- Dec 23, 2018
- 598
- 2,509
I don't think that's cashmere but if I can just borrow it for a second or two I'll check for you
- Dec 21, 2020
- 1,570
- 3,767
Would anyone else feel embarrassed introducing her to your mom?
- Dec 31, 2016
- 316
- 708
there is a slight chance i'd suggest something not quite that low cut
(assuming i could think that far...)
- Jan 24, 2020
- 1,401
- 3,802
You need to post the png file. You can find it in stable-diffusion-webui\outputs\txt2img-images, then the date it was generated.
Then we can see the generation data and better help you out. It's also against the thread guidelines to not include the prompt.
Don't worry no one is going to try rip you off or something stupid like that. The more info we have the better we can help.
Also it's the spirit and purpose of this thread to share prompts for learning purposes. We are very serious about not copying anyone else's work without giving proper credit etc.
Apologize if this is a repeat question, but is there a way to specify Girl A is Lora:X and Girl B is Lora:Y?
I'm trying to work backwards from this example (
Is there a way to base the rear girl off one Lora and the front off another, or does it just blend whatever models you add to the prompts?
I'm trying to work backwards from this example (
You must be registered to see the links
):
Is there a way to base the rear girl off one Lora and the front off another, or does it just blend whatever models you add to the prompts?
- Dec 23, 2018
- 598
- 2,509
Yeah you can use something like Regional Prompter (there's a really good overview of it on the github page)
You must be registered to see the links
So you could have a prompt similar to :-
2 people on a couch in a living room
BREAK One girl with Lora A
BREAK One girl with Lora B
- Sep 26, 2017
- 394
- 614
Yeah, I completely miss read the comment lol. I thought they were asking how to use LyCORIS not make a LyCORIS lol
- Jan 24, 2020
- 1,401
- 3,802
Don't worry about it, you gave good info. It will without a doubt help someone.
- Dec 31, 2016
- 316
- 708
First of all i've never used Comfyui before so probably a lot of basics done horribly wrong, even more than usual.
Second, never used SDXL so no idea how prompting differs.
But it was the only thing i could get the model to even load in without OOM so needs must...
So with the ideal situation of using multiple unknowns i don't really no if the base model is working correctly, the UI setup is even remotely behaving well, nor if the refiner being applied in any way close to what it's meant to.
So here some test images, base and refiner "pairs"...
just a base image to show that there still seem to be an issue with multiple subjects (didn't try to fix it with just prompts) the rest of the image didn't seem too bad thought.
Second, never used SDXL so no idea how prompting differs.
But it was the only thing i could get the model to even load in without OOM so needs must...
So with the ideal situation of using multiple unknowns i don't really no if the base model is working correctly, the UI setup is even remotely behaving well, nor if the refiner being applied in any way close to what it's meant to.
So here some test images, base and refiner "pairs"...
just a base image to show that there still seem to be an issue with multiple subjects (didn't try to fix it with just prompts) the rest of the image didn't seem too bad thought.
- Dec 21, 2020
- 1,570
- 3,767
Nice! I am struggling to see the purpose for the SDXL. I watched a few videos, but still am in WTF mode. Hear me out. I think what the SDXL actually under the hood is is an upscaler workflow. But the user gets stuck with a single model. Naturally, if there are other applications, I am merely uninformed.
But if one picks up SDXL for upscales, then ComfyUI already has a bunch of approaches that one can mix and match based on one's own machine capabilities, desired rendering time, and model preference. These approaches are posted on Civitai, sometimes with "ComfyUI" tag or somesuch. So, I think the solutions are already there and none require a cool 20gb download and get you stuck on a single model.
I attached my go-to upscale CUI approach using your prompt but Zovya's RPGArtist model:
If you pop this into CUI you'll see that you can add upscale blocks up until your VRAM faints. Again, granted I heard about SDXL entire long minute ago, I'd say using any other but SDXL upscale methods where you have flexibility of changing the actual model is more valuable (at least to me). Tho surprisingly three other models I tried produce notably crappier results which I am attaching for science:
You don't have permission to view the spoiler content.
Log in or register now.
What I would love to know if anyone has a ComfyUI workflow for these kind of
You must be registered to see the links
.I picked these from here:
You must be registered to see the links
You must be registered to see the links
(all the way in the end)I can't figure out a way to map these into ComfyUI. Naturally, I mean this in a certain context - that there are tile-like workarounds that would let me trade limited VRAM for time yet upscale a fukton into 10k.
