[Stable Diffusion] Prompt Sharing and Learning Thread

[Sepheyer]

I could not replicate this with hiresfix. Just to be clear. Did you talk about "normal" upscalers? I have an overclocked GTX1070 with 8Gb vram and I'm stuck with 1280x1920. I can crank up the sampling steps and hires steps, it only takes ages but with very low amount of steps I can't get over that resolution without getting cuda memory error.

I could easily draw incorrect conclusion from my observations. May be steps don't matter at all. I won't be surprised to eventually reach that conclusion.

So, here is the proof that back in the day I couldn't render 1536x2304 using ComfyUI:

"Not enough memory to render 1536x2304 on a 6gb GPU."
https://f95zone.to/threads/ai-art-show-us-your-ai-skill.138575/post-10795995

Naturally, the issue there might be a different workflow where instead of upscaling 512x768 > 1536x2304 I actually upscaled the original 4 times with 1.5 zoom increments. May be the pipeline itself was consuming too much memory storing four different latents for each upscaler.

 

[me3]

When i tested how large images i could get with SDXL and when it would start making duplicate subjects, i noticed that Comfyui automatically kicked in tiled diffusion when it got an OOM. Not sure what version i was using compared to yours, but could be possible that's what was involved, or tiled vae. That drastically affects speed, but it was shown in my console output so unless there's a version difference or some suppressed output it should have been mentioned for you as well

 

[Mr-Fox]

Rub.. rub.. scrub.. scrub.. Jiggle.. Jiggle..

 

[Sepheyer]

When i tested how large images i could get with SDXL and when it would start making duplicate subjects, i noticed that Comfyui automatically kicked in tiled diffusion when it got an OOM. Not sure what version i was using compared to yours, but could be possible that's what was involved, or tiled vae. That drastically affects speed, but it was shown in my console output so unless there's a version difference or some suppressed output it should have been mentioned for you as well

Yes, I saw VAE switched to tile VAE during my ControlNet experiments, but that was a different thing. The post above about that "out of memory error" -- the error was generated not at the VAE level but when the 1536x2304 latent was passed into respective sampler.

It literally kept failing at the sampler level. I lowered the latent to some odd value but gave up after a few tries as I wasn't finding the "breakeven".

 

[devilkkw]

Comfy UI inside a1111 is released. check

You must be registered to see the links

.

 

[me3]

Comfy UI inside a1111 is released. check

You must be registered to see the links

.

Not sure that's worth using compared to just setting it up separate. If it still uses a1111 to load and use models you won't get any of those advantages.
If you want to use that type of UI it'd be much easier to just install comfy, single download and launch for windows (might be for other os too) and you edit one line in a config file to make it read your models/loras/embeddings from a1111 or other installs so you don't need symlinks or copies of that.

 

[devilkkw]

i'm testing it now, it launch itself server and run as self. tab is only a frame page of comfyUi, good is with extension is all configured and ready to use with all model you have.
I'm able to use one model in a1111 and another in comfyUI.
I think is useful for fast comparing prompt and result.
Actually seem not different in perfomance, but i'm totally noob on comfy, i'm just curius on how it work and for me a1111 is my standard.

 

[Mr-Fox]

i'm testing it now, it launch itself server and run as self. tab is only a frame page of comfyUi, good is with extension is all configured and ready to use with all model you have.
I'm able to use one model in a1111 and another in comfyUI.
I think is useful for fast comparing prompt and result.
Actually seem not different in perfomance, but i'm totally noob on comfy, i'm just curius on how it work and for me a1111 is my standard.

I would be curious to try it for the benefit of making widescreen images. Can the extension in A1111 do widescreen? And with hiresfix? With the subject standing? This would be the ideal.

 

[me3]

I would be curious to try it for the benefit of making widescreen images. Can the extension in A1111 do widescreen? And with hiresfix? With the subject standing? This would be the ideal.

do you have an example image of the type of thing you're after? obviously doesn't need to be anything generated, just to have something to ballpark it

 

[me3]

I wonder if the AI is hinting that we should be on the look out for something...
(hint: filename)

 

[Mr-Fox]

do you have an example image of the type of thing you're after? obviously doesn't need to be anything generated, just to have something to ballpark it

I meant in general. When ever I have attempted any widescreen images, it often or almost always results in either multiple subjects or the subject is lying down. I'm working on something special that would be awesome in widescreen.
Posting very soon. Maybe minutes..

 

[Mr-Fox]

This is using the awesome prompt of the eminent Sharlotte. Since I first saw these gorgeous images he shared in this post, I have thought of trying it out myself but with my own Kendra Lora instead of his Patricia TI. I have left the prompt mostly intact, only made a few additions and changed the settings to my own liking.
Thank you very much Sharlotte for sharing this prompt.

The original image:


My rendition:

 

[devilkkw]

I would be curious to try it for the benefit of making widescreen images. Can the extension in A1111 do widescreen? And with hiresfix? With the subject standing? This would be the ideal.

I'm understanding now the extension, but seem you have better control on sampler, preprocess and postprocess.
for hi.res i don't fund the hi.res option, but there are mane Upscale option, i think is these option (also in upscale you can use different model). I like auto memory managment, going up to in resolution and it automatic use tiled vad if you run out of memory.
For high size i got same problem as a1111, multiple subject.

 

[sharlotte]

Mr-Fox you are very welcome. Good to share the original prompts so we can learn off each other
On a different note, I see Sebastian Kamph has just released a 12' video on Comfy UI - very informative, especially if you have never used this type of flow:

You must be registered to see the links

 

[Mr-Fox]

I'm understanding now the extension, but seem you have better control on sampler, preprocess and postprocess.
for hi.res i don't fund the hi.res option, but there are mane Upscale option, i think is these option (also in upscale you can use different model). I like auto memory managment, going up to in resolution and it automatic use tiled vad if you run out of memory.
For high size i got same problem as a1111, multiple subject.

I ran out of reactions. So I say thank you for sharing your testing. Heartemoji

 

[Mr-Fox]

Mr-Fox you are very welcome. Good to share the original prompts so we can learn off each other
On a different note, I see Sebastian Kamph has just released a 12' video on Comfy UI - very informative, especially if you have never used this type of flow:

You must be registered to see the links

 

[Sepheyer]

I meant in general. When ever I have attempted any widescreen images, it often or almost always results in either multiple subjects or the subject is lying down. I'm working on something special that would be awesome in widescreen.
Posting very soon. Maybe minutes..

Here's a workflow file for ComfyUI to do a 2688 x 1536 widescreen using latent composing.

Takes between 20 and 30 minutes on my 6gb card depending on what other windows / apps I have open. Now, I haven't experimented one bit how to make these look better.

But! I think this is actually a deadend, and one should go with OpenPose control nets instead for widescreens. Imma try to do one soon(c).

 

[Mr-Fox]

Here's a workflow file for ComfyUI to do a 2688 x 1536 widescreen using latent composing.

Takes between 20 and 30 minutes on my 6gb card depending on what other windows / apps I have open. Now, I haven't experimented one bit how to make these look better.

But! I think this is actually a deadend, and one should go with OpenPose control nets instead for widescreens. Imma try to do one soon(c).

View attachment 2771940

Thank you! Heartemoji

 

[Synalon]

Is it possible to use tiling in controlnet to upscale the image without affecting the image quality?

And if it is can somebody tell me how please.

 

[Dukez]

Comfy UI inside a1111 is released. check

You must be registered to see the links

. View attachment 2770004

That UI looks way worse than the default experience you get lol, I'm assuming you can add on to it but if not that's an entirely pointless design IMO.