Diffus
시작하기
모델/UltraRealistic Lora Project - Flux - v2

UltraRealistic Lora Project - Flux - v2

Danrisi
|
10/21/2025
|
11:43:32 PM
| Discussion|
0
Elegant Bulgarian model taking a joyful selfie in a minimalist loft, illuminated by soft directional window light highlighting her glowing complexion and natural skin texture.
Polished white metallic robotic figure with a fragmented crystalline halo, swirling black smoke in eye cavities, and a circular keyhole revealing gears in the center of its face, set against an indigo to ultraviolet gradient background.
A woman in a yellow biohazard suit stands on a rocky barren landscape facing a colossal dark sci-fi yellow sphere made of intertwined organic and mutated spheres, under an overcast sky.

추천 매개변수

samplers

dpmpp_2m, DPM++ 2M

steps

40

cfg

1

팁

For Flux use CFG=1, Guidance=2.5, Sampler=dpmpp_2m, Steps=40, Strength between 0.8 and 1.0; lower strength like 0.87 improves hands if they degrade.

For SD 3.5 use CFG=1, Guidance=3.5, Sampler=dpmpp_2m, Steps=40, Strength around 0.7 works well.

LoRA allows for quality flexibility from high-definition to intentionally lower-quality aesthetics by adjusting prompts.

Improving anatomy and stability is ongoing with plans to train full checkpoints and expand datasets with diverse poses.

크리에이터 스폰서

If you'd like to support my work and future updates, you can find me on Ko-fi: https://ko-fi.com/danrisi

The main goal was to make more 'live' images with livelier emotions and more dynamic poses and slightly amateurish quality (also can produce high quality images).

P.S: Thanks to everyone for the feedback! I've noticed the comments (not only here) about anatomy issues, and I’ve been collecting reports and examples from all of you. I'm considering a couple of options to address this:

  1. Training a full checkpoint, which might be the more rational approach for consistent improvements.

  2. Expanding the dataset with more photos that cover diverse poses to help refine anatomical accuracy.

I appreciate the input - it really helps me shape the future updates

P.S.2: I’ve moved training to RunPod for consistent, high-quality results. If you'd like to support my work and future updates, you can find me on Ko-fi. Cause i plan to fine-tune a model, not just a LoRa. https://ko-fi.com/danrisi

Setting i use in ComfyUI for Flux:
CFG=1, Guidance =2.5, Scheduler=Beta, Sampler=dpmpp_2m, Steps=40, Strength= from 0.8 to 1.0 works good, but i'm usually use with 1, but if hands getting worse then i set 0.87

Setting i use in ComfyUI for SD3.5:
CFG=1, Guidance =3.5, Scheduler=sgm_uniform, Sampler=dpmpp_2m, Steps=40, Strength= from 0.5 to 1.0 works good, but i'm usually use with 0.7

V2 - Flux

Brings even more realism and versatility to your creations, with significant improvements in stability, anatomy, and overall quality. This update makes the LoRA more adaptive, allowing you to achieve various quality levels based on your prompts—from high-definition realism to intentionally lower-quality aesthetics.

Trained on 1048 images.

What's New:

Stability Improvements: The new version is more stable and works better with text-based prompts, providing a smoother and more predictable output.

Enhanced Hands & Anatomy: Hands and body anatomy are more refined, enhancing lifelike quality.

Quality Flexibility: With the right prompts, you can adjust for both high-quality and lower-quality aesthetics (examples available).



V1.2 for SD3.5 - Large

Decided to make a version for sd3.5 almost with same settings. Imo looks good, but i noticed some problems with anatomy (in some moments even worse then flux), but aesthetic (colors, contrast and other stuff looks even better then flux). I see that sd3.5 have potential, maybe new versions will be on sd3.5 too.

V1.2

Changed half of images in dataset, changed prompting style, improved hands, less 'flashlight effects' at night scenes and overall LoRa quality improvement (i hope).
In this version it's unnecessarily to use tons of 'trigger words' like in V1. Just add some of them that i mentioned in trigger words

V1

Trained another amateur lora (that's already been done a lot around here).

