Run Locally
face_strong_sevenof9.safetensors
435 MB · SafeTensor
Downloads are served by Civitai. Some creators ask for a Civitai login first.
About This Model
STABLE DIFFUSION XL 1.0 · LoRAs
Creator notes
I found that images generated with my LoRA appear bit more amateur and less like the puppy "model_flux" style.
In Better Faces, I aimed to include a diverse range of cultures and ethnicities—15 if I remember correctly—with both young and old subjects, currently focusing on women.
aborigines, african, arab, arctic, brazilian, chinese, egyptian, finish, german, havaiian, indian, japanese, mongolian, russian, western
my FLUX-lora responds to age prompts like __yo for 20yo, 30yo, 40yo.
Weight: start with 0.3
look image post for more, i was curious also negativ has an impact^^
V........... see below ..............V
Try my other face expression LoRA. If you use it at a weight of only 0.4 (without trigger words), you'll achieve more realistic results.
I aim for realistic faces with natural skin, avoiding perfect symmetry. :)
FLUX with Euler-Sampler and SGM-Uniform-Scheduler performs well at -> 15-25 Steps
Trigger words aren't essential but are useful for specifying cultural features! and "yo" ;)
Model Descriptions:
FLUXV3: new image set, new caption, 15 cultures, no permission to merge!
FLUX: Recognizes mature (40yo) and young (20yo) subjects with reduced bokeh effect. For higher weights, it learns faces without jewelry, so consider adding jewelry and background details if desired.
pony_weak: Better for close-ups; doesn't perform well with complex prompts. Not limited to "1girl" and includes backgrounds.
pony_strong: works better with more complex prompts, not only 1girl, and call background
face enhancer_v3: Stronger in close-ups. Please consider using my prompts. ;)
face enhancer_v2: Much smoother and improved.
Multi-Face Models:
multifacesv_3: (Keywords: group, crowd, many faces) Generates more people, but distant faces still need improvement. Recommended weight: 0.3-0.8.
multifaces_v2: (Trigger: specify the "number" of faces) i used also copax and juggernaut that is already not that bad at small faces so may you dont need it!
multifaces_v1 -> (trigger: group, faces)
Additional Recommendations:
Overall, I suggest using Adetailer or a refiner for enhancing small faces.
Face Swap with Adetailer and Reactor
The new SDXL VAE (released on 2023.07.26) is significantly better than older versions for face generation.
Please try my LoRA, and you'll often get more realistic faces—not those blurred, soft ones. ;)
Hints:
-
please, almost no negative prompt is necessary!
see my articles:
All SFW!
Trigger words
aborigines
african
arabian
arctic
brazilian
chinese
egyptian
european
japanese
nordic
russian
western
SHA256
B6F75216F6B49F1620FADCEBF8FDED7A854E4213698A5D1EA16D8858B6090974
ModelTrends.ai Model ID
#3084
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++ 2M Karras
Steps
26
Guidance
6
Seed
1866094683
Size
832x1216
Clip skip
2
Weight used
0.8
Prompt
Expressive, score_6_up, score_7_up, score_8_up, score_9. Masterpiece, best quality, highly detailed, harmonious anatomy, (natural beauty:1.1), consistent details. fighting, azula, japanese, <lora:azula-book2-ponyxl-lora-nochekaiser:1>, azula, black hair, brown eyes, topknot, sidelocks, hair bun, single hair bun, flowing hair, action shot, wind in hair, (afraid look), [surprised look], skintight clothes, chinese clothes, capelet, sash, long sleeves, elbow gloves, pronounced female figure, areola slip, exposed skin, flashing thighs, (torn clothes:1.2), [scar, blood, defeated, wounded], in feudal japanese background, blue fire power aura, blue flames, dynamic pose, dynamic view, perfect hands, [blue fire around closed fists], martial art position,
