Diffus
Get started
models/UltraRealistic Lora Project - Flux - v2

UltraRealistic Lora Project - Flux - v2

Danrisi
|
10/7/2025
|
5:43:32 PM
| Discussion
Close-up selfie of a smiling Bulgarian woman with natural glowing skin under soft window light, wearing silver earrings and a high-neck sleeveless top in a minimalist loft.
Polished white metallic robotic figure with visible servo joints and geometric plating, featuring a fragmented crystalline halo above the head, black smoke swirling in eye cavities, and a circular keyhole revealing intricate gears on the face against an indigo-to-ultraviolet gradient background.
A woman in a yellow biohazard suit stands on a rocky barren landscape staring at a colossal yellow organic sphere with fused egg-like structures and veins under an overcast sky.

Recommended Parameters

samplers

dpmpp_2m, DPM++ 2M

steps

40

cfg

1

Tips

For ComfyUI with Flux model: CFG=1, Guidance=2.5, Scheduler=Beta, Sampler=dpmpp_2m, Steps=40, Strength between 0.8 and 1.0 (typically 1.0; reduce to 0.87 if hand quality degrades).

For ComfyUI with SD3.5 model: CFG=1, Guidance=3.5, Scheduler=sgm_uniform, Sampler=dpmpp_2m, Steps=40, Strength between 0.5 and 1.0 (typically 0.7).

Consider expanding the dataset with more diverse poses to improve anatomical accuracy in future updates.

Creator Sponsors

If you'd like to support the work and future updates of the Flux model, please visit and donate at 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

Previous
Frieren フリーレン - 葬送のフリーレン - v2.0-alpha [FLUX]
Next
Crimson Acryllic FLUX - V1
Use this model

Model Details

Model type

LORA

Base model

Flux.1 D

Model version

Flux - v2

Model hash

b1c4ddf956

Trained words

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

Creator

Danrisi's avatar
Danrisi

Discussion

Please log in to leave a comment.

Images by UltraRealistic Lora Project - Flux - v2

Close-up selfie of a smiling Bulgarian woman with natural glowing skin under soft window light, wearing silver earrings and a high-neck sleeveless top in a minimalist loft.
Polished white metallic robotic figure with visible servo joints and geometric plating, featuring a fragmented crystalline halo above the head, black smoke swirling in eye cavities, and a circular keyhole revealing intricate gears on the face against an indigo-to-ultraviolet gradient background.
A woman in a yellow biohazard suit stands on a rocky barren landscape staring at a colossal yellow organic sphere with fused egg-like structures and veins under an overcast sky.

aesthetic Images

Fantasy supermodel with ethereal beauty wearing a vibrant, colorful avant-garde dress, adorned with intricate jewelry, set against a swirling, vivid multicolored background.
Close-up of a steaming coffee cup on a saucer placed on a rustic wooden table with a clean beige background.
A girl with blue-green hair holding a bright pink umbrella stands on a wet reflective surface under rain, against a low-tone sky with vibrant clouds.
Photorealistic image of a Chinese girl in traditional hanfu attire adorned with flower blossom jewelry and long dark hair, set against an ancient art-inspired background.
A woman with messy brown hair in a ponytail, wearing a teal raincoat, torn jeans, and leather boots, sitting pensively on a large rock by a misty river bank with visible breath in cold air.
A young elven witch with blue eyes and flowing dark hair wearing a large witch hat and dark blue trimmed clothing stands in a ruined castle environment surrounded by a magical whirlwind.
A princess clad in golden armor rides a detailed metallic dinosaur with blue gem decorations and red bat-like wings at sunset, set in a fantasy mountainous landscape with colorful flowers.
Anime-style girl standing under a gradient sky during sunset, watching a bright shooting star with scattered clouds and stars above.
Silhouetted wildflower stems against a dramatic orange sunset sky with circular bokeh highlights in a shallow depth of field macro photograph
A tranquil minimalist mountain landscape with jagged peaks reflecting on a calm lake under early dawn light, surrounded by soft mist and a clear sky.

