Model
Trends
.ai
Model
Trends
.ai
the best open source ai models
Run Locally
IDunnohowtonameLora.safetensors
146 MB · SafeTensor
Downloads are served by Civitai. Some creators ask for a Civitai login first.
AD
Install / Run on Graydient
Requires membership
<ultrareal-flux>
About This Model
FLUX · LoRAs
Created by
Danrisi
on Civitai
by Danrisi - I dunno how to call this lora. UltraReal
Creator notes
--Qwen2.1 Me recommendations: 3-4 cfg (but if image become slop, then change to 1) beta scheduler, res_2m / res_2s / res_multistep (2s best quality, multistep the fastest, 2m balance) I'll post my flow a bit later when finish uploading other loras P.S: im in a hurry so more exmaples will be soon for all my loras --Krea2 Actually i tested with different combinations raw and turbo. For best quality i use raw with cfg4, for fast result i use raw, but witth cfg1 and turbo lora (it really gives better quality then kreo2 turbo model). U can use with other loras freely, also works good with nicegirls lora and nsfw loras. recommended weight 0.8 for raw and 1.2-2 for turbo --Ideogram4 Works good with for nsfw images. Also updated my repo for better lora control One more. Made cool nodes with cursor (i have no clue how some of them to use) for ideogram --Anima1.0 Trained on top of my last ultrareal_finetune_base1 checkpoint for a slight realism boost. I also "vibecoded" a few experimental nodes for Anima (pretty sure something similar already exists, but here we are): Consider this a temporary realism upgrade until I train the next major fine-tune. --Anima0.5 Trained on anima3. Recommended strength: 0.6. Works best with block filtering — I created a ComfyUI nodepack for this: . Examples generated alongside my other LoRA — nicegirls. Experimental version. Results may vary depending on prompt and block weight settings. --Flux2 I use it with res2m+beta57, guidance 4, and it works very well. The quality is similar to my Qwen Lenovo, but I noticed that Flux2 is more flexible and has better prompt adherence. Recommend to use with strength 0.85-0.9 -- Z-image Turbo Actually i'm not sure that my workflow is correct, i believe the result could be better Recommend to use with strength 0.80-0.9 I used euler + sgm_uniform with 4 guidance P.S: at this moment for ComfyUI u need this pack to load lora properly --Chroma My first try to train lora that enhance realism in Chroma. I'll upload my workflow today a lil bit later (or atm u can just take it from images) cause there some nuances about settings. But from my observations i noticed that for fast gen dpmpp2m + beta with cfg 3 works good . More experimental settigns are res_2s_rkmk2e + beta57 and cfg 3, more accurate gens, better limbs and fingers, but gives a bit weird grain on very small details + plus this method is pretty long --Qwen Works perfectly and much better then other versions. Gives extremely "live" images with amateurish quality with dramatic light and shadows, some blur and with vibe of 2000s street photography You can take workflow here Thanx to . i understood that it's possible (and even have better effect) to use lora with values 1.5 - 2.0. P.S.: almost all example images generate with both loras (NiceGirls) --Wan This is the first release — mainly a test to explore Wan's capabilities. Note: In this initial version, facial details are somewhat lacking. For better results, I recommend using it alongside the by my friend, which significantly enhances facial features. --Flux Who needs a fancy name when the shadows and highlights do all the talking? This experimental LoRA is the scrappy cousin of my Samsung one—same punchy light-and-shadow mojo, but trained on a chaotic mix of pics from my ancient phones (so no Samsung for now)
Trigger words
l3n0v0
8,338 downloads · 589 likes on Civitai
SHA256
670508BBB8C6111ED9FFC46A6C3D08C0D37F702F14EC2C47007314A62C7E3A99
ModelTrends.ai Model ID
#15476
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
Euler Simple
Steps
24
Guidance
5
Seed
88888888888888
Size
NonexNone
Prompt
"T5XXL",A detailed high resolution cinematic photograph. A starkly composed monochrome photograph depicts the bustling interior of a fire station dispatch office, bathed in a diffused daylight that streams through large windows to the left, casting long shadows across the polished control panel dominating the foreground. A woman with short, styled hair, dressed in a practical blouse and high-waisted trousers, is absorbed in her work at the desk, her posture suggesting both attentiveness and weary familiarity; she’s casually perched on a chair with her legs crossed. Behind her, slightly elevated, stands a uniformed fireman, his cap casting a shadow over his face as he observes the activity with quiet authority. The room itself feels compact yet functional, filled with an array of analogue telephone switchboards, calculators, and control panels – a web of wires and dials hinting at the constant flow of urgent communication. Through the open doorway, a large red fire engine looms, partially obscured by shadow, its presence suggesting imminent action and a sense of contained energy; the vehicle's form is robust and powerful, yet softened by the gentle light. The overall mood is one of quiet efficiency and understated drama, capturing a moment suspended between routine and response in a distinctly 1970s aesthetic."Clip-l",female operator, dispatch center, fireman in background, vintage switchboard, rotary phones, analog equipment, mid-century, 1970s, black and white photograph, indoor scene, fluorescent lighting, utilitarian interior, busy workspace, focused attention, practical clothing, side view, medium shot, documentary photography, high contrast, realistic detail, professional setting, organized chaos, functional design.<lora:Natural Realism.safetensors:0.3500000000000001:0.3500000000000001> <lora:Pandora-RAWr.safetensors:0.25000000000000006:0.25000000000000006> <lora:fluxlisimo_aura_v2-FLUX.safetensors:0.25000000000000006:0.25000000000000006> <lora:fluxlisimo_v4_lora_FLUX.safetensors:0.25000000000000006:0.25000000000000006> <lora:fluxskin/Detailed Skin&Textures Flux V3.safetensors:0.15000000000000002:0.15000000000000002> <lora:SameFace_Fix.safetensors:-0.3500000000000001:-0.3500000000000001> <lora:age_v1.safetensors:0.25000000000000006:0.25000000000000006> <lora:IDunnohowtonameLora.safetensors:0.3500000000000001:0.3500000000000001>