You must be registered to see the links
can be used in Stable-Diffusion WebuiIf you download the pretrained 4x model you can rename it to ERGAN4x (Not 4x+) and use it in stable diffusion
- Dec 31, 2016
- 316
- 708
SDXL is meant to be much better at prompting, like needing less/no negative prompts and being better at understanding shorter tagging etc.
Bit hard for me to tell if that's the case since everything i used were new to me and quickest way to deal with it was to throw weighting and negatives, it's also version 0.9 so it's probably safe to assume there's some issues.
Smallest size you can use it at is >1024x and even at that it seemed like there was some face crushing going on, but that could also be something i was/wasn't doing.
I did notice that it was mainly drawing full body shots, usually when you have square images other models zoom in to fill the width with as much of the character as possible and it actually filled in quite a bit of background on its own. I might have been "lucky" with seeds.
Even in the little time i spent there is clearly issues with SDXL, the size is obviously one, both in GB and vram needs. Still have a way to go to catch some LLM models
Finger seems to be an issue, same with the distorted faces at "range", but since it's meant to be very well suited for finetuning this should be fixable for those that do that awesome work and create models. It's also not gonna have sd2's issues with nsfw since they claim it should just be a simple matter of finetuning. Almost sounded like they'd done it, but couldn't/wouldn't release it just to avoid backlash.
I'm sure there will be a bunch of fixes and optimising done as there's been with other base models/systems time will tell.
There's more than enough things still needing optimising in older version, but we've all seen the improvements so far.
As an example, even on my bad 6gb card i can batch 1024x images at 8 (with a bit of luck), meaning 8 images generated at once, but i can't use highres.fix to "upscale" to 1024 in anything else than just single image. So some "features" have some way to go in older stuff too
Bit hard for me to tell if that's the case since everything i used were new to me and quickest way to deal with it was to throw weighting and negatives, it's also version 0.9 so it's probably safe to assume there's some issues.
Smallest size you can use it at is >1024x and even at that it seemed like there was some face crushing going on, but that could also be something i was/wasn't doing.
I did notice that it was mainly drawing full body shots, usually when you have square images other models zoom in to fill the width with as much of the character as possible and it actually filled in quite a bit of background on its own. I might have been "lucky" with seeds.
Even in the little time i spent there is clearly issues with SDXL, the size is obviously one, both in GB and vram needs. Still have a way to go to catch some LLM models
Finger seems to be an issue, same with the distorted faces at "range", but since it's meant to be very well suited for finetuning this should be fixable for those that do that awesome work and create models. It's also not gonna have sd2's issues with nsfw since they claim it should just be a simple matter of finetuning. Almost sounded like they'd done it, but couldn't/wouldn't release it just to avoid backlash.
I'm sure there will be a bunch of fixes and optimising done as there's been with other base models/systems time will tell.
There's more than enough things still needing optimising in older version, but we've all seen the improvements so far.
As an example, even on my bad 6gb card i can batch 1024x images at 8 (with a bit of luck), meaning 8 images generated at once, but i can't use highres.fix to "upscale" to 1024 in anything else than just single image. So some "features" have some way to go in older stuff too
- Dec 31, 2016
- 316
- 708
Since i mentioned SDXL still having issues with a basic concept as "fingers" i guess this illustrates it
No idea what's really going on but does seem like "something" is getting cooked...
Changed element and did some more tests, some turned out usable
No idea what's really going on but does seem like "something" is getting cooked...Changed element and did some more tests, some turned out usable
- Dec 21, 2020
- 1,570
- 3,767
Upscaler Tips
So, I was pondering. A latent with 100 steps is markedly larger, takes more memory than a latent with 20 steps. May be I incorrectly attribute it to memory, but those refinement steps are not free, you keep paying for them even after you ran them and they are sitting inside your latent. When you manipulate the latent that has more steps you keep paying for those extra steps.
I emperically arrived at it when reducing the refinement in an upscale workflow. The first latent had 18 iterations, the upscale latent denoised 0.5 and ran 7 iterations more.
Turns out the workflow executes exponentially faster when the first latent has less refinement steps. Hmmm.