Negative prompt
score_4, score_5, monochrome, source_furry, ((futa)), ((trans)), busty, big breasts, man, sex, boy, two people, purple dildo, orange dildo, colored plastic dildo, abs, muscular, multiple heads, extra fingers
Settings
Sampler
DPM++ 2M Karras
Steps
26
Guidance
6
Seed
590399295
Size
832x1216
Clip skip
2
Weight used
0.8
Prompt
Expressive, score_6_up, score_7_up, score_8_up, score_9. Masterpiece, best quality, highly detailed, harmonious anatomy, (natural beauty:1.1), consistent details. fighting, azula, japanese, <lora:azula-book2-ponyxl-lora-nochekaiser:1>, azula, black hair, brown eyes, topknot, sidelocks, hair bun, single hair bun, flowing hair, action shot, wind in hair, (afraid look), [surprised look], skintight clothes, chinese clothes, capelet, sash, long sleeves, elbow gloves, pronounced female figure, areola slip, exposed skin, (torn clothes:1.2), [scar, blood, defeated, wounded], in feudal japanese background, blue fire power aura, blue flames, dynamic pose, dynamic view, perfect hands, [blue fire]
Negative prompt
score_4, score_5, monochrome, source_furry, ((futa)), ((trans)), busty, big breasts, man, sex, boy, two people, purple dildo, orange dildo, colored plastic dildo, abs, muscular,
Settings
Sampler
DPM++ 2M Karras
Steps
26
Guidance
6
Seed
1277709266
Size
832x1216
Clip skip
2
Weight used
0.8
Prompt
Expressive, score_6_up, score_7_up, score_8_up, score_9. Masterpiece, best quality, highly detailed, harmonious anatomy, (natural beauty:1.1), consistent details. fighting, azula, japanese, <lora:azula-book2-ponyxl-lora-nochekaiser:1>, azula, black hair, brown eyes, topknot, sidelocks, hair bun, single hair bun, flowing hair, action shot, wind in hair, (afraid look), [surprised look], skintight clothes, chinese clothes, capelet, sash, long sleeves, elbow gloves, pronounced female figure, areola slip, exposed skin, flashing thighs, (torn clothes:1.2), [scar, blood, defeated, wounded], in feudal japanese background, blue fire power aura, blue flames, dynamic pose, dynamic view, perfect hands, [blue fire around closed fists], martial art position,
Negative prompt
score_4, score_5, monochrome, source_furry, ((futa)), ((trans)), busty, big breasts, man, sex, boy, two people, purple dildo, orange dildo, colored plastic dildo, abs, muscular, multiple heads, extra fingers
Settings
Sampler
Euler a
Steps
40
Guidance
8.5
Seed
720714026
Size
832x1216
Clip skip
2
Weight used
0.7
Prompt
view from behind, extremely low angle,: score_11, score_10, photorealistic, ultra detailed, young, 18yo, gorgeous ebony girl, african girl, dark ebony skin, hime cut hair, 1girl, detailed kitchen, marble countertop, copper cooking set, crystal , view from behind , ass view, very beautiful girl, short hair, ebony girl, african girl, afro hair, heart earrings, freckles, pale skin, tan lines, wide hips:1.5, big soft ass, large nose piercing, lip piercing ring, man strangling girl,man choking girl, dark lipstick, thick soft thighs:1.6, fat ass, large very soft droopy breasts, legs spread wide open, natural pubic hair, slave collar, looking behind and over her shoulder, puffy nipples, spread breasts, green eyes, revealing french maid uniform, choker, thigh highs, floral print, lip-gloss, elaborate japanese body tattoos, tattoos on thigh, tattoos on arms and chest, excessive makeup, floral pattern, loose crop top, underboob, tight skirt, detailed face, detailed mouth, detailed eyes, realistic detailed skin, (small lips, small mouth, puffy lips:1.1), blushing, excited ,
