Vampire Hunter D (1985) style -- LoCon for Pony -- Beta V1版本VampHuntD-Pony-V1 (ID: 487221) 综合资源合集综合资源合集

A huge Pony style LoCon for the 1985 Vampire Hunter D OVA film.

The main reason that I'm calling this a beta version is that, despite tagging each character with their own unique name, negative prompts are still often necessary to prevent some characters' features from showing up. I personally find this pretty manageable, but I'm the guy who made the LoCon!

Maybe lowering the strength will make things work perfectly to your tastes? All of my testing was at strength 1.0, with the trigger word at the very start of the prompt. Maybe I am being too picky/stubborn about getting all of my LoCons to work at "full strength."

More information below. But in general, be prepared to do some negative prompting, some "rerolling," and maybe a little bit of inpainting in order to get some features correct (like the red gem on D's hat). I did not do any inpainting on the sample images, so they should give you a good idea of what to expect.

A quick plug: I have other classic anime style LoRAs/LoCons. Check out https://civitai.com/user/SweetRammaJamma!

SOME INFORMATION SPECIFIC TO THIS PONY LOCON:

Primary trigger word is VHD85.

Characters were tagged with the following (please keep in mind that character likenesses are NOT guaranteed, especially as you get lower on the list):

MCDhampir (as in, the title character, D)
MCDoris (the main female character, and by far the most common "1girl")
MCLee (as in, the main villain, Count Lee)
MCDan (Doris' little bother)
MCRei (D's main nemesis)
MCLarmica (the main female vampire)
MCGreco (the blonde dude who wants to fuck Doris)
MCFerringo (the doctor)
MCSnakeSisters (the snake sisters from the cave under the castle)
MCCarbuncle (D's talking hand)
MCGolem (the giant golem monster guy)
MCGimlet (the annoying flying purple guy)
MCOldWitch (the small orange-haired witch lady)
MCGhostCat (yes, I tagged the ghost cat that D fought in the castle)
MCMessenger (the purple-cloaked messenger that gives the special candle to Rei)
MCChuula (the green goblin guy who seems to exist for the sole purpose of getting bisected by D)

Also, D's hat was tagged with "wide-brimmed hat, black headwear." This generally works OK, and the hat can be applied to any 1boy or 1girl. And you can even change the color of the hat (for example, "wide-brimmed hat, white headwear"). But the major problem is that the LoCon doesn't know where to put the hat's red gem... Unless you also use the tag MCDhampir. Which means that the LoCon associates a lot of the hat's details with "MCDhampir," and not just "wide-brimmed hat, black headwear." This makes perfect sense, because D is the only character in the dataset who wears that hat, and there's barely any images of him not wearing the hat. So to get this LoCon out of beta, I'll try to figure out if adding "red gem," "gem on hat" (etc etc) could help to separate details of D's hat from "MCDhampir." Switching from "wide-brimmed hat" to "witch hat" might help, too. We'll see.

In general, prepare for your 1girls to look somewhat like Doris, even if you don't use the "MCDoris" tag. Notably, clothing will default to blue, and some blue clothing might show up even if you're very specific in your positive prompting. So I recommend putting "blue clothing, green clothing" in the negative prompt unless you're trying to get blue clothing and/or green clothing.

Some other features will seem overfit, too -- like Larmica's red "earmuffs." But, I'm providing the earliest epoch that reliably produces the correct shape of D's hat. The difficulty in getting D's hat correct is a sign to me that overfitting will have to be addressed through additional tagging, plus careful manipulation of image repeats.

Overall, I think everything's pretty good, given the limited, repetitive images that I had to work with. We'll see if I can substantially improve things in the future -- but for now, I'm trying to release my other LoRAs/LoCons.

All of my testing was on ColorburstXL, and all of the current sample images are from ColorburstXL.

IN GENERAL, FOR PONY CHECKPOINTS, TRY: 1) ColorburstXL, 2) LuminaverseXL, 3) Reponygine, and 4) "Prototype" (see the "GENERAL INFORMATION" below for more info, as well as "RECOMMENDED RESOURCES" at the bottom). Keep in mind that there's non-Pony versions of some of those checkpoints, so be sure to get the Pony ones. Also, most of my testing is with "primarytriggerword, score_9, score_8_up, score_7_up, score_6_up, source_anime" at the beginning of the positive prompt, so try that first.

_______

SOME GENERAL INFORMATION ABOUT ALL OF MY LORAS/LOCONS:

To generate the sample images, I don't use outside LoRAs. As in, I only use the checkpoints plus my own LoRA/LoCon. I don't use embeddings, either. So the sample images are very "pure/simple."