So, naturally, each "refinement step" is probably a big ass vector/matrix that the GPU adds to the previous already large collection of big ass vectors to start with.
Which made me re-try a resolution I never had enough memory for: 1536 x 2304. This time I lowered the steps and it worked.
A 1536 x 2304 image on a 6GB card, 13/6 steps, 17 minutes to render:
The point of the exercise was that I never knew that the extra steps do limit one's ability to upscale an image.
So, I was pondering. A latent with 100 steps is markedly larger, takes more memory than a latent with 20 steps. May be I incorrectly attribute it to memory, but those refinement steps are not free, you keep paying for them even after you ran them and they are sitting inside your latent. When you manipulate the latent that has more steps you keep paying for those extra steps.
I emperically arrived at it when reducing the refinement in an upscale workflow. The first latent had 18 iterations, the upscale latent denoised 0.5 and ran 7 iterations more.
Turns out the workflow executes exponentially faster when the first latent has less refinement steps. Hmmm.
So, naturally, each "refinement step" is probably a big ass vector/matrix that the GPU adds to the previous already large collection of big ass vectors to start with.
Which made me re-try a resolution I never had enough memory for: 1536 x 2304. This time I lowered the steps and it worked.
A 1536 x 2304 image on a 6GB card, 13/6 steps, 17 minutes to render:
The point of the exercise was that I never knew that the extra steps do limit one's ability to upscale an image.
- Mar 17, 2021
- 323
- 1,093
interesting, need to try this.
Guy's, during my testing on my
Sometimes we need to weight it, but some weight put bad result.
After some test i found weight it then re-add it without weight work like a charm.
Adding (kkw-new-neg-v1.4:1.8) kkw-new-neg-v1.4 work's better then adding only weighted.
Also work adding it multiple time without weight.
Did someone have made some test on textual inversion like these?
Testing it also on positive, had same result, adding textual inversion in weighted followed with non weighted seem really useful.
I hope it work in other Textual inverison.
Guy's, during my testing on my
You must be registered to see the links
, i found a trick these seem really work great.Sometimes we need to weight it, but some weight put bad result.
After some test i found weight it then re-add it without weight work like a charm.
Adding (kkw-new-neg-v1.4:1.8) kkw-new-neg-v1.4 work's better then adding only weighted.
Also work adding it multiple time without weight.
Did someone have made some test on textual inversion like these?
Testing it also on positive, had same result, adding textual inversion in weighted followed with non weighted seem really useful.
I hope it work in other Textual inverison.
- Jan 24, 2020
- 1,401
- 3,802
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.
- Dec 31, 2016
- 316
- 708
Comfy seems to do a few things differently including how it loads models. IE it can load the ~12gb SDXL base model in less than 6gb vram, while a1111 and the SD.next fork can't even load the pruned 7gb version without OOM.
Looking at the operations i'm guessing a way to describe what gets done is that the first steps generate one image, then that image is used in a img2img way and the final steps are applied to it.
So to replicate it in A1111 you'd probably need to pass on the image to that and and apply the "finishing touches". Not really used that so don't know how or if it would work
Looking at the operations i'm guessing a way to describe what gets done is that the first steps generate one image, then that image is used in a img2img way and the final steps are applied to it.
So to replicate it in A1111 you'd probably need to pass on the image to that and and apply the "finishing touches". Not really used that so don't know how or if it would work
- Jan 24, 2020
- 1,401
- 3,802
AFAIK, upscaling in img2img doesn't work like hiresfix. Hiresfix is part of the generative process and "creates" new pixels and thus improves the image quality while "normal" upscaling can't "invent" pixels that aren't already there, so it only makes the image larger without the same bump in quality. So in my opinion and many other's, hiresfix is superior. This is why I wanted to try to replicate what seph had discovered but with hiresfix. I'm sticking to A1111 for now, I never got used to the node system in any of the many softwares I have messed with. Blender, 4d wrap etc.
Hi, i have a question, if i take several pictures of a real life person, do you think i should be able to create a model of that person ?
- Jan 24, 2020
- 1,401
- 3,802
Yes, this is what a Lora or Textual Inversion is. If you are proficient with SD, this would be the next step. If you search in this thread you can find a lot of information and links about this. I recommend to read the awesome guide by Schlongborn that you can find the link to on the first page if you decide to try it out.