samefacefix flux — FLUX AI-model

"by VadimFedenko - Important This Lora should be used with a NEGATIVE weight. Also The model is aimed at diversifying the look of women only. I plan to do a separate model for men later and men with beards especially Also cool fact the size of the Lora is only 4mb it is limited to 2 blocks with a high rank So, What's a Sameface? It's a common problem in generative AI, in which the model generates people with identical appearances. Unlike with SD1.5/SDXL, this is not just a result of the diverse dataset converging into a single token like ""woman"". in Flux,"

Notities van de maker

Important: This Lora should be used with a NEGATIVE weight. Also: The model is aimed at diversifying the look of women only. I plan to do a separate model for men later (and men with beards especially) Also cool fact: the size of the Lora is only 4mb (it is limited to 2 blocks with a high rank) - So, What's a "Sameface"? It's a common problem in generative AI, in which the model generates people with identical appearances. Unlike with SD1.5/SDXL, this is not just a result of the diverse dataset converging into a single token like "woman". in Flux, Dev/Schnell were distilled from the Pro version, resulting in a loss of diversity. - Why use Negative weight? Lora was trained on the most generic photos of women that Flux generates. If you then apply this Lora with a NEGATIVE weight, it will work as a sort of negative prompt, but without negative prompt! By using this clever trick, Lora will basically tell Flux to generate anything except a typical Flux face. And as result, we'll get beautiful unique faces every time! - Why Lora and not tricks like lower Guidance? People want diverse faces with high guidance in order to maintain high prompt adherence and image quality, that's why interventions at the latent space level are optimal. - How does it differ from other character Loras? While other Loras introduce their own "samefaces", this Lora, only tells Flux what should NOT be in the generation, not what to add. As a result, this Lora diversifies people's appearance, rather than narrowing it even further. - How was the Lora actually made? At first I was disappointed because nothing worked out. I was about to give up this project, but then tried to train Lora with just 2 layers, and suddenly during testing, I was met with beautiful faces, and with authentic, distant from Flux, appearance. - What's next? I have a lot to experiment with. Different learning rates, layers and ranks have to be tested in order to improve quality. Merging different Lora variants might fix the problems with artifacts at higher values. I'll make sure to make a better version, If this Lora has enough interest I'm really forward to your feedback, as this model is highly experimental. Any feedback is appreciated and will hopefully help me to improve the model. special thanks to Ostris for

Triggerwoorden

woman

17,504 downloads · 1,232 likes op Civitai

SHA256

5B7919B792DC536621D95D0F42F77D3D68789874F4D5926C42F7242C30F78E7C

ModelTrends.ai model-ID

#6205

Inhoud melden

Voorbeeldrenders

Prompts en instellingen gedeeld door de mensen die deze renders op Civitai maakten. Kies een render om te zien hoe hij is gemaakt.

Deze prompt ophalen

Render van Bertoko op Civitai

Melden

Instellingen

Sampler

Undefined

Stappen

Guidance

3.5

Seed

4294967295

Formaat

832x1216

Clip skip

Gebruikt gewicht

-0.35

Prompt

(Candid photography:1.3), face and cleavage closeup from above, A beautiful supermarket, a blushed smiling brunette freckled Woman in high wooly stockings and very short skirt standing at a candy shelf on tiptoes, colorful knitted sweater, cleavage, looking up, messy hairbun, infront of the atmospheric led-adverstisment, crepuscular rays, volumetric lighting, ultra detailed, deep Blacks, very detailed, atmospheric haze, Film grain, cinematic film still, shallow depth of field, highly detailed, high budget, cinemascope, moody, epic, OverallDetail, 2000s vintage RAW photo, photorealistic, candid camera, color graded cinematic, eye catchlights, atmospheric lighting, imperfections, natural, shallow dof,undefined

Render van fkb42 op Civitai

Melden

Instellingen

Sampler

Undefined

Stappen

Guidance

Seed

3560779263

Formaat

832x1216

Clip skip

Gebruikt gewicht

-0.9

Prompt

(Soft Lighting Photography by Mimoza Veliu and Mario Giacomelli:1.2), NSFW, surreal lucid erotic dream with strong memorable effect full of sexyness captured by lustful photographer, aesthetic_pose, magazine_cover, A hyper-realistic portrait of a young nordic woman with a pale complexion and delicate facial feature, Her eyes are almond-shaped, and have a striking light blue color with a slightly intense gaze,

Render van Volnovik op Civitai

Melden

Instellingen

Sampler

DPM++ 2M

Stappen

Guidance

Seed

3504570443

Formaat

1392x1848

Prompt

In a captivating nighttime scene shot from side and slightly above, stylish latina woman with perfect features squats gracefully near back of a sideways-positioned tuned Toyota AE86 Sprinter Trueno, partially in the frame. Girl is resting her back on the car's side. The car's underbody lights illuminate the asphalt below, creating intricate, glowing patterns around its perimeter. She is adorned in an exquisite Playboy bunny outfit featuring a strapless black leotard, fake bunny ears, wrist cuffs, white pantyhose, high heels, and a detached collar with a bowtie. Her long, lush, wavy hair cascades like a waterfall, adding to her captivating presence. Depicted with accurate female anatomy, she exudes confidence and allure. The high-definition detail emphasizes the sleek lines of the car and the elegance of the woman, all bathed in the ethereal glow of the illuminated surroundings, creating a mesmerizing and enchanting atmosphere. <lora:Dever_Flux_Enhancer:0.5> <lora:Flux_spirals_of_light:0.8> <lora:sameface2:-0.35>

Render van halconwood op Civitai

Melden

Instellingen

Sampler

Undefined

Stappen

Guidance

3.5

Seed

3349949569

Formaat

832x1216

Clip skip

Gebruikt gewicht

-0.6

Prompt

photo of a female jedi master by famous photographer, rim light, great contrast, epic, masterpiece, highly detailed

Vergelijkbare modellen

Badges for creators

Made this model? Put its standing on your Civitai page, your Hugging Face card, your README or your site. Each badge is a small picture that shows the standing on the day you copy it and never changes afterwards, however the rankings move later. The date is part of the badge.

AI-modellen voor het genereren van afbeeldingen, video en tekst

samefacefix flux is een LoRA voor de Flux-familie, vermeld op ModelTrends.ai, een alleen-lezen catalogus van open source AI-modellen voor afbeeldingen, video en tekst. Vergelijk het met andere Flux-modellen, bekijk de populariteitsscore om de trend te zien en open het op PirateDiffusion of BitVector om het te proberen.

Meer Flux-modellen Meer Flux LoRA's women negatives anatomy characters

Bladeren op modelfamilie