I use ComfyUI only, so my image generation methods might be different from what's typical with Automatic1111 or CivitAI's online generator. Notably, I can't inpaint in the STRAIGHTFORWARD/POWERFUL/EASY Automatic1111 way! If things get too weird, I usually just "roll the dice" again! But chances are good that inpainting will be an asset to you, especially for things like getting eyes that are 100% stylistically correct.

99% of my testing is with Euler A, at 25-30 steps, CFG 6-7, with the LoRA/LoCon at strength 1.0, and with the trigger word at the very start of the positive prompt. I test both latent upscaling (1.25x to 1.5x, 0.60-0.65 denoise, ~12 steps) and "regular" upscaling. I've tested face detailers, too. All of it works appropriately, but some typical "light troubleshooting" will be required if you're going for a specific output.

I do upscale my sample images quite a bit. Usually, it's latent upscaling first, then an additional pass with "regular" upscaling at about 1.5x. I usually resize with boring old Lanczos, and not "model upscalers" (such as AnimeSharp4X), because Lanczos resizing ends up more faithful to the original anime's style -- but really, I do whatever works.

In regards to upscaling and YOU: Don't be surprised if something like my Guyver OVA LoCon gives you gritty/grainy initial results. Experimentation is required. And it varies from LoRA to LoRA -- for example, FLCL is a nice-looking and somewhat modern anime, so it doesn't have the same problems as the Guyver OVAs.

Where you put the trigger word does matter, and (the trigger word's weight:1.2) does affect things. So to decrease the "faithfulness/literalness" of the style, put the trigger word all the way at the end, and (decrease its weight:0.5). Of course, you can play with the weight of <the actual LoRA/LoCon:0.8>, but I tried to ensure that things work reasonably at 100% strength. (If my LoRAs/LoCons are totally unusable at 1.0 strength, I simply don't release them! I find another way to re-train them!)

For both Pony and Animagine, I try "simple background, gradient background" in the negative prompt. This does seem to help with the typical boring backgrounds of SDXL anime models, and it might help more than usual in cases where a LoRA/LoCon is based on an anime that has many boring/simple backgrounds (FLCL comes to mind).

In general, my prompts are uncreative. I just use wildcards -- which is partly why, if you look at the image generation data, you'll see some "dead weight" words that don't seem to be doing anything. Also, I'm very lazy, and I don't even bother removing tags like "worst quality, low quality" when switching from AnimagineXL to Pony. So, I gave you my actual prompts in the image generation data... but don't assume that my prompts are worth imitating.

___

GENERAL INFORMATION FOR MY PONY LOCONS:

My Pony testing was all done with pretty standard quality tags in the positive prompt, in the form of "primary trigger word, score_9, score_8_up, score_7_up, score_6_up, source_anime," so I can guarantee that those work, but feel free to experiment!

For checkpoints to combine with this Pony LoCon at 1.0 strength, I recommend starting with the following (which are in the "Recommended Resources" at the bottom of the page):

1) ColorburstXL (Pony), because it produces "faithful style" while still being more consistent and aesthetically pleasing than the base Pony model. Then, maybe try...
2) Luminaverse (Pony) will get you something more "modern" while still being quite faithful to the LoCon.
3) Reponygine (Pony) will get you something quite "modern and pleasant," while still retaining good core style features (like eyes and hair details) and character likenesses.
4) "Prototype" (Pony). I don't quite know how to describe the look yet, but it works well.
5) AnimeConfettiComrade (Pony), IF you want a MORE "literal" interpretation of the LoCon, while still being more consistent than the base Pony model.

You CAN use this Pony LoCon with the base Pony model, but the style might be overpowering, and you may have to lower the LoCon's strength a fair bit below 1.0, and/or move the trigger word to the end of the positive prompt, and/or reduce the strength of (the trigger word:0.1) -- which are all the same ways that you'd adjust the strength with other checkpoints, of course. Adjust to your taste, always :) And, there are many more Pony-based checkpoints that I haven't even tried, so if you find one that works well with this LoCon, please let us all know!

Yes, my filenames are long. It's because I personally use LoRA filenames to quickly compare different versions of my LoRAs while testing things. I recommend renaming the file to your tastes! Though it would make sense to leave the primary trigger word in the filename, right? (It's up to you!)

Yes, my Pony LoCons are extraordinarily large. But I made them for myself, and, to quote my genius friend, "it works for me and what I do." If you try these Pony LoCons, and you've made some SDXL style LoRAs/LoCons that you like, I would be happy to discuss training settings with you.

No warranty, express or implied.

I place no special restrictions on what you may do with these .safetensors files. Likewise, I am not responsible for anything that you do with them.