photorealistic Images

A photorealistic landscape featuring a mountain topped with white cliffs above a desert background, with vast expanses of black sand dunes and a lone figure walking across the sand.
A photorealistic futuristic robot with a glowing white head and metallic body. The robot is posed dynamically with sound waves around, surrounded by bright light effects and sparkles against a blue background.
A fierce yeti with white fur and sharp teeth reaching out with a hand in a snowy mountain blizzard.
Photorealistic close-up of a woman with detailed skin pores wearing glasses and a white shirt, seated in a leather chair in an office.
Black chibi anime cat lying under a park bench at night surrounded by neon-colored animated fish and light streaks, with heavy bokeh in the background.
A dark knight in full armor stands on a rocky cliff facing a gigantic abyssal dragon with glowing red eyes and mouth, under dramatic cinematic lighting with a moody fantasy atmosphere.
Close-up of a young woman with ginger hair, blue eyes, and freckles wearing a crystal crown and diamond necklace, holding a crystal ball with a medieval castle backdrop at sunset.
Portrait of a confident punk girl with asymmetric buzz cut hair dyed blue and red, hazel eyes, multiple tattoos and piercings, wearing a black fishnet dress
Photorealistic female character with medium chestnut brown hair and amber eyes pointing at the viewer in a dynamic jojo pose, set against an orange glowing background.

sexy Images

A futuristic robot girl with metallic skin and a blonde braid stands on the moon's surface, holding a glowing star with Earth and a large moon in the background under a starry sky.
A neon-themed high fashion image of a blonde girl in a dramatic sitting pose, wearing a black outfit and a choker, with orange and teal lighting and digital glitch graphics over her eyes.
Blonde woman with freckles and smile sitting outdoors wearing a maroon v-neck t-shirt and floral microskirt under natural lighting
Close-up portrait of a young woman with blue eyes wearing detailed Celtic-style armor in a forest, featuring realistic skin texture and soft natural light.
Close-up portrait of an elegant adult Spanish woman with dark brown eyes, light brown hair in a quiff style, wearing blue gemstone earrings, and stylish dark goth makeup, against a light blue swirling bokeh background.
A stylized anime girl with long black hair and striking green eyes, wearing a black outfit and thigh-high stockings adorned with red flowers tattoo, holding a katana against a red background.
Detailed side profile of a tribal prehistoric dinosaur adorned with vibrant orange and black ornate feathers and decorations in a flat color style with an inverted background.
A flat-design style illustration of a mermaid floating underwater, featuring intricate fractal patterns in orange against a dark inverted background with pearlescent and neon effects.
A fierce Amazon warrior with white braided hair in detailed bronze armor, holding a trident and an axe, standing in ancient stone ruins with volumetric lighting.
Stylized punk girl with bright red hair in a dynamic side profile pose, set against an orange fractal and neon patterned inverted background, rendered in flat design with spot colors and no line art.

style Images

A cyberpunk hooded figure wearing a black techwear hoodie and bionic legs stands on a futuristic city rooftop illuminated by neon cyan and red lights with floating cubes and digital shards around.
3D model of the Iron Giant robot standing outdoors at night, facing a boy in a yellow hoodie, with a starry sky and mountain scenery in the background.
Detailed illustration of a black-haired girl in a dynamic, abstract ink and chalk composition with a curvy figure and vibrant lips
A detailed oil painting of a black raven perched on a gnarled, leafless tree branch against a vibrant sunset sky with orange and red clouds, distant mountains, and a soft glowing moon.
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.
A stylish anime girl with dark hair in a ponytail, wearing a white shirt, red high-waisted pants, and a black jacket. AI generated image using Stable Diffusion.
Blonde woman with long straight hair, wearing an off-shoulder white top, standing in a bright room. This is an AI generated image using Stable Diffusion.

woman Images

A woman with disheveled hair wearing a summer dress, shot overhead with a fisheye lens, featuring wide orange light leaks on a blue background.
Hyper detailed digital illustration of a woman with short dark hair wearing a frilly shirt and lace-up underbust corset, standing in a grass field with flowers.
A woman with long black hair wearing a t-shirt takes a selfie in a dimly lit bedroom at night, lying on a bed covered with comforters and quilts.
Photorealistic close-up of a woman with detailed skin pores wearing glasses and a white shirt, seated in a leather chair in an office.
30-year-old woman in a bathroom wearing a pink towel wrapped around her head, white tank top, and patterned loose pajama pants, taking a night time selfie with a small smile
A mature woman dressed in a blue vintage dress with a low neckline and a blue shawl, standing in an old French village setting.
Woman sitting on a cozy brown couch crossing her legs, wearing a light beige sweater, softly lit by natural light from the side.
Impressionist painting of a woman in denim jeans and a plaid shirt picking apples from a tree under soft cloudy light
Black and white photograph of a woman in formal attire and a wide-brimmed hat standing on a floating ice platform beside a modern chair, reflected on calm water under an overcast sky.