Negative prompt
embedding:urn:air:sd1:embedding:civitai:222256@250712, core_6, score_5, score_4, worst quality, low quality, text, censored, deformed, bad hand, blurry, (watermark), multiple phones, weights, extra hands, naked, embedding:urn:air:sdxl:embedding:civitai:332646@509253 wispy hair, (glowing eyes:1.2), (painted:1.4), deformed, not anatomical, (pov, man:1.4), puffy anus, muscular, denim, nude, jeans
Settings
Sampler
Euler a
Steps
19
Guidance
7
Seed
1188399006
Size
832x1216
Clip skip
2
Weight used
0.8
Prompt
Expressive, score_6_up, score_7_up, score_8_up, score_9. Masterpiece, best quality, highly detailed, harmonious anatomy, (natural beauty:1.1), consistent details. fighting, chinese, toph bei fong, short black hair, white eyes, headband,hair ornament, blind, green chinese clothes, tunic, bracers, big boobs, musculous thights, ((adult: 1.5)), looking serious, fighting pose, floating rocks, canyon background, exposed skin, ((flashing thighs)), (torn clothes:1.2), [scar, blood, defeated, wounded], dynamic pose, dynamic view, perfect hands, martial art position,
Negative prompt
score_4, score_5, monochrome, source_furry, ((futa)), ((trans)), busty, big breasts, man, sex, boy, two people, purple dildo, orange dildo, colored plastic dildo, abs, muscular, multiple heads, extra fingers
Settings
Sampler
DPM++ 2M Karras
Steps
31
Guidance
8
Seed
2695782714
Size
832x1216
Clip skip
2
Weight used
0.65
Prompt
a female paladin adorned in holy armor, wielding a holy sword, ((African woman)), furrowed brow, fighting stance, surrounded by the aura of the sun, red and gold armor, strong face, detailed eyes, ebony skin, wide nose, cowboy shot, score_9, score_8_up, score_7_up,1dk, g0thicPXL, glowing, portrait
Negative prompt
catsuit, bodysuit, swimsuit, BadDream, UnrealisticDream, (score_6, score_5, score_4), (3d, black and white, grayscale), (patreon, watermark, signature), (text, writing, words), (ugly face, mutated hands, blurry face, bad hands, deformed), low res, blurry face, bad teeth
Settings
Sampler
Euler a
Steps
16
Guidance
4
Seed
1748212851
Size
832x1216
Clip skip
2
Weight used
0.7
Prompt
score_9, score_8_up, score_7_up, source_anime, intricate details, anime screencap, perfect balance, official art, extremely detailed CG unity 8k wallpaper, perfect lighting, Colorful, Warm_Front_face_Lighting, (masterpiece:1.0),(best_quality:1.0), ultra high res,4K,ultra-detailed, photography, 8K, HDR, highres, absurdres:1.2, Kodak portra 400, blurry background, bokeh, lens flare, (Anime) (vibrant_color:1.2), professional photograph, night, (cute_face:1.2), 2d, anime, upper body, intricate iris, American, Professional character design, 1girl, female focus, (Orange eyes), perfect eyes, (black-hair), Native American, Indigenous, American Indian, youthful, solo, jujutsu_kaisen_style, character portrait, (perfect-lighting), face, young, (Dark-black-hair), Long hair, (Native American), Indigenous, American Indian, (((wild eyes))), (Native North American), (Upturned eyes), (high cheekbones), (strong jawline), (Black Hair), ((((Native-American-Eagle-feather-braids, Native American Eagle feather accessories)))), (((wild eyes))) ((Bobbed Bangs)) (((Slanted-Eyes))) (Psycho) (Happy) (Inuit Clothing), (Sleeveless Parka) (Warpaint), (Redwood Forest, Pacific Northwest Forests), (Inuit), (Tan skin), (Dark Skin), (Brown skin), (bobbed hair), White Eagle-Feather-Earrings, Thick Bangs, Bobbed hair, Bob-cut, White-Feather-Earrings, Brown-skin, Inuit Face-paint, Full-Bangs, Wide-Bangs, Thick-Hair, Native Face-paint, cleavage, Psycho, Yandere, big irises, Big eyes, (Sleeveless Inuit Parka, Fur)
