - hkennereth noticed my denoiser was 0.5.
---
May be something went completely tits up in your workflow and got corrupted and shit? I kept getting pixels when running yours, but then I replaced the whole thing with my old latent upscale only workflow and poped your prompts in, and everything worked fine (other than being weird AF):

 

[hkennereth]

I am creating a 3x version with 0.55 denoise now and post the result then, you'll see it will be clear but higher res than the 2x I posted above..

"Funny" side note, this time Comfyui started right away with the process of upscaling, while it previously entirely generated the first picture new. Would be cool to know what determines this so that I have control over this, if anyone who's reading this knows the answer

Regarding the "pixelated" image, I don't believe that the latent upscale works at all with lower than 0.5 denoise values. I couldn't get it to ever work, that's probably a better way to describe it. And I prefer to use the upscale with model technique anyway.

As for your next question: did you tweak the prompt at all? As pointed out, Comfy will only reset the cached nodes if anything changes before them, so if you change the prompt than every single rendering that depends on that prompt will need to be redone. That is true for every single parameter of every node; if you change in one before, it will need to recalculate the following nodes.

 

[Fuchsschweif]

May be something went completely tits up in your workflow and got corrupted and shit?

I would not know what. I posted my workflow, it's quite simple..

Here's the 3x upscaler with 0.55 denoise:

Spoiler: Image

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

As you can see, fantastic quality. But with everything over 2x and denoise below 0.55 I get that trash results..

Regarding the "pixelated" image, I don't believe that the latent upscale works at all with lower than 0.5 denoise values. I couldn't get it to ever work, that's probably a better way to describe it.

It does, I can go down to 45 or 40 as long as I keep the upscaler on 2x.

As for your next question: did you tweak the prompt at all? As pointed out, Comfy will only reset the cached nodes if anything changes before them, so if you change the prompt than every single rendering that depends on that prompt will need to be redone. That is true for every single parameter of every node; if you change in one before, it will need to recalculate the following nodes.

I only tweaked the denoise and upscale setting, but those come after the first generation and the preview picture. So it shouldn't redo all of that too.. how else am I supposed to tweak minor things in the upscale settings to refine my picture, if any little change immediately leads to a new generation?

 

[hkennereth]

May be something went completely tits up in your workflow and got corrupted and shit? I kept getting pixels when running yours, but then I replaced the whole thing with my old latent upscale only workflow and poped your prompts in, and everything worked fine (other than being weird AF):

View attachment 3319384

Yeah, it's because on your workflow you're using 0.5 denoise for the latent upscale. That's why it works.

I would not know what. I posted my workflow, it's quite simple..

Here's the 3x upscaler with 0.55 denoise:

Spoiler: Image

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

As you can see, fantastic quality. But with everything over 2x and denoise below 0.55 I get that trash results..



It does, I can go down to 45 or 40 as long as I keep the upscaler on 2x.



I only tweaked the denoise and upscale setting, but those come after the first generation and the preview picture. So it shouldn't redo all of that too.. how else am I supposed to tweak minor things in the upscale settings to refine my picture, if any little change immediately leads to a new generation?

I used the workflow directly from your image, and (switching to 2x upscale because my GPU is not that fast) this is what I got with the original 0.4 denoise:


And then, just changing to 0.5 denoise, same settings on everything otherwise:


I usually don't use latent upscale because it doesn't usually work well to preserve likeness of people that were created with loras, but if all you care is the final image and you're not trying to make it look like anyone in particular, it works great... but just need to set the denoise to 0.5 or higher.

 

[Fuchsschweif]

I used the workflow directly from your image, and (switching to 2x upscale because my GPU is not that fast) this is what I got with the original 0.4 denoise:

Hmmmm weird, now I get that look too, but the last time I tried it worked well. I still don't get why it happens though. Denoise of 0.40 means that the AI will just have to do fewer things new and takes more from the existing generation.. 0.55 makes too varied results if one wants to stick closer to the original, it must be possible to go lower.

 

[Sepheyer]

Regarding the "pixelated" image, I don't believe that the latent upscale works at all with lower than 0.5 denoise values. I couldn't get it to ever work, that's probably a better way to describe it. And I prefer to use the upscale with model technique anyway.

As for your next question: did you tweak the prompt at all? As pointed out, Comfy will only reset the cached nodes if anything changes before them, so if you change the prompt than every single rendering that depends on that prompt will need to be redone. That is true for every single parameter of every node; if you change in one before, it will need to recalculate the following nodes.

Aight here is a "fix" - use different latent upscale called NNLatent it works for ~0.2 and up in exchange for dropping some details.

 

[Fuchsschweif]

If I want a let's say 2K picture in 16:9 ratio (for youtube videos), what's the starting resolution I need to in the empty latent image?