Still, I took some pictures from my dataset on the 2000s and added another 700 pictures. It came out pretty good so far, but there is a controversial point about quality optimization, I was hoping it would help control the quality, but as I see it only confused the model. In the dataset there are many different gradations of quality, like:

1) High-resolution photo, shot on a mobile phone, no visible artifacts, clear and sharp

2) Low-resolution, amateur photo shot on digital camera, no visible jpeg artifacts, slightly noisy

3) Medium-resolution photo, shot on a mobile phone, slight graininess due to low light conditions, no significant digital artifacts

And other their combinations and variations. I think i'll remove such in next version. But this one working the best for me:

Low-resolution, amateur photo shot on digital camera, no visible jpeg artifacts, slightly noisy

이전
Yes Your Grace Portrait Style (FLUX) - flux v1
다음
SXZ Vintage Fantasy DVD Screengrab [ FLUX ] - v1
이 모델 사용하기

모델 세부사항

모델 유형

LORA

기본 모델

Flux.1 D

모델 버전

Flux - v2

모델 해시

b1c4ddf956

학습된 단어

amateurish photo
low lighting
in motion
overexposed
underexposed
GoPro lens
eerie atmosphere
smeared background
smeared foreground

제작자

Danrisi's avatar
Danrisi

토론

댓글을 남기려면 log in하세요.

UltraRealistic Lora Project - Flux - v2 제작 이미지

Elegant Bulgarian model taking a joyful selfie in a minimalist loft, illuminated by soft directional window light highlighting her glowing complexion and natural skin texture.
Polished white metallic robotic figure with a fragmented crystalline halo, swirling black smoke in eye cavities, and a circular keyhole revealing gears in the center of its face, set against an indigo to ultraviolet gradient background.
A woman in a yellow biohazard suit stands on a rocky barren landscape facing a colossal dark sci-fi yellow sphere made of intertwined organic and mutated spheres, under an overcast sky.

aesthetic 이미지

A woman wearing a straw hat and white linen dress sits in a brown wooden canoe on a tranquil waterlily-covered lake surrounded by a lush, sunlit forest.
Close-up side portrait of a cyberpunk goddess with long white hair, mechanical headgear, and chrome robotic hand under soft, low-saturation light.
A confident fashion model with long blonde hair and pink sunglasses wearing a tight orange sleeveless dress and pink high-heeled boots poses on a sunny urban street with palm trees and retro buildings.
A semi-realistic watercolor painting of a white-haired elf woman with pointed ears, wearing a white crop top, white pants, and a flowing cape. She is surrounded by flying doves against a soft, pastel sky background.
Profile silhouette of a young woman with a long braid walking in a street at sunset with warm neon pink lighting and vintage atmosphere.
Oil painting of Azuma Seren with multicolored hair holding a bright floral bouquet against a clear blue sky with clouds.
Side profile of a male wearing an animal skull mask with horns and a lace cloth on an orange background in analog photo style with film grain effect.
A hyper-realistic fantasy illustration of a supermodel wearing a colorful, avant-garde dress, surrounded by vibrant swirling patterns.
Elegant young woman in traditional Chinese Hanfu attire with flower blossom jewelry and long dark hair, posing surrounded by pink blossoms and soft white smoke.
A detailed portrait of an elven witch with a large pointed hat and flowing hair, wearing a blue dress, surrounded by dark magic and floating particles in a ruined castle background.

사진같은 이미지

A photorealistic image of an astronaut sitting on a small mountain on a reddish Martian landscape with a large moon in the starry sky and an alien ship flying above dense clouds.
A handsome young man with wet medium-length black hair wearing a soaked dark blue trench coat, standing in a rainy neon-lit city street at night, looking melancholic with raindrops on his face and sharp dramatic lighting.
A photorealistic robotic skeleton female figure with pink hair flowing dramatically, glowing eyes, and an open mouth, surrounded by red spider lily flowers.
A photorealistic giant titan robot with glowing red sensors sitting incapacitated in a rain-soaked urban ruin, with two hazmat-suited figures observing it under volumetric fog.
A photorealistic small cartoonish man covered in thick fur with wild hair. The character has large wide eyes looking forward, standing on a textured edge under dramatic cinematic lighting.
Side profile of a futuristic female character with short blonde hair wearing a grey high-collar jacket, orange skirt, black mechanical arm, and headphones against a plain grey background.
A photorealistic spiral staircase formed by twisting tree branches with glowing orange autumn leaves, ascending through a dense forest canopy with cinematic sunset lighting.
Close-up detailed portrait of a woman with realistic skin texture, pink hair, blue eyes, freckles, and glossy, parted lips.
Silhouette of Batman perched on a gothic gargoyle against a luminous full moon over an art-deco cityscape at night.
Close-up of a fuzzy black and green fly with large eyes holding a glass of beer on a snowy wooden plank, snowflakes falling in the background.

