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, westernmy FLUX-lora responds to age prompts like __yo for 20yo, 30yo, 40yo. Weight: start with 0.3look image post for more, i was curious also negativ has an impact^^V........... see below ..............VTry 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.<a target="_blank" rel="ugc" href="https://civarchive.com/models/151594?modelVersionId=827638">https://civarchive.com/models/151594?modelVersionId=827638</a><hr />I aim for realistic faces with natural skin, avoiding perfect symmetry. :)FLUX with Euler-Sampler and SGM-Uniform-Scheduler performs well at -&gt; 15-25 StepsTrigger words aren't essential but are useful for specifying cultural features! and "yo" ;)<hr />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 backgroundface enhancer_v3: Stronger in close-ups. Please consider using my prompts. ;)face enhancer_v2: Much smoother and improved.<hr />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 -&gt; (trigger: group, faces)<hr />Additional Recommendations:Overall, I suggest using Adetailer or a refiner for enhancing small faces.Face Swap with Adetailer and Reactor <a target="_blank" rel="ugc" href="https://civarchive.com/articles/5002/face-swap-with-adetailer-and-reactor">https://civarchive.com/articles/5002/face-swap-with-adetailer-and-reactor</a>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:<ul><li>please, almost no negative prompt is necessary!</li></ul>see my articles: <a target="_blank" rel="ugc" href="https://civarchive.com/articles/1890/better-faces-lora">https://civarchive.com/articles/1890/better-faces-lora</a> <a target="_blank" rel="ugc" href="https://civarchive.com/articles/1826/sdxl-prompts">https://civarchive.com/articles/1826/sdxl-prompts</a>All SFW!

better faces cultures sdxl/FLUX

srtonger trained, better for long and complex promptstrained on my pony modelshould work for most real/pony

face_strong_sevenof9.safetensors

better_faces_pony_strong

cultures_flux_v3

cultures_flux_v2

Cultures_Portait_FLUX

better_faces_pony_weak

multifaces v3

multifaces v2

multifaces v1

face enhancer v3.0

face enhancer v2.0

face enhancer v1.0low sdx

face enhancer v1.0 sdxl

I found that images generated with my LoRA appear more ******* and less like the puppy "model_flux" style.In Better Faces, I aimed to include a diverse range of cultures and ethnicities—11 if I remember correctly—with both young and old subjects, currently focusing on women.my FLUX-lora responds to age prompts like __yo for 20yo, 30yo, 40yo. Weight: start with 0.3V........... see below ..............VTry 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.<hr>I aim for realistic faces with natural skin, avoiding perfect symmetry. :)FLUX with Euler-Sampler and SGM-Uniform-Scheduler performs well at -&gt; 15-25 StepsTrigger words aren't essential but are useful for specifying cultural features! and "yo" ;)<hr>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 backgroundface enhancer_v3: Stronger in close-ups. Please consider using my prompts. ;)face enhancer_v2: Much smoother and improved.<hr>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 -&gt; (trigger: group, faces)<hr>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:<ul><li>please, almost no negative prompt is necessary!</li></ul>see my articles: All SFW!

&lt;p&gt;srtonger trained, better for long and complex prompts&lt;/p&gt;&lt;p&gt;trained on my pony model&lt;/p&gt;&lt;p&gt;should work for most real/pony&lt;/p&gt;

Files with SHA256: b6f75216f6b49f1620fadcebf8fded7a854e4213698a5d1ea16d8858b6090974