Model
Trends
.ai
Model
Trends
.ai
the best open source ai models
Run Locally
faces_v3.safetensors
435 MB · SafeTensor
Downloads are served by Civitai. Some creators ask for a Civitai login first.
AD
Install / Run on Graydient
Requires membership
<face-enhancerv3-xl>
About This Model
STABLE DIFFUSION XL 1.0 · LoRAs
Created by
sevenof9247
on Civitai
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!
17,388 downloads · 496 likes on Civitai
SHA256
F1D5492E633C877F75F9824C5102B1FFC40ADFB4860FE498EB58F4E8BF2450CB
ModelTrends.ai Model ID
#14721
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
30
Guidance
7
Seed
1179871379
Size
1024x1024
Clip skip
1
Weight used
1
Prompt
[Verse 1] Khada hun aaj bhi wahi Ki dil fir bekaraar hai Khada hun aaj bhi wahin Ki tera intezaar hai [Chorus] Chhoo lo jo mujhe tum kabhi Kho na jaun main raat-din Nazaron mein tum ho base Kehdo jo tum ek baar Mere ho bas tum mere Nazaron mein tum ho base [Instrumental-break] [Verse 2] Khada hun aaj bhi wahin Lagi teri hi aas hai Kaisi hai yeh bebasi Ye kaisi dil ki pyaas hai [Chorus] Chhoo lo jo mujhe tum kabhi Kho na jaun main raat-din Nazaron mein tum ho base You might also like Anuv Jain - Husn (Romanized) Genius Romanizations SHOOTING STAR XG Anuv Jain - Baarishein (Romanized) Genius Romanizations Kehdo jo tum ek baar Mere ho bas tum mere Nazaron mein tum ho base [Bridge] Reh jaunga yunhi, bas yunhi, bas yunhi Reh jaunga yunhi, bas yunhi, bas yunhi Reh jaunga yunhi, bas yunhi, bas yunhi Reh jaunga yunhi, bas yunhi, bas yunhi Reh jaunga yunhi, bas yunhi, bas yunhi [Chorus] Chhoo lo jo mujhe tum kabhi Kho na jaun main raat-din Nazaron mein tum ho base Kehdo jo tum ek baar Mere ho bas tum mere Nazaron mein tum ho base [Outro] Haa main ruka hu Tu jaa chuka hai Haa main ruka hu Tu jaa chuka hai
Negative prompt
(worst quality, low quality:1.4), FastNegativeV2, badhandv4, inequalities:2, epiCPhotoGasm-colorfulPhoto-neg, UnrealisticDream, nsfw
Settings
Sampler
DPM++ 2M Karras
Steps
30
Guidance
7
Seed
2009699900
Size
1024x1024
Clip skip
1
Weight used
1
Prompt
billo bagge billeyan da ki karengi, moye moye, Food, dragon, human head, festive, colorful, amoled black, mutated, weird, vehicle riding a cat with human head, army tank, beach sea, underwater, lava, ((realism, Realistic, photograph, noise))
Negative prompt
(worst quality, low quality:1.4), FastNegativeV2, badhandv4, inequalities:2, epiCPhotoGasm-colorfulPhoto-neg, UnrealisticDream, nsfw
Settings
Sampler
DPM++ 2M Karras
Steps
25
Guidance
7
Seed
382419211
Size
832x1216
Clip skip
1
Weight used
1
Prompt
(masterpiece), (extremely intricate:1.3), (realistic), picture of the most beautiful woman in Ireland, Brid Lightbringer, Warrior Queen, wavy curly blonde hair, (blue and white science-fiction armor and leather, intricate breastplate, thigh high boots), metal reflections, outdoors, enchanted woods river bank, stunning professional entire body photograph of the prettiest, most stunning woman in the world, detailed, sharp focus, dramatic, award winning, cinematic lighting, octane render unreal engine, volumetrics dtx, (film grain, blurry background, blurry foreground, bokeh, depth of field, motion blur:1.3)
Settings
Sampler
DPM++ 2M SDE Karras
Steps
60
Guidance
7
Seed
4219196480
Size
680x1024
Prompt
analog style, portrait photo of a beautiful swedish model , who looks at you in a Demandingly way with two beautiful green eyes She is naked and the image was taken in close-up, imperfect face, <lora:faces_v3:0.5>
Negative prompt
painting, drawing, sketch, cartoon, anime, manga, render, CG, 3d, watermark, signature, label, naked, nude, nsfw, symmetrical except iris, symmetry except iris, green background
