Legend Of Galactic Heroes (Ginga Eiyuu Densetsu, 1988) style -- LoCon for Pony, LoRA for AnimagineXL 3.1

A style LoRA (a huge LoCon for Pony, a large LoRA for AnimagineXL 3.1) for the original 1988 Legend Of Galactic Heroes show.

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

__

SOME INFORMATION SPECIFIC TO THIS LORA/LOCON:

Primary trigger word is LZGH.

I recommend trying the Pony LoCon with 1) ColorburstXL, 2) LuminaverseXL, 3) Reponygine, and 4) AnimeConfettiComrade (see the "GENERAL INFORMATION" below for more info). Keep in mind that there's non-Pony versions of all of those checkpoints, so be sure to try the Pony ones. Also, all 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.

For the Animagine XL 3.1 LoRA version, I've tested it to work adequately with the AnimagineXL 3.1 base model itself (see "GENERAL INFORMATION" below for more info). Also, all of my testing is with the primary trigger word at the beginning of the positive prompt, plus "masterpiece, best quality, very aesthetic, absurdres" at the end of the positive prompt, plus "worst quality, low quality, jpeg artifacts, lowres, blurry" at the end of the negative prompt.

Characters were tagged with the following trigger words... with some additional features/tags afterwards. I recommend testing just the "MC" character name, and then adding other features as necessary/desired. Also, note that I used some non-standard hair colors (including "bright red hair," "yellow hair," "dark yellow hair," etc). For eyes colors, I usually just let the WDTagger decide, because, in the source material, there were indeed plenty of eye color inconsistencies.

Please note that "specific character likenesses" were never my actual goal. Also, for various reasons, the Pony version will probably give better character likenesses than the Animagine version. And, less common characters (towards the bottom of the list) are usually either "underfit" (mediocre likeness) or "overfit" (difficult to alter the character). That said, most of the character likenesses end up quite good:

MCLohengramm ... yellow hair, military uniform, epaulettes, cape, blue eyes, grey eyes
MCMintz ... light brown hair, brown eyes, beret, uniform, military uniform collared shirt ... and, for adult Julian Mintz, you can try "large chin" (but I admit that I haven't tested it)
MCWen-Li ... dark blue hair, beret, uniform, military uniform, ascot, collared shirt, ascot, jacket ... and you could try "large chin," too, because Yang Wen-Li's appearance wasn't always consistent
MCKircheis ... bright red hair, military uniform
MCJessica ... blonde hair, jewelry, necklace, green eyes
MCFrederica ... golden hair, mullet, light brown eyes, beret, uniform, military uniform, ascot
MCHildegard ... dark blonde hair, mullet, aqua eyes, jewelry, earrings, ascot, formal, suit, brooch, military uniform
MCKaterose ... orange hair, blue eyes, uniform, military uniform, ascot, beret
MCDominique ... red hair, hair over one eye, mole under mouth, green eyes, jewelry, necklace, blue eyes
MCAnnerose ... yellow hair, long hair, blue eyes, jewelry, dress, long sleeves, necklace, brooch, choker
MCOberstein ... brown hair, white bangs, parted hair, blue eyes, military uniform
MCSchonkopf ... dark grey hair, thick eyebrows, brown eyes, uniform, military uniform, jacket
MCRubinsky ... bald, thick eyebrows, turtleneck, jacket, grey eyes, sweater
MCAttemborough ... light aqua hair, freckles, beret, uniform, military uniform, green eyes, ascot
MCPoplin ... light orange hair, green eyes, pilot suit, uniform, military uniform, jacket, blue shirt, ascot, pilot suit, spacesuit, helmet removed
MCMittermeyer ... dark yellow hair, thick eyebrows, military uniform, blue eyes
MCKesler ... brown hair, striped hair, white stripes, brown eyes, military uniform
MCSusana ... aqua hair, makeup, lipstick, jewelry, earrings, green eyes, red lips, circlet, necklace, long hair, braid, dress, gloves, hair bun, single braid, hat, single hair bun, hair over shoulder, ascot
MCCornelia ... dark red hair, jacket, suit, formal, long sleeves, necklace, earrings, jewelry
MCMagdalena ... black hair, purple eyes, choker, jewelry, earrings, dress, makeup, lipstick, hair bow

Note that I used "mullet" for both Frederica and Hildegard's... interesting hairstyles.

"Helmet, astronaut, spacesuit, pilot suit" can produce the orange/white spacesuits worn during combat.

_______

SOME GENERAL INFORMATION ABOUT ALL OF MY LORAS/LOCONS:

Sorry about the lack of image generation data. I'm going to work on uploading images with generation data when I have time/energy. In the meantime, I can tell you:

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 don't inpaint! 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). Putting the primary trigger word at the end seems to be more important to play with when using AnimagineXL 3.1 with the LoRAs. 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).

___


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) 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!

_

GENERAL INFORMATION FOR MY ANIMAGINE XL 3.1 LORAS:

My testing was all done with "masterpiece, best quality, very aesthetic, absurdres" at the end of the positive prompt, and "worst quality, low quality, jpeg artifacts, lowres, blurry" at the end of the negative prompt. If necessary, I put the primary trigger word at the very, very, very end of the positive prompt, after all quality tags.

The LoRA should work fine with the AnimagineXL 3.1 base model at 1.0 strength or a little below. You can use AnimaPencil if you want to try a 2.5D look, but you'll be sacrificing quite a bit of the overall style.

Let us all know if you find any other checkpoints that work well with the LoRA!

Also, I've heard that AnimagineXL 3.1 supports a shit-load of artist tags, so if you're adventurous, you could try combining with those... but I haven't investigated that yet.

|___

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.

My AnimagineXL 3.1 LoRAs are also quite large, but more standard. I trained them as regular LoRAs instead of LoCons because I've always had weird results training/testing my style LoRAs/LoCons on AnimagineXL (going all the way back to AnimagineXL 2.0), and keeping things simpler seems to work better. Note that I don't release the AnimagineXL 3.1 LoRA versions unless they work OK, so if one is missing, that's why. I plan on troubleshooting that later, but for now, I'm trying to work through uploading my backlog!

I keep training datasets identical for both the Pony and Animagine versions. If there are any minor differences, I will make a note of that in the "specific information" section closer to the top of this page. (Major dataset changes will be noted by the version numbers, like "Pony-V1" versus "Pony-V2," and "ANXL3.1-V1" and "ANXL3.1-V2")

__

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.