Negative prompt
deformed, bad anatomy, plastic skin, waxy skin, overly smoothed, oily skin, unnatural highlights, cartoon skin, distorted features, imperfect tone, smile, symmetry, big boobs, shiny skin, abstract, nipples,
Settings
Size
1800x1184
Prompt
l3n0v0. BMW E39 and Mercedes C-class drifting in tandem on a rain-slicked asphalt road at night, thick white smoke billowing from the tires, neon signs reflecting off the wet pavement creating vibrant streaks of light, dynamic low-angle perspective capturing the cars' aggressive stance. amateur quality, candid style
Settings
Sampler
DPM++ 2M
Steps
60
Size
1504x992
Prompt
l3n0v0. Serene lake landscape, autumn morning, bare deciduous trees lining shoreline, golden sunlight breaking through branches, tall dried reeds and cattails at water's edge, calm water surface with light and cube reflections, fallen autumn leaves covering ground, dark silhouettes of trees against misty sky, natural outdoor setting, muted autumn colors, overexposed lighting near horizon, soft morning mist, low contrast atmospheric conditions, huge glossy reflective 3 metal cubes are floating above the water in the air and casting dark shadow onto the water, one cube is blue, second cube is red, third cube is green; slight lens flare visible. amateur quality, candid style
Settings
Sampler
DPM++ 2M
Steps
100
Seed
873541362456633
Size
1264x1688
Prompt
l3n0v0. A teenage girl stands outdoors during sunset in an industrial or urban area. She has platinum blonde, voluminous hair, very fair skin, and green eyes. She is wearing a black jacket and earrings and is facing the camera with a slight smile. The sun is low in the sky, positioned behind her to the left. The sunlight hits the left side of her face and hair, producing a warm, golden glow. The right side of her face is in hard shadow and underexposed. The lighting creates strong contrast between lit and shadowed areas of her face. The background includes a gravel or dirt-covered lot and midground warehouse-type buildings. A large electrical transmission tower is visible in the distance. The sky is orange and gold with scattered clouds. The sunset light casts long shadows across the scene. amateur quality, candid style
Settings
Size
2592x1696
Prompt
l3n0v0. wide-angle 18 mm interior shot, deserted shopping-mall corridor after closing time, rows of closed metal roller shutters, “You shouldn't be here” signage half-lit, lonely potted plant for scale, moody tungsten floodlights casting deep orange glow and long shadows, pockets of near-black darkness at the edges, soft volumetric beam slicing through dust motes, early-2000s CCD sensor vibe with slight noise and bloom, low-key cinematic lighting, mirror’s-edge-meets-y2k minimalism, gritty urban isolation mood. amateur quality, candid style
Settings
Size
1688x1264
Prompt
l3n0v0. closeup portrait of teenager girl, blue eyes, black long hair, she is showing piece sign, relaxed expression. Railroad tracks stretching into distance, parallel electrified lines overhead, wooden utility poles with power cables, concrete barriers with graffiti on both sides, dirt path alongside tracks, green trees visible, industrial buildings in far distance, bright blue sky with white puffy clouds, late afternoon natural lighting, urban industrial setting, weathered concrete posts in foreground, gravel railway bed, abandoned industrial appearance, natural spring daylight, wide-angle perspective. amateur quality, candid style
Settings
Size
1800x1184
Prompt
l3n0v0. ultra-wide pov, from ground view angle, lush tropical archipelago, towering jungle-covered cliffs and dramatic rocky outcrop dropping into a turquoise lagoon, ivory crescent beache along the shoreline, crystal-clear water reflecting cotton-candy cumulus clouds, sun-bleached dirt path snaking through dense emerald foliage, distant bamboo huts barely visible through the canopy, intense high-noon sunlight casting dramatic bloom and lens flare over the scene, deep shadows enveloping the foreground for contrast, subtle heat shimmer rising from treetops, gentle coastal breeze swaying palm crowns, early-2000s digital camera aesthetic with soft sensor grain and chromatic edges. amateur quality, candid style
Settings
Sampler
DPM++ 2M Karras
Steps
20
Guidance
1
Seed
1034390214815658
Size
2048x2048
Prompt
l3n0v0. ultra-wide pov, from ground view angle, lush tropical archipelago, towering jungle-covered cliffs and dramatic rocky outcrop dropping into a turquoise lagoon, ivory crescent beache along the shoreline, crystal-clear water reflecting cotton-candy cumulus clouds, sun-bleached dirt path snaking through dense emerald foliage, distant bamboo huts barely visible through the canopy, intense high-noon sunlight casting dramatic bloom and lens flare over the scene, deep shadows enveloping the foreground for contrast, subtle heat shimmer rising from treetops, gentle coastal breeze swaying palm crowns, early-2000s digital camera aesthetic with soft sensor grain and chromatic edges. amateur quality, candid style
AI Models for Image, Video & Text Generation
ultrareal flux is a LoRA for the Flux family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Flux 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