Tensor.Art
Create

Final Fantasy VII Remake Style (Unreal Engine 4) L

LORA
Original


Updated:

blur image
622896122215723048
blur image
ff7r style, aerith gainsborough, 1girl, solo, realistic, green eyes, brown hair, long hair, blurry, looking at viewer, red jacket, jewelry, blurry background, necklace, choker, jacket, portrait, lips, ribbon, hair ribbon, bow, nose, closed mouth , ((masterpiece)) <lora:ff7r_style_ned_offset:1>
  • ff7r style, aerith gainsborough, 1girl, solo, realistic, green eyes, brown hair, long hair, blurry, looking at viewer, red jacket, jewelry, blurry background, necklace, choker, jacket, portrait, lips, ribbon, hair ribbon, bow, nose, closed mouth , ((masterpiece)) <lora:ff7r_style_ned_offset:1>
  • 622896122215723048
  • ff7r style, tifa lockhart, 1girl, thick lips, arm up, armpits, artist name, belt, black hair, breasts, red eyes, cleavage, closed mouth, collarbone, cowboy shot, crop top, earrings, elbow gloves, elbow pads, gloves, jewelry, large breasts, lips, long hair, low-tied long hair, midriff, navel,   indoors, skirt, smile, solo, stomach, suspenders, tank top, upper body, ((masterpiece)) <lora:tifa_lockhart:0.2> <lora:ff7r_style_ned_offset:1>
  • ff7r style, 1girl, solo, armor, jewelry, earrings, brown hair, shoulder armor, headband, brown eyes, red headband, looking at viewer, chainmail, lips, breastplate, upper body, pauldrons, bodysuit, realistic, boobplate, short hair, smile, braid<lora:ff7r_style_ned_offset:1>
  • ff7r style, hatsune miku,1girl, bare shoulders, blue eyes, blue hair, blue necktie, blush, breasts, closed mouth, detached sleeves, from side, headphones, long hair, long sleeves, looking at viewer, looking to the side, necktie, number tattoo, shirt, shoulder tattoo, simple background, small breasts, solo, tattoo, twintails, upper body, very long hair, white background, white shirt, ((masterpiece))<lora:ff7r_style_ned_offset:1>
  • ff7r style, tifa lockhart,1girl, solo, long hair, earrings, jewelry, red eyes, black hair, looking at viewer, realistic, blurry, parted lips, blurry background, tank top, swept bangs, lips, portrait, suspenders, bare shoulders, brown eyes, bangs, ((masterpiece))<lora:ff7r_style_ned_offset:1>
  • ff7r style,nanakusa nazuna, 1girl, bangs, black background, black jacket, black shirt, black shorts, blue eyes, blunt bangs, breasts, cleavage cutout, clothing cutout, crop top, eyeshadow, fangs, gradient hair, grey hair, hair rings, jacket, light purple hair, looking at viewer, makeup, multicolored hair, navel, open mouth, red eyeshadow, shirt, shorts, sleeveless, sleeveless turtleneck, sleeveless turtleneck crop top, small breasts, solo, stomach, turtleneck, turtleneck crop top, two-tone hair, vampire <lora:nanakusa_nazuna_offset:0.6><lora:ff7r_style_ned_offset:1>
  • ff7r style,long hair, male focus, solo, 1boy, shoulder armor, armor, blurry background, blurry, green eyes, closed mouth, realistic, smile, black jacket, looking at viewer, jacket, grey hair, bangs, upper body, portrait, pauldrons, white hair, ((masterpiece))<lora:ff7r_style_ned_offset:1>

UPDATE: Retrained on NED.

  • For v1 a weight around 0.65 works fine from my tests. Triggers with ff7r style.

  • For NED version use weight 1 on Never Ending Dream (v1.0). Triggers with ff7r style. I'll maybe train another one on NED 1.22 to make it accurate on that one too.

Also this came up kind of biased towards FF7 characters, so while this is mainly a style LoRA, it could replicate characters from the main cast of the game fairly well without embeddings or additional LoRA.

V1 original description: This is kind of experimental. I wanted to see if I could finetune an anime model to replicate the style of a game in Unreal Engine. I think this was kind of a success. It works on AbyssOrangeMixV2 with a normal negative prompt, or on AnyLoRA with my usual negative prompt with negative embeddings (but don't mix them up, as that neg prompt doesn't work well on AOM with this LoRA). See the examples for the various comparisons.

14,296
Runs
16
Downloads
Uploaded
Base ModelSD 1.5
Trigger Words
For v1 a weight around 0.65 works fine from my tests. Triggers with ff7r style. For NED version use weight 1 on Never Ending Dream (v1.0). Triggers with ff7r style. I'll maybe train another one on NED 1.22 to make it accurate on that one too. Also this came up kind of biased towards FF7 characters, so while this is mainly a style LoRA, it could replicate characters from the main cast of the game fairly well without embeddings or additional LoRA. V1 original description: This is kind of experimental. I wanted to see if I could finetune an anime model to replicate the style of a game in Unreal Engine. I think this was kind of a success. It works on AbyssOrangeMixV2 with a normal negative prompt, or on AnyLoRA with my usual negative prompt with negative embeddings (but don't mix them up, as that neg prompt doesn't work well on AOM with this LoRA). See the examples for the various comparisons. How to use LoRA's in auto1111: Update webui (use git pull like here or redownload it) Copy the file to stable-diffusion-webui/models/lora Select your LoRA like in this video Make sure to change the weight (by default it's :1 which is usually too high)
  • Download the model file

  • Use without crediting

  • Share merges of this model

  • Use different permissions on merges

Commercial use: None

Comments

Related Posts