Model
Trends
.ai
Model
Trends
.ai
the best open source ai models
Run Locally
CoMix_BGXL_V2.safetensors
218 MB · SafeTensor
Downloads are served by Civitai. Some creators ask for a Civitai login first.
AD
Install / Run on Graydient
Requires membership
<comix-bg-xl>
About This Model
STABLE DIFFUSION XL 1.0 · LoRAs
Created by
Fish788
on Civitai
Creator notes
These lora were trained on about 53-160 images from the CoMix Wave films, Your Name, Weathering With You, and Suzume. My goal was to capture the background art style from the films. Most of the images used for training do not contain any characters. There are two main reasons for this. - I really like background art and the background art from these films are some of my favorites. - I wanted to use these lora to improve the backgrounds of the gens for my other loras. I am happy to say I have achieved my goal. It's not perfect, but I hope this lora will bring some life to your gens as well. To get the results you see in the images above, . Visit My Site For Models I Can't Post On CivitAI: Version 3 This version was trained on using 53 images. I’ve been trying to create a new version of this lora ever since V2 but it never came out right. After countless iterations and the introduction of a new model, I’ve finally made a version I feel is a much better reflection of the source images than the versions before it. Version 2 V2 was trained on AutismMix. It was an attempt to increase the density of detail in the background art. What I actually managed to accomplish was make a version with greater prompt comprehension, more detailed and accurate characters and a bit more coherent backgrounds. You can compare the two loras and decide which one you like best. To sum it up, V2 is like V1 but easier to prompt accurate results. Some things to take note with this lora. The tag Scenery is extremely over powering in base Pony. You will struggle to gen characters if you include it in your prompt. The more detail you get with explaining the background, the harder it will become to add characters. You must work with a balance or focus on characters mainly. Prompting accurate backgrounds is a super gatcha in stable diffusion and XL is no exception. V1 was trained on for the ultimate compatibility. Version 1 The V1 includes images using another lora of mine since the 2d style is similar to the film's character art. The rest of the images are just the lora alone. V2 didn't seem to need the extra lora at all. It captured the 2d style all on it's own. Very nice. Even though V1 was trained on Pony, I exclusively use and I recommend you do the same. All of the examples were made with that model. That's all folk, enjoy!
1,777 downloads · 186 likes on Civitai
SHA256
BC75289A12B4B7643EBB7767B39C47BC74EFD94A89E514894C7F19520225CBEC
ModelTrends.ai Model ID
#10070
Flag content
Example renders
Prompts and settings shared by the people who made these renders on Civitai. Pick a render to see how it was made.
Settings
Sampler
DPM++ 2S a
Steps
27
Guidance
7
Seed
3658062096
Size
1664x2432
Clip skip
2
Prompt
(score_9:1.1),score_8_up,score_7_up,score_6_up,source_anime,anime screencap,<lora:CoMix_BGXL_V2:1>,falling,1girl,from side,black hair,school uniform,barefoot,blue eyes,happy,cloud,sky,outdoors,sunset,large cloud,colorful cloud,cloudy sky,colorful sky,blue sky,sunlight,water drop,
Negative prompt
mosaic censoring,bar censor,censored,source_cartoon,source_pony,source_furry,simple background,lipstick,
Settings
Sampler
Euler a
Steps
29
Guidance
7
Seed
477914812
Size
832x1216
Clip skip
2
Weight used
1
Prompt
score_9, score_8_up, score_7_up, score_6_up, 1girl, 25 years old, dark eyes, brown hair, very long hair, twintails, Asian, black shirt, crop top, bare shoulders, long sleeves, midriff, navel, off-shoulder shirt, short shorts, black denim shorts, black thighhighs, holding leaf, autumn, autumn leaves, falling leaves, cowboy shot, dutch angle, lying on back, view from top, happy,
Negative prompt
score_6, score_5, score_4, pony, furry, monochrome, curvy, fat, pubic hair, watermark, artist name, ugly, ugly face, mutated hands, low res, bad anatomy, bad eyes, blurry face, unfinished, sketch, greyscale, (deformed),
Settings
