Yes, you are right! It is weird, because the interface looks exactly the same as of Stable Diffusion and it is the first result you get if you search it with DuckDuckGo. Fell for that one.
I mean, the rules are all self-imposed here – OP was just suggesting not using anything other than the username to see what comes up. If you want something with a bit of flash, it’s definitely doable. You can also do a batch and grab the one you like the most – I’ve a self-imposed rule that I’ve just been using a fixed seed rather than doing a batch of 20 or so and taking the best, just in the spirit of the game. If the goal is a really neat image, then that batching is normally what one would do. Some of the other people are definitely doing a batch and taking their favorite.
Really nice! I like most of them, actually. I think the comic book ones are the best. Thank you and also thanks for the explanation. I have not that much experience with generating images yet. This definitely helps!
You’re probably not seeing a particularly broad set of examples of what could be done; I happen to be a real sucker for intense light-on-dark hand-drawn stuff, so it’s just a random sprinkling of some of the presets that I happen to have sitting around for my own use and like the look of.
Another suggestion: I’m not familiar with StableDiffusionWeb, which is apparently what you’re using, but I would assume that it’s internally using Stable Diffusion and some model. If you look at civitai.com, you can see a metric ton of images that people have generated…and also the prompts that they used to achieve those effects. Some of those won’t be using the standard model – they’ll be trained on other images – so you won’t get exactly the same impact, but usually the prompts are still a solid place to start.
Fairy tale fairy tale|gothic, natural skin texture, (full body:1.4), enchanted glade, lighting by flying fireflies, tree branches alive with dancing neon leaves, a beautiful woman wearing a white chiffon dress, crystal shoes, jewelry, lips, medium, open, sensitive, sleeveless, solo, sundress, teeth, thighs, wind, a swirling tornado around her, paint explosion splatter, <lora:SDXLPaintSplash:0.7> paint splatter <lora:DetailedEyes_V3:1> <lora:add-detail-xl_2:1> . Magical, fantastical, enchanting, storybook style, highly detailed
Okay, that’s using a nonstandard model and some LoRA models – which are like little models, that add on effects. I haven’t downloaded those LoRA models, and I assume you won’t have them available. So we aren’t going to get exactly the same effect. But…let’s try tacking the non-LoRA prompt stuff onto your username. Maybe pull off a couple of parameters…maybe take off one or two to make it just a bit less revealing…
Shelena, Fairy tale fairy tale|gothic, natural skin texture, (full body:1.4), enchanted glade, lighting by flying fireflies, tree branches alive with dancing neon leaves, a beautiful woman wearing a white chiffon dress, crystal shoes, jewelry, medium, open, sensitive, sleeveless, solo, sundress, wind, a swirling tornado around her, paint explosion splatter, paint splatter . Magical, fantastical, enchanting, storybook style, highly detailed
And that required me I dunno, maybe three minutes for looking at the websites and trying a couple images and copying the prompt, and at one point in there my web browser crashed, which counted towards those three minutes. I’m not particularly advocating for that as an end image, just pointing out the knobs that are available.
That is really cool! Thank you so much. I have been thinking about trying this stuff for a while and this is some really good advise to get started. Cannot wait to try it. Thanks!
Why is mine so boring? :-(
Here’s a few more. I hope you like one of them.
The normal model.
The niji(anime) model
Cool! I like both of them, but if I have to choose, I like the first one best. I really like flowers! :-)
Glad you like it! :)
I suspect the website you use is fake, i have seen a lot of images similar to this
Yes, you are right! It is weird, because the interface looks exactly the same as of Stable Diffusion and it is the first result you get if you search it with DuckDuckGo. Fell for that one.
We can cheat a bit, give it some style hints, if you don’t want a photograph-looking thing:
I mean, the rules are all self-imposed here – OP was just suggesting not using anything other than the username to see what comes up. If you want something with a bit of flash, it’s definitely doable. You can also do a batch and grab the one you like the most – I’ve a self-imposed rule that I’ve just been using a fixed seed rather than doing a batch of 20 or so and taking the best, just in the spirit of the game. If the goal is a really neat image, then that batching is normally what one would do. Some of the other people are definitely doing a batch and taking their favorite.
Really nice! I like most of them, actually. I think the comic book ones are the best. Thank you and also thanks for the explanation. I have not that much experience with generating images yet. This definitely helps!
You’re probably not seeing a particularly broad set of examples of what could be done; I happen to be a real sucker for intense light-on-dark hand-drawn stuff, so it’s just a random sprinkling of some of the presets that I happen to have sitting around for my own use and like the look of.
Another suggestion: I’m not familiar with StableDiffusionWeb, which is apparently what you’re using, but I would assume that it’s internally using Stable Diffusion and some model. If you look at civitai.com, you can see a metric ton of images that people have generated…and also the prompts that they used to achieve those effects. Some of those won’t be using the standard model – they’ll be trained on other images – so you won’t get exactly the same impact, but usually the prompts are still a solid place to start.
So, to take a random example:
https://civitai.com/images/2680672
Okay, that’s using a nonstandard model and some LoRA models – which are like little models, that add on effects. I haven’t downloaded those LoRA models, and I assume you won’t have them available. So we aren’t going to get exactly the same effect. But…let’s try tacking the non-LoRA prompt stuff onto your username. Maybe pull off a couple of parameters…maybe take off one or two to make it just a bit less revealing…
And that required me I dunno, maybe three minutes for looking at the websites and trying a couple images and copying the prompt, and at one point in there my web browser crashed, which counted towards those three minutes. I’m not particularly advocating for that as an end image, just pointing out the knobs that are available.
That is really cool! Thank you so much. I have been thinking about trying this stuff for a while and this is some really good advise to get started. Cannot wait to try it. Thanks!
shelena
Steps: 20, Sampler: DPM++ 3M SDE Karras, CFG scale: 7, Seed: 3150620848, Size: 768x1280, Model hash: 74dda471cc, Model: realvisxlV20_v20Bakedvae, Clip skip: 2, RNG: CPU, Version: v1.6.0
Does not look like me at all, but very realistic!