Negative prompt
score_4_up, score_5_up, score_6_up, lowres, messy drawing, amateur drawing, ugly face, bad face, bad teeth, (interlocked fingers, badly drawn hands and fingers, anatomically incorrect hands, bad anatomy), watermark, greyscale, monochrome, blurry, source_cartoon, source_furry, source_pony, sketch, painting, Sukuna, asian, sweat, closeup, tropical, Brown Hair, Tan jacket, Brown jacket, Blue Jacket, bad bangs, Forehead, parted hair, center part, Blue-feathers, Blue-Earrings, Blue-jewelry, pale-skin
Settings
Sampler
Euler a
Steps
16
Guidance
4
Seed
2119084684
Size
832x1216
Clip skip
2
Weight used
0.7
Prompt
score_9, score_8_up, score_7_up, source_anime, intricate details, anime screencap, perfect balance, official art, extremely detailed CG unity 8k wallpaper, perfect lighting, Colorful, Warm_Front_face_Lighting, (masterpiece:1.0),(best_quality:1.0), ultra high res,4K,ultra-detailed, photography, 8K, HDR, highres, absurdres:1.2, Kodak portra 400, blurry background, bokeh, lens flare, (Anime) (vibrant_color:1.2), professional photograph, night, (cute_face:1.2), 2d, anime, upper body, intricate iris, American, Professional character design, 1girl, female focus, (Orange eyes), perfect eyes, (black-hair), Native American, Indigenous, American Indian, youthful, solo, jujutsu_kaisen_style, character portrait, (perfect-lighting), face, young, (Dark-black-hair), Long hair, (Native American), Indigenous, American Indian, (((wild eyes))), (Native North American), (Upturned eyes), (high cheekbones), (strong jawline), (Black Hair), ((((Native-American-Eagle-feather-braids, Native American Eagle feather accessories)))), (((wild eyes))) ((Bobbed Bangs)) (((Slanted-Eyes))) (Psycho) (Happy) (Inuit Clothing), (Sleeveless Parka) (Warpaint), (Redwood Forest, Pacific Northwest Forests), (Inuit), (Tan skin), (Dark Skin), (Brown skin), (bobbed hair), White Eagle-Feather-Earrings, Thick Bangs, Bobbed hair, Bob-cut, White-Feather-Earrings, Brown-skin, Inuit Face-paint, Full-Bangs, Wide-Bangs, Thick-Hair, Native Face-paint, cleavage, Psycho, Yandere, big irises, Big eyes, (Sleeveless Parka, Fur-trim)
Negative prompt
score_4_up, score_5_up, score_6_up, lowres, messy drawing, amateur drawing, ugly face, bad face, bad teeth, (interlocked fingers, badly drawn hands and fingers, anatomically incorrect hands, bad anatomy), watermark, greyscale, monochrome, blurry, source_cartoon, source_furry, source_pony, sketch, painting, Sukuna, asian, sweat, closeup, tropical, Brown Hair, Tan jacket, Brown jacket, Blue Jacket, bad bangs, Forehead, parted hair, center part, Blue-feathers, Blue-Earrings, Blue-jewelry, pale-skin
Similar Models
AI Models for Image, Video & Text Generation
betterfaces strong 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.
More Stable Diffusion XL 1.0 modelsMore Stable Diffusion XL 1.0 LoRAsponytypewomenconceptflux1dethnicsdxlculturedetail
Browse by Model Family
Text / LLM Models
411
Anima Models
509
Chroma Models
14
Flux Models
1,071
Flux 2 / Klein Models
1,237
MiniMax H3 Models
331
Hunyuan Models
197
Ideogram Models
20
Krea2 Models
674
Qwen Models
17
Qwen2 Models
36
Ltx2 Models
150
Stable Diffusion 1.5 Models
6,465
Stable Diffusion XL 1.0 Models
15,432
Zimage Models
804
Wan Models
919

Model
Trends
.ai
© ModelTrends.ai
|
Made in Japan
|
© 2026
