Model
Trends
.ai
Model
Trends
.ai
the best open source ai models
Run Locally
Adjust_details_AND_photorealism_-_Krea2_krea2_3275772_epoch_10.safetensors
218 MB · SafeTensor · bf16
Downloads are served by Civitai. Some creators ask for a Civitai login first.
AD
Install / Run on Graydient
Requires membership
<adjust-details-krea2>
About This Model
KREA2 · LoRAs
Created by
maxxxx_civitai
on Civitai
by maxxxx_civitai - Adjust details AND photorealism - V9.0 ULTRA further improving realism, color grading, sharpness, details, composition, lighting, epicness
Creator notes
v9.0 ULTRA Can we make this lora even cooler? Yes! ULTRA brings a new depth to the lora, further improving: - realism - color grading - sharpness - details - composition - lighting - epicness What is more, both Positive and Negative directions make sense, you can see examples in the gallery. Strength: - around 1.00 to 2.00 - or -0.50 to -1.00 Enjoy, have fun, and share your creations : -) v9.0 This version is more epic, more rich in details, plus it was trained for both illustrations and realistic photos. Trigger: - not needed but... - the lora was trained with this set of tags and description: 'improved, photo, photorealistic, cinematic, detailed, intricate, sharp, refined, rich textures, fullness,' 'The image is filled with intricate finely detailed textures with every surface object and background element appearing sharp textured and realistic. The composition is rich and full avoiding emptiness and emphasizing both quantity and quality of details' - these can be used to enhance the effects of the lora alone - but might get great results without it too Strength: - usually best around 1.00-1.5 but often 2.00 has the richest details (sometimes thoough less sharp) Enjoy! v8.0 This model has mode details and richer backgrounds compared to v7.0. Trigger: - No trigger is needed - if you want to have extra improvements, use these expressions: improved, high_detail, rich_background - the no trigger prompt will be closer to the original image, if you use these extra tags, it will be a bit further but you will get extra details Strength: - between 1.00 to 1.5 seems to be best for SDXL - between 0.25 to 2.0 seems to be best for ILL, 0.25 works already nicely - both positive and negative strength works!!! POSITIVE strength adds more details, NEGATIVE strength means less details but more creativitiy - experiment with both Have fun! v7.0 This model goes back to the original roots to create adjustments. if you want to have a richer background, just add 'simple background' to the negatives, the lora will amplify its effect SDXL - Strength: - both negative and positive works - you might start -0.30 or +0.30 and go from there, it seems to be the most optimal range but you can go up and low as -2.00 and +2.00 - beyond a certain negative strength the images will have lower and lower level of details and realism which opens the room for creativity - see example in the gallery PONY - Strength: - both negative and positive works - in case of realistic checkpoints, you can go to -1.00 or even further, it will still be able to create good quality images. In case of anime-style checkpoints you can still use the negative side, it will be even less real than normally - this works until -0.5 to -1. - but on the positive side you can go up to +2.00. Most of the time the real magic happens around 2.00 : -) - you might go even up to 2.50 or 3.00, in many cases it will be creating still good and even more detailed reasults (see examples in the gallery) - the level of intricate details above 1.5 strength is simply INSANE! Good exploration, have fun! v6.0 The two versions of v6 v6.a and v6.b are both based on the same database but went trhough a little bit different training path. This means that these are two different versions and sometimes you will like v6.a sometimes v6.b. Check the galleries and see for yourself :) This version has lost some of the porn aspects knowledge but learnt to