Sampler
Euler a
Steps
29
Guidance
7
Seed
3606068330
Size
832x1216
Clip skip
2
Weight used
1
Prompt
score_9, score_8_up, score_7_up, score_6_up, 1girl, 25 years old, red eyes, white hair, short hair, messy hair, crossed bangs, hair between eye, pointy ears, black choker, glasses, big glasses, hipster, (blue skin), oni, blue oni, red sweater, black skirt, pleated skirt, belt, holding book, reading book, black thighhighs, thighs, night town, autumn, autumn leaves, falling leaves, cowboy shot, depth of field, dutch angle, happy,
Negative prompt
score_6, score_5, score_4, pony, furry, monochrome, curvy, fat, pubic hair, watermark, artist name, ugly, ugly face, mutated hands, low res, bad anatomy, bad eyes, blurry face, unfinished, sketch, greyscale, (deformed),
Settings
Sampler
DPM++ 2S a
Steps
27
Guidance
7
Seed
4040987912
Size
1664x2432
Clip skip
2
Prompt
score_9,score_8_up,score_7_up,score_6_up,source_anime,anime screencap,<lora:CoMix_BGXL_V2:1>,sitting,full body,from behind,looking back,blonde hair,ponytail,blue eyes,light smile,camouflage jacket,jeans,boots,cloud,outdoors,blue sky,sunlight,lake,mountain,rock,campfire,
Negative prompt
mosaic censoring,bar censor,censored,source_cartoon,source_pony,source_furry,simple background,lipstick,
Settings
Sampler
Euler a
Steps
29
Guidance
7
Seed
3769764698
Size
832x1216
Clip skip
2
Weight used
1
Prompt
score_9, score_8_up, score_7_up, score_6_up, 1girl, 25 years old, red eyes, white hair, short hair, messy hair, crossed bangs, hair between eye, pointy ears, black choker, glasses, big glasses, hipster, (blue skin), oni, blue oni, red sweater, night town, autumn, portrait, face focus, detailed face, shy smile, blush
Negative prompt
score_6, score_5, score_4, pony, furry, monochrome, curvy, fat, pubic hair, watermark, artist name, ugly, ugly face, mutated hands, low res, bad anatomy, bad eyes, blurry face, unfinished, sketch, greyscale, (deformed),
Settings
Sampler
Euler a
Steps
29
Guidance
7
Seed
708643822
Size
832x1216
Clip skip
2
Weight used
1
Prompt
score_9, score_8_up, score_7_up, score_6_up, 1girl, 25 years old, red eyes, white hair, short hair, messy hair, crossed bangs, hair between eye, pointy ears, black choker, glasses, big glasses, hipster, blue skin, oni, blue oni, red sweater, black skirt, pleated skirt, belt, black thighhighs, thighs, night town, autumn, autumn leaves, falling leaves, cowboy shot, depth of field, dutch angle, happy, sitting under tree, hugging own legs, holding book, reading book,
Negative prompt
score_6, score_5, score_4, pony, furry, monochrome, curvy, fat, pubic hair, watermark, artist name, ugly, ugly face, mutated hands, low res, bad anatomy, bad eyes, blurry face, unfinished, sketch, greyscale, (deformed),
Settings
Sampler
Euler a
Steps
30
Guidance
4.5
Seed
2233554348
Size
1280x1856
Clip skip
2
Weight used
0.45
Prompt
masterpiece, best quality, amazing quality, detailed sketch, 1girl, solo, mm, twintails,purple hair,brown eyes,anime coloring, white sundress,bare shoulders, expressionless, looking to the side, soft smile,blush,embarrassed,glasses, hands behind back,wind, rooftop,cute face,(askz:0.3),(wlop:0.3),(tomose shunsaku:0.35), hu99y
Negative prompt
bad quality, worst quality, worst detail, sketch, censor, simple background, transparent background, multiple girls, watermark,
Settings
Sampler
DPM++ 2S a
Steps
24
Guidance
7
Seed
474034362
Size
2432x1664
Clip skip
2
Prompt
score_9,score_8_up,score_7_up,score_6_up,source_anime,anime screencap,<lora:CoMix_BGXL_V2:1>,front view,3girls,laughing,happy,smile,blue hair,red hair,green hair,blue eyes,brown eyes,straight hair,parted bangs,twintails,very long hair,large breasts,curly hair,messy hair,short hair,medium hair,small breast,squatting,flower garden,hands on gace,
Negative prompt
mosaic censoring,bar censor,censored,source_cartoon,source_pony,source_furry,simple background,lipstick,
AI Models for Image, Video & Text Generation
comix bg xl is a LoRA for the Stable Diffusion XL 1.0 family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Stable Diffusion XL 1.0 models, check its heat score to see how it is trending, and open it on PirateDiffusion or BitVector to try it.
Browse by Model Family
Browse all models