tal

https://www.military-ranks.org/decorations

https://en.wikipedia.org/wiki/List_of_naval_battles

Most recent three entries as an example:

• August 21, 2024: 21 August - In Red Sea, the Greek flagged tanker Sounion was attacked and exchanged gunfire with two Houthi manned fast attack craft. The Sounion was then hit by three projectiles and set afire before being abandoned by its crew.

https://en.wikipedia.org/wiki/Attacks_on_the_Sounion

Two Houthi fast attack craft engaged in a firefight with the Sounion armed guards before three projectiles struck the tanker.

Sounds like that may have been small arms, if armed guards were involved. There was a subsequent boarding action.

• 15 July, 2024 - In the Red Sea, the Panamaninan flagged tanker Bentley-I is unsuccessfully attacked by a Houthi sea drone before engaging in a gun battle with two Houthi manned fast attack craft, which are driven off.[29]

I assume that the sea drone attempted to ram. The attack craft were using guns.

• 5 March, 2024 – Sinking of the Sergey Kotov – Russian Bykov-class patrol ship, RFS Sergey Kotov is attacked and sunk by Ukrainian sea drones in the Kerch Strait.[28]

Probably ramming.

We may, surprisingly-enough, be at more of a knife-fight range than we have for a long time in naval combat, though I suppose one could argue that maybe USVs should be thought of as more like long-range torpedoes or something than watercraft.

6900

kagis

If that's 16GB, that should be more than fine for SDXL.

So, I haven't done much with the base Stable Diffusion XL model. I could totally believe that it has very little Sailor Moon training data. But I am confident that there are models out there that do know about Sailor Moon. In fact, I'll bet that there are LoRAs -- like, little "add-on" models that add "knowledge" to a checkpoint model on Civitai specifically for generating Sailor Moon images.

Looks like I don't have vanilla SDXL even installed at the moment to test.

downloads vanilla

Here's what I get from vanilla SDXL for "Sailor Moon, anime". Yeah, doesn't look great, probably isn't trained on Sailor Moon:

Sailor Moon, anime
Steps: 20, Sampler: DPM++ 2M, Schedule type: Karras, CFG scale: 7, Seed: 2, Size: 1024x1024, Model hash: 31e35c80fc, Model: sd_xl_base_1.0, Token merging ratio: 0.5, Version: v1.9.4-169-ga30b19dd

searches civitai

Yeah. There are. Doing a model search just for SDXL-based LoRA models:

https://civitai.com/search/models?baseModel=SDXL%201.0&modelType=LORA&sortBy=models_v9&query=sailor%20moon

75 results for ‘sailor moon’

goes to investigate

Trying out Animagine, which appears to be a checkpoint model aimed at anime derived from SDXL, with a Sailor Moon LoRA that targets that to add Sailor Moon training.

I guess you were going for an angelic Sailor Moon? Or angelic money, not sure there...doing an angelic Sailor Moon:

Doing a batch of 20 and grabbing my personal favorite:

(masterpiece, best quality, very aesthetic, ultra detailed), intricate details, 4k, aausagi, long hair, double bun, twintails, hair ornament, parted bangs, tiara, earrings, blue eyes, heart choker, blue sailor collar, red bow, white shirt, see-through, elbow gloves, white gloves, multicolored skirt, white skirt, lora:sailor_moon_animaginexl_v1:0.9, standing, angel, halo

Negative prompt: (worst quality, low quality, very displeasing, lowres), (interlocked fingers, badly drawn hands and fingers, anatomically incorrect hands), blurry, watermark, 3d

Steps: 30, Sampler: Euler a, Schedule type: Automatic, CFG scale: 7, Seed: 11, Size: 1024x1024, Model hash: 1449e5b0b9, Model: animagineXLV31_v30, Token merging ratio: 0.5, Lora hashes: "sailor_moon_animaginexl_v1: e658577df088", Version: v1.9.4-169-ga30b19dd

Time taken: 8 min. 18.0 sec. (to do a batch of 20, and with 30 steps, whereas I typically use 20...used 30 because the LoRA example image did, don't wanna go experiment a bunch).

I grabbed some of those prompt terms from the example images for the Sailor Moon LoRA on Civitai. Haven't really tried experimenting with what works well. I dunno what's up with those skirt colors, but it looks like the "multicolored skirt, white skirt" does it -- maybe there are various uniforms that Sailor Moon wears in different series or something, since it looks like this LoRA knows about them and can use specific ones, as they have those different skirts and different prompt terms on the example images.

I just dropped the Animagine model in the models/Stable-diffusion directory in Automatic1111, and the Sailor Moon Tsukino Usagi LoRA in the models/Lora directory, chose the checkpoint model, included that <lora:sailor_moon_animaginexl_v1:0.9> prompt term to make the render use that LoRA and some trigger terms.

That's 1024x1024. Then doing a 4x upscale to a 16GB 4096x4096 PNG using SwinIR_4x in img2img using the SD Ultimate Upscale script (which does a tiled upscale, so memory shouldn't be an issue):

The above should be doable with an Automatic1111 install and your hardware and the above models.

EDIT: On Civitai, when you view example images, you can click the little "i" in a circle on the image to view what settings they used to create them.