give more details and depth of field, plus bigger changes. Strength: - Both negative and postive work - usually works until -1.00 more or less - on the postive side it might go up until 1.50-2.00 even Enjoy! v5.0 The v5 brings a lot of changes, it is the mixture of the earlier two systems. This model usually does the followings when in the positive or negative range: - POSITIVE: focus on sobject, creates more creative changes, adjusts realism, zooms in - NEGATIVE: focus on the background, zooms out, less realism yet still a lot of creative changes You might want to use it between -1.0 and 1.0 most of the time, you can start around -0.5 and 0.5 to and see where you want to go from there. Make sure to use both directions and check the sample images for both direstions! This is definetely NOT a "positive strength only" lora :-)) v4.0 The v4 goes back to the roots of the series where the bigger the number the stronger the change and stronger the realism (up to +1.50-2.00) whereas smaller numbers (up to -2.00) means more anime style/less realistic/less detailed images. The lora is not perfect, sometimes gives low-res or pixelated results, be warned (when using with FLUX and SDXL). On the other hand it is in many aspects the best version of the series, so it is definetely worth sharing it. This version has kept many of main category tags from duo versions where the effects are stronger and has some new additions: - battle, steampunk, cyberpunk, car, robot, medieval, female model, modern female hairstyle, male model, modern male hairstyle, flaccid penis, uncut penis, cum, cum on face, cum on body, anal sex, oral, sucking, fucking (ie. vaginal sex), vagina, pov, cum in mouth, handjob, asshole, anus, fingering, bukkake, dildo, group blowjob, group sex, licking, rimming, flying machines, floating city/space, (futuristic) car, (futuristic) soldier, robot. The checkpoint will create images with intricate details and detailed background and it excels with Pony. Strength SDXL/FLUX: - -2.00 will do strange things but it still works there, not really meaningful above +1.5 - in general you want to work between -1.5 to 1.5 based on how simplistic OR how realistic/detailed you want the image to be. - see different strength examples in the gallery Strength PONY: - the model has a strongest affect on PONY, even the smallest sthrength can have visible adjustments - 0.5 seems to be already a very strong strength, creating 3D-realistic images, 1.00 brings this to the level of very cl
829 downloads · 93 likes on Civitai
SHA256
C95914A57A83B8F14FEAF56C6901510709D3D314B3BC10FF6860DE331338ACB8
ModelTrends.ai Model ID
#27242
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
Steps
8
Guidance
1
Seed
2028268353
Size
928x1152
Prompt
Epic fantasy fighting scene, award winning, clashing weapons, cinematic moment, highly-detailed. Angel woman versus Demon man, Holy_Sword versus Burning_Axe, Light versus Darkness. Depict a dynamic mid-air clash featuring an angel wielding a massive, glowing white axe radiating ethereal light, and a demon gripping a colossal, fiery axe engulfed in a blazing aura. Both characters are in intense action poses with fierce expressions, shouting amidst the chaos. The angel boasts radiant white wings and intricate, shining armor, while the demon has tattered black wings and dark, detailed armor. Holy light, female angel, halo, holy sword on the right side. Demon man, burning axe, fire on the left side.
Settings
Sampler
euler
Steps
8
Guidance
1
Seed
2028268353
Size
928x1152
Prompt
A striking close-up portrait of a young woman in a cyberpunk world. She has glowing cybernetic eyes, sleek metallic implants along her temples, and soft neon light reflecting off her skin. Her hair is slightly windswept, catching highlights from the city’s ambient neon. Every detail—from skin pores to the texture of the implants—should be rendered with extreme realism, in a dark futuristic setting with vivid lighting accents in pinks, blues, and purples.
