After a bumpy start (see my other thread about it), I start to feel a bit comfortable with SDXL to the point that I probably wont look back at the 1.5 models. This wizard-hat wearing cat was generated in A1111 with:
"a cute kitty cat wearing a wizard hat, candy rays beaming out of the cat ears, (a swirling galaxy of candy pops background:0.7), 1980's style digital art, hyperrealistic, paintbrush, shallow depth of field, bokeh, spotlight on face, cinematic lighting " Negative (from a standard style I use): "(bad anatomy:1.1), (high contrast:1.3), watermark, text, inscription, signature, canvas frame, (over saturated:1.2), (glossy:1.1), cartoon, 3d, ((disfigured)), ((bad art)), ((b&w)), blurry, ((bad anatomy)), (((bad proportions))), ((extra limbs)), cloned face, (((disfigured))), extra limbs, (bad anatomy), gross proportions, (malformed limbs), ((missing arms)), ((missing legs)), (((extra arms))), (((extra legs))), mutated hands, (fused fingers), (too many fingers), (((long neck))), Photoshop, video game, ugly, tiling, poorly drawn hands, 3d render
Generated at 1024x1024 without refiner.
There's a few things to be aware of, when working with SDXL in A1111 that I found:
And the biggest one for me:
A word to the refiner model: as of now I don't see big quality improvements if I go with the refiner model in img2img @about 0.1 - 0.25 denoising. I think I will play around more with this at higher denoising strength and see what I can get out of it.
Anyway, I think the SDXL is a huge improvement and I start getting really exciting results already Cheers :)
I look them up at lemmyverse.net
I go there about once a week to see if there are new communities I might be interested in. I'm on a selfhosted single-user instance, so my "all" is identical to my "subscribed" and this is how I populate my feed.
Yeah, reducing CFG can help a lot. It sometimes feels to me, that getting a good image is knowing at what point to let loose ...
When I started I was just copying from online galleries like Civitai or Leonardo.ai, which gave me noticeable better images than what I have came up with myself before. However, it seemed to me that many of these images may also just have copied prompts without understanding what's really going on with them and I started to experiment for myself.
What I will do right now is to build my images "from ground up" starting with super basic prompts like "a house on a lake" and work from there. First adding descriptions to get the image composition right, then work in the style I'm looking for (photography, digital artwork, cartoon, 3D render, ...). Then I will work in enhancers and see what they change. I found that one has to be patient, only change one thing at a time and always do a couple of images (at least a batch of 8) to see if and what the changes are.
So, I still comb though image galleries for inspiration in prompting, but I will now most of the time just pick one keyword or enhancer and see what it does to my own images.
It is a long process that requires many iterations, but I find it really enjoyable.
please do, I thinking to start making LoRa's as well and the tool looks like it would make the process much easier. Let me know how it goes for you.
I started with the smallest offer available and later upgraded to the second smallest, which now has 4GB RAM. I also have rented additional diskspace, so that I have 30GB now. RAM and CPU are now certainly fine, but I don't know yet about disk space. I read that Lemmy/Mastodon can eat up space quickly and I have currently used up about half of my disk space.
You should be able to configure this differently. Either switch of the confirmation mails completely or use the email credentials from another server.
I use Synapse as Matrix server and Element as client. It doesn't need port 25 (8008 and 8448 are needed in my setup). On Lemmy and Mastodon I configured outgoing mail using smtp via my existing mail hoster, so I don't send mail from my own server. Also, all googling I did said to stay away from selfhosting email, as it is a hassle not to be immediately blocked as a spam mail server ..
I use Synapse as the Matrix server and Element as client on desktop and mobile. It does support video calls, but so far I only tested it for a minute.
I spent a lot of time googling and on youtube, to get a basic understanding for what I was trying to achieve, 2 weeks of after-work time at least. If I should guess 40-50 hours in total. Getting a single piece to work, by following a tutorial can be easy but to get all the things working together was a struggle. Once I had a better grasp on what a reverse proxy is and how docker containers work together in networks, pieces started to fall into place.
I have fail2ban running as well, didn‘t mention it in the op. Also closed all ports beside 80 and 443, which are routed through my NPM proxy. SSH is allowed, but login only with ssh key, no pw authentication.
So far it‘s running well, but I expect things to break when I‘ll need to update parts of it. I have a snapshot from which i can reinstall, but recurring backups need yet to be set up.
I run Nginx with Nginx Proxy Manager web-ui, which makes setting up proxy hosts and handling letsencrypt certificates really easy. I also use Portainer to manage my docker containers. This works well for the stuff I mentioned above (Nextcloud, Matrix, Lemmy mostly)
If I can get Mastodon into the same setup, it'd be neat. I just found a lot of discussion with problems, so I thought I'll ask about it before I spend a few hours in vain :)
The prompt was just an example and usually my prompts get quite a bit longer than that. But in 1.5 models I manage to get what I want to see eventually. I also find that throwing in qualifiers like "mesmerizing" does do something to the image, although in can be subtle.
However, what I wanted to say here was that in SDXL my prompting seems to go to nowhere and I feel I'm not able to get out the kind of image I have in my head. Keeping the prompt example, in SD1.5 using a custom model like Deliberate 2.0 I'm able to end up with an image of a hat wearing cat surround by surreal looking candy pops. (however the final prompt for this reads). In SDXL my images "break" (i.e start looking flat, unrefined or even bizarre) at some point long before I can direct them towards my imagined result. All my usual approaches like reducing CFG, re-ordering prompts, using a variety of qualifierts don't seem to work like I'm used to.
And tbh, I think this has to be expected. These are new models, so we need new toools (prompts) to work with them. I just haven't learned how to do it yet and I'm asking how others do it :)