Settings
Sampler
DPM++ 2M SDE Karras
Steps
60
Guidance
7
Seed
4219196480
Size
680x1024
Prompt
analog style, portrait photo of a beautiful swedish model , who looks at you in a Demandingly way with two beautiful green eyes She is naked and the image was taken in close-up, imperfect face,
Negative prompt
painting, drawing, sketch, cartoon, anime, manga, render, CG, 3d, watermark, signature, label, naked, nude, nsfw, symmetrical except iris, symmetry except iris, green background
Settings
Sampler
DPM++ 2M Karras
Steps
20
Guidance
5
Seed
1823629047
Size
768x1344
Prompt
Silhouette Art, breathtaking (masterpiece realistic aesthetic extravaganza alcohol ink sketch). beautiful , amazing, awe-inspiring, mesmerizing, radiant, magnificent, luxurious, fine, detailed. (dark gray hues and white and black and fine day-glo orange accent and shiny glossy gold color scheme:1.02). glossy. <lora:InkArtXL_1.2:0.4> <lora:FaeTastic:0.39> . award-winning, professional, highly detailed . extremely high-resolution details, photographic, realism pushed to extreme, fine texture, incredibly lifelike, high contrast, well defined . <lora:aesthetic:4> <lora:people_005_cosine_iter2_ 0000005_sdxl_10epoches_adafactor:0.4> nordic
Negative prompt
doll, kid, child, (NSFW, ((visible nipple)), spread fingers), paper sheet, visible canvas edged, visible sheet edges, manly, wide hips, alcohol, wineglass, alcohol drink, poorly drawn, ((asian, chinese)), fat body, anorexic, afro, arched forward spine, bad posture, crooked back, (big forehead:1.2), mature face, ((frown), old), big updo, (gap-toothed, unhealthy teeth, small teeth), strongly tilted forward head, broad-boned, (unhappy facial expression:1.2), (elongated neck), (unnaturally big head, elongated head, high forehead:1.4), (tall:0.5), green color hues, low contrast, vulgar frivole and cheap look, messy, (wide-set eyes, closed eyes, thin lips:0.8), ((wings)), ugly, deformed, noisy, blurry, distorted, grainy, ugly, deformed, noisy, blurry, low contrast, fish eye, (busty:0.6)
Settings
Sampler
DPM++ 2M Karras
Steps
35
Guidance
3.5
Seed
586378720
Size
832x1216
Clip skip
2
Weight used
0.8
Prompt
full body photo of a petite 18 year old beautiful Japanese woman, smiling seductively, gym trainer and gymnast, with a narrow face and straight light brunette hair in a messy bun with blonde highlights, dressed in a tight white long sleeved track jacket and high waisted sage green leggings, showcasing pale glistening skin on her slender body, firm round breasts, small round ass, and thin legs with thigh gap, large seductive eyes, (view from the front:1.3), walking on the beach, camera focused on her full lips
Negative prompt
worst quality, low quality, worst detail, low detail, source_furry, source_pony, source_cartoon, 2d, bad anatomy, bad hands, text, error, missing fingers, (extra digit:1.4), fewer digits, cropped, bad artist, outlines, jpeg artifacts, signature, watermark, username, blurry, 3d,
Settings
Sampler
DPM++ 2M
Steps
25
Guidance
7
Seed
135259662
Size
832x1216
Clip skip
2
Weight used
0.7
Prompt
(woman on a stairwell:0.9), (red hair, fancy dress:0.8), (closeup on her face, skin texture:1.1)
Negative prompt
text, watermark, low quality, medium quality, blurry, censored, wrinkles, deformed, mutated text, watermark, low quality, medium quality, blurry, censored, wrinkles, deformed, mutated, BadDream-SDXL, FastNegativeV2-SDXL
AI Models for Image, Video & Text Generation
face enhancerv3 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