Settings
Sampler
euler
Steps
8
Guidance
1
Seed
1050247322
Size
1024x1024
Weight used
0.5
Prompt
(masterpiece, best quality, amazing quality, very aesthetic, extremely detailed, very detailed, incredibly absurdres, newest, highres, score_9, score_8),face focus, sharp focus on face and eyes, unobstructed face, eyes fully visible, finely detailed face, delicate facial features, balanced facial proportions, well-defined facial contours, detailed irises, clear pupils, clean sclera, natural catchlights, finely detailed eyelashes, softly defined eyelids, refined lips, soft skin, subtle facial shading, softly lit face, gentle facial highlights, no shadow over the eyes, Ephemeral_Elegance, DeathWolf, anthro wolf, male, white fur, red glowing eyes, black sclera, sharp features, muscular, pearl blades, pale blue and white hanfu, flowing translucent sleeves, sitting beside a lotus pond, one knee raised slightly, body leaning forward, fingertips touching the surface of the water, looking down at his own reflection, quiet expression, large translucent lotus flowers surrounding him, black koi swimming beneath the surface, scattered dark petals floating on water, distorted reflection of him face and moonlight in ripples, moonlit night garden, stone lantern in distant background, mist hovering over water, soft silver rim light, reflected red light illuminating his face from below, hanging willow branches framing the scene, delicate water droplets, blurred foreground lotus petals, poetic poster composition, tranquil but mysterious atmosphere
Settings
Sampler
euler
Steps
8
Guidance
1
Seed
2028268353
Size
928x1152
Prompt
A close-up portrait of an insanely handsome 25-year-old male model college student, captured with cinematic lighting. The image is highly detailed, showing every pore and strand of hair with photorealistic clarity. His facial features are sharp and well-defined, with realistic shadows and natural skin texture. Looking at viewer,
Settings
Sampler
euler
Steps
8
Guidance
1
Seed
2028268353
Size
928x1152
Prompt
improved, photo, photorealistic, cinematic, ultra detail, photographic quality, realistic. 25 yo beautiful female fashion model posing for fashion shooting, extravagant clothing, extravagant make-up, luxury loft, head and shoulders shot, looking at viewer
Settings
Sampler
euler
Steps
8
Guidance
1
Seed
945394864
Size
1024x1024
Weight used
0.5
Prompt
AASML_LUX, masterpiece, best quality, amazing quality, highres, absurdres, newest, DeathWolf, anthro wolf, male, white fur, red glowing eyes, black sclera, sharp features, muscular, upper_body, portrait, close-up, three-quarter view, reaching one hand toward the viewer, the other hand near a crystal mirror reflecting himself, looking_at_viewer, serious expression, slightly somber, shoulders turned, upper body leaning forward slightly, dynamic interaction pose, long fur, reflective fur, ruby eyes, black poncho, red thunder like particles, translucent_fabric, bare_shoulders, rough blade, elegant clothing, robe floating in the air, wind, luminous_particles, sparkling_dust, black glowing_fragments, holographic_reflections, dreamlike_city_lights, abstract_background, blurred_lights, reflective_crystals, prismatic_light, chromatic_aberration, bloom, soft_focus, volumetric_lighting, soft_overhead_light, ambient_glow, backlighting, strong_rim_light, light_through_hair, light_through_fabric, reflected_light, subsurface_scattering, deep_grey_lighting, red_glow, faint_purple_lighting, warm_cool_contrast, delicate_shadows, luminous_atmosphere, ethereal, cinematic_lighting, atmospheric_perspective, artistic, key_visual, poster, cinematic_composition, gothic style
Settings
Sampler
euler
Steps
8
Guidance
1
Seed
2028268353
Size
928x1152
Prompt
The image shows a futuristic warrior in a city at night. The warrior is in a crouching position holding a sword with a pink and purple flame-like design on it. He is wearing a black suit with a hood and a helmet with a visor. The background is filled with neon signs and buildings and the street is lit up with colorful lights. The overall mood of the image is dark and intense with a sense of power and power. The image appears to be a digital illustration that captures the character in action, improved, photo, photorealistic, cinematic, detailed, intricate, sharp, refined, rich textures, fullness, The image is filled with intricate finely detailed textures with every surface object and background element appearing sharp textured and realistic. The composition is rich and full avoiding emptiness and emphasizing both quantity and quality of details,
Settings
Sampler
euler
Steps
8
Guidance
1
Seed
2028268353
Size
928x1152
Prompt
Close-up of a joyful Labrador puppy’s face, filled with happiness and excitement as it plays in the snow. The puppy’s eyes are bright and full of life, sparkling with energy, and its mouth is slightly open in a playful grin, showing its tongue. Snowflakes gently dust its soft, golden fur, and a few cling to its nose. Its ears are perked up, and there’s a visible sense of movement as if it’s in mid-play. The background is blurred with a soft winter atmosphere—perhaps a few trees or the hint of a snow-covered landscape. The puppy’s expression radiates pure joy and contentment, capturing the essence of a carefree moment in the snow.
AI Models for Image, Video & Text Generation
adjust details krea2 is a LoRA for the Krea2 family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Krea2 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