sexy 이미지

A detailed 3D render of a humanoid robot with sleek white and black robotic design, cat-like ears, glowing orange eyes, sitting contemplatively with arms crossed in a futuristic cockpit with advanced control panels and cables.
Anime art of a young woman in desert attire standing in a barren desert with rocky formations under a clear blue sky.
A girl with flowing ginger hair, green eyes, and a Scotland-inspired outfit kneeling in a green meadow with a cloudy sky background, styled in arcane art style.
A monochromatic detailed illustration of a woman with large black-and-white angel wings, kneeling with a surprised expression and flowing hair.
A hyper-realistic female warrior with white hair and tattoos, wearing a red crop top and skirt with fur trim, holding a fantasy weapon in a snowy forest.
Anime-style bunny girl with platinum blonde hair and pink tips, dressed in a glossy pink crop top and mini skirt with bunny ears, black lace gloves, and high platform heels, surrounded by black, white, and pink balloons on a clean light background.
Close-up neon-style digital portrait of a blonde woman wearing a black choker and dark clothing with orange and teal lighting effects over her face and hair.
A hooded skaven rat holding a knife and running with a piece of cheese in its mouth, set in dark, ruined city streets with green haze.
A futuristic DJ girl with heterochromia eyes, pink and blue hair, colorful bracelets, black leather outfit, and detailed tattoos operating a DJ mixer.
Female rock singer with short white hair wearing a black leather jacket and gloves, holding a microphone on stage with dramatic lighting and blurred guitarist in background.

style 이미지

A dynamic portrait of a Polish archer holding a royal scimitar and drawing a bow, wrapped in the Polish flag with detailed armor, set against a dark fantasy background.
3D rendered giant robot standing in a field at night, glowing eyes, facing a boy in a yellow hoodie with starry sky and forest background.
Detailed illustration of a girl with long black hair and a curvy figure, rendered in an artistic chalk and coal style with dynamic composition.
Oil painting of a black raven perched on a gnarled tree branch against a vibrant sunset sky with dramatic clouds and distant mountains.
A striking upper body portrait of a gothic woman with vibrant orange and black abstract patterns overlaying her face, glowing eyes, and a sensual, sinister smile, depicted in a highly detailed charcoal drawing style with intense, vibrant colors and volumetric lighting.
Stylized Parisian woman in black haute couture dress and hat walking a white Scottish terrier on a yellow background, shown in side profile with minimalist pop art style.
Full-body shot of a ballet dancer with violet hair in a pleated dress on a polished floor with ribbons and petals.
Woman with short blue hair in black mini dress at amusement park.
Woman in animal print leggings and satin camisole in a handcrafted living room.
Lower body wearing gold ankle boots and multicolor dress.

여성 이미지

Silhouette of a woman partially obscured by vertical light streaks standing in a field near a cabin at sunset with warm golden and orange hues.
A woman wearing a straw hat and white linen dress sits in a brown wooden canoe on a tranquil waterlily-covered lake surrounded by a lush, sunlit forest.
Monochrome silhouette of a woman with long wavy hair, lit from behind creating strong chiaroscuro contrast against a black background.
A realistic drawing of a woman with short curly hair standing in a bright kitchen, wearing a white oversized shirt and sneakers, feeding a black and white cat sitting by her feet.
A woman in a long flowing purple gown stands in a forest of towering crystalline structures, her head emitting a vertical beam of light that illuminates the surroundings with prism-like colors.
A woman and a deer facing each other in a dark, foggy autumn forest with mystic lighting and soft bokeh effects.
Monochromatic surreal portrait of an ethereal woman with expressive eyes and porcelain skin, set against a circular background with glass fragments and soft light highlights.
A woman in an impasto style painting wearing a flowing yellow dress with red accents and red high heels against a gray background with dynamic brushstrokes.
A woman standing against a wall with bold black-and-white vertical stripes, wearing a loose-fitting white button-up shirt and black high-waisted pants, softly lit with a serene expression.
A fierce woman with black long hair and tribal warpaint yells and raises her fist while riding a large black and orange T-Rex in a jungle setting, illustrated in flat vector style.