EDIT2: It looks like the same guy that made a LoRA for Sailor Moon also did LoRAs for the other characters in her series, so if you want, like, training on Sailor Mars or whatever, looks like you could grab that and also add knowledge about her in.

Well, for me, the selling points are:

• Versus earlier versions of USB, it's reversible. This isn't a game changer, I guess, but it's definitely nice to not have to fiddle plugs around all the time.

• I don't know if it's the only form of USB that does USB PD -- I'd guess not -- but in practice, it seems to be pretty strongly associated with USB PD. Having USB PD isn't essential, but it makes charging larger devices, like laptops, a lot more practical. I can lug around a power station that doesn't need to have an embedded inverter.

I still feel that it's kind of physically small and weak compared to USB A. That's an okay tradeoff for small portable devices that don't have the space for larger connectors, but I'm kinda not enthralled about it on desktop. I worry more about bending connectors (and I have bent them before).

So for me, I'd say that it's definitely nice, but not really in a game changing sense. I could do the things it can do in somewhat-worse ways prior to USB-C.

Thanks for trying it out! Both the inpainting and outpainting -- the expansion -- worked better than I'd expected, though I dunno if that's exactly what M0oP0o's after.

Lots of odd artifacting, slow creation time and yes it had some issues with sailormoon.

It probably isn't worth the effort for most things, but one option might also be -- and I'm not saying that this will work well, but a thought -- using both. That is, if Bing Image Creator can generate images with content that you want but gets some details wrong and can't do inpainting, but Midjourney can do inpainting, it might be possible to take a Bing-generated image that's 90% of what you want and then inpaint the particular detail at issue using Midjourney. The inpainting will use the surrounding image as an input, so it should tend to try to generate similar image.

I'd guess that the problem is that an image generated with one model probably isn't going to be terribly stable in another model -- like, it probably won't converge on exactly the same thing -- but it might be that surrounding content is enough to hint it to do the right thing, if there's enough of that context.

I mean, that's basically -- for a limited case -- how AI upscaling works. It gets an image that the model didn't generate, and then it tries to generate a new image, albeit with only slight "pressure" to modify rather than retain the existing image.

It might produce total garbage, too, but might be worth an experiment.

What I'd probably try to do if I were doing this locally is to feed my starting image into the thing to generate prompt terms that my local model can use to generate a similar-looking image, and include those when doing inpainting, since those prompt terms will be adapted to trying to create a reasonably-similar image using the different model. On Automatic1111, there's an extension called Clip Interrogator that can do this ("image to text").

Searching online, it looks like Midjourney has similar functionality, the /describe command.

https://docs.midjourney.com/docs/describe

It's not magic -- I mean, end of the day, the model can only do what it's been trained on -- but I've found that to be helpful locally, since I'd bet that Bing and Midjourney expect different prompt terms for a given image.

Oh I also tried local generation (forgot the name) and wooooow is my local PC bad at pictures (clearly can’t be my lack of ability it setting it up).

Hmm. Well, that I've done. Like, was the problem that it was slow? I can believe it, but just as a sanity check, if you run on a CPU, pretty much everything is mind-bogglingly slow. Do you know if you were running it on a GPU, and if so, how much VRAM it has? And what you were using (like, Stable Diffusion 1.5, Stable Diffusion XL, Flux, etc?)

@M0oP0o@mander.xyz, as far as I can tell, you always use Bing Image Creator.

And as far as I can tell, @Thelsim@sh.itjust.works always uses Midjourney.

I don't use either. But as far as I know, neither service currently charges for generation of images. I don't know if there's some sort of different rate-limit that favors one over the other, or another reason to use Bing (perhaps Midjourney's model is intentionally not trained on Sailor Moon?), but I do believe that Midjourney can do a few things that Bing doesn't.

One of those is inpainting. Inpainting, for those who haven't used it, lets one start with an existing image, create a mask that specifies that only part of the image should be regenerated, and then regenerate that part of the image using a specified prompt (which might differ from the prompt used to generate the image as a whole). I know that Thelsim's used this feature before with Midjourney, because she once used it to update an image with some sort of poison witch image with hands over a green glowing pot, so I'm pretty sure that it's available to Midjourney general users.

I know that you recently expressed frustration with Bing's Image Creator's current functionality, wanted more.

Inpainting's time-consuming, but it can let a lot of images be rescued, rather than having to just re-reroll the whole image. Have you tried using Midjourney? Was there anything there that you found made it not acceptable?

Relevant username.

Back under Boris Johnson, Dominic Cummings was a very vocal advocate of the UK setting up something similar (though he referenced ARPA, DARPA's predecessor, which wasn't explicitly-military).

The result of that was ARIA being set up last year.

He was also very interested in advanced artificial intelligence work, so I kind of imagine that funding that was a goal.

https://www.aria.org.uk/

I don't know if all their work is public, but looking at that website, it looks like they're publicly working on:

• Genetic engineering of plants

• Robot dexterity

• Analysis of "tipping points" caused by climate change

• Safeguarded AI research (how to "contain" advanced artificial intelligences)

Aww. Thanks for doing the research, though!

These are indeed gay times we live in.

it's just ComfyUI behaving this way. Nothing is loaded, no LLMs

Oh, okay, then I'm probably wrong on VRAM, then. On my system, it needs to actually run the nodes before the VRAM gets allocated. Sorry! I thought I had it...