, electric pokemon, rabbit, yellow body, (masterpiece), high quality, best quality, high-definition, ultra.jpeg)
, pokemon _(creature_), , salamence, charizard mega X, solo, open mouth, simple background, full body, win.jpeg)
, ghost and ground pokemon _(creature_), full body, gengar, marowak, solo, grin, half-closed eye, happy,.jpeg)
, megumin, 1girl, bare shoulders, black hair, black cape, black gloves, blush, cape, choker, collarbone, d.jpeg)
, fire pokemon, lizard, full body, no humans, claws, white background, red body, ((masterpiece)).jpeg)
, 1girl, black hair, breasts, dark-skinned female, dark skin, freckles, grin, long hair, naranja academy s.jpeg)
, grass and water pokemon, fox, full body, no humans, claws, white background, blue body, ((masterpiece)).jpeg)
, bulbasaur, solo, looking at viewer, smile, open mouth, flower on back, red eyes, full body, _d, no human.jpeg)
, 1girl, breasts, green eyes, mint green hair, twin_braids, white shirt, flower necktie, white beret, skir.jpeg)
, ghost and ground pokemon _(creature_), full body, gengar, marowak, solo, grin, half-closed eye, happy,.jpeg)
, pokemon _(creature_), (venusaur), cobalion, solo, looking at viewer, simple background, brown eyes, clos.jpeg)
, fire pokemon, charizard and dragonite mix, full body, no humans, claws, white background, red body, ((m.jpeg)
, 1girl, bag, black hair, breasts, creatures _(company_), dark-skinned female, dark skin, fingerless glove.jpeg)
, electric and steel pokemon, (masterpiece), high quality, best quality, high-definition, ultra-detailed,.jpeg)
, electric pokemon, rabbit, yellow, (masterpiece), high quality, best quality, high-definition, ultra-deta.jpeg)
Type | |
Stats | 12,455 131,543 |
Reviews | |
Published | May 18, 2023 |
Base Model | |
Hash | AutoV2 8510EFEB67 |
Pokemon LoRA (Ken Sugimori style for Pokemon and trainers)
Making models can be expensive. Do you like what I do? Consider supporting me on Patreon 🅿️ or feel free to buy me a coffee ☕
V3 UPDATE: trained on all Pokemon currently released or announced as of today (all the ones until S/V and some of the DLC ones that have been announced).
V3 CAPTION STYLE UPDATE: trained on all Pokemon currently released or announced and their Bulbapedia descriptions (shortened using ChatGPT). Read "About this version" on the right for more.
This started out as a fun experiment. I know there is already a Pokémon style model which is decently good, but I wanted to see how things could work with a LoRA instead. For v1 I didn't pay much attention to the dataset, but the result was still better than I expected, so I made a v2 which is much more consistent and can also do Pokémon characters and style in general.
V3 is offset and should be used at weight 1.
V1 and V2 trigger words are sugimori ken \(style\), pokemon \(creature\) (optional if you don't want to make humans) and all Pokémon names until XY (plus some more).
I've used it with AnyLoRA at 0.5 or 0.6 weight. Also use CLIP skip 2 and remember to generate relatively small images (max 768 w/h) and then upscale.
V2 was trained on like 800+ characters inside (up to XY + some random recent ones and many human characters), it cannot replicate characters perfectly, but it's still god enough to make Pokémon fusions (like Blastoise + Venusaur in the examples), especially with inpainting as a guide (which I didn't use for the examples). It's also good at creating completely new Pokémon and trainers. Use no humans, pokemon \(creature\) if you want to create Pokémon only.
How to use LoRA's in auto1111:
Update webui (use
git pulllike here or redownload it)Copy the file to
stable-diffusion-webui/models/loraSelect your LoRA like in this video
Make sure to change the weight (by default it's
:1which is usually too high)