Rulează local
afterdark2_klein.safetensors
158 MB · SafeTensor
Descărcările sunt servite de Civitai. Unii creatori cer mai întâi autentificarea pe Civitai.
Despre acest model
FLUX 2 / KLEIN · LoRA
by HackAfterDark - AfterDark
Notele creatorului
AfterDark for Krea 2, Z-Image Turbo & Flux.2 Klein
This LoRA enhances your images with more punch, contrast, depth of field, and lighting. It's been trained on a mixture of photographic content with a focus on low-key, film noir, and fashion photography. It makes things pop without destroying image quality (in fact, it often enhances quality).
Suggested Krea 2 Turbo Settings
Model strength: 0.5-0.9
Samplers/schedulers:
-
dpm_2_ancestral / ddim_uniform (or sgm_uniform)
-
exp_heun_2_x0 / ddim_uniform
-
euler / beta57 (or beta)
Suggested Z-Image Turbo Settings
Model strength: 0.3-0.8
Samplers/schedulers:
-
seeds_3 / beta
-
ddim / kl_optimal (or beta)
-
dpm_2_ancestral / sgm_uniform (or ddim_uniform)
Suggested Flux.2 Klein 9b Settings
Model strength: 0.3-1.2
Samplers:
-
res_multistep
-
sa_solver
-
seeds_3
-
er_sde
-
ddim
-
...and so many more
Distilled
Cfg Scale: 1-1.5
Steps: 8-10
Base
Cfg scale: 2.5-4
Steps: 40-55
This LoRA works with both Flux.2 Klein 9b base and distilled. I often use the distilled version because it generates images much faster and the quality is still really good.
v2 LoRA Technical Details
The Krea 2 Turbo LoRA ended up with a loss value of 0.09540. I took step 750, but did train to 1,500 steps and compared all of them. They all looked great so it wasn't an easy choice.
The Z-Image Turbo LoRA ended up with a loss value around 0.336 (this compares to v1 at around 0.71).
The Flux.2 Klein 9B LoRA ended up with a loss value of 0.5129 (5.129e-01). It was a "low and slow" train with a low learning rate (5.0e-05) over 6,000 steps. This was much longer than the Z-Image Turbo LoRA's training, but I think it was worthwhile. I might use a more powerful GPU next time (I used an A40 for this one).
A lot of training time went into these models followed by a lot of testing. I decided to keep the same model listing on Civitai simply because they were both trained from the exact same dataset (same images and captions). The training for the Klein version in ai-toolkit started off the same as the Z-Image one. I soon learned that wasn't going to work for Flux.2 Klein 9b so I adjusted the settings.
Version 2 is very stable for both base models. In fact I find that I don't often like the distilled version of Klein 9b without this LoRA. Images are generally too bright for my taste and while you could apply a LUT or do post processing work on the images, I simply prefer to use this LoRA because it does more than just lighting.
Cuvinte declanșatoare
4ft3rd4rk
SHA256
8B1D59F4221121581573CCC113ED81EC8DC3C5EBF3BED8F9DBBC42F880863182
ID model ModelTrends.ai
#24258
Semnalează conținutul
Exemple de randări
Prompturi și setări partajate de cei care au făcut aceste randări pe Civitai. Alege o randare pentru a vedea cum a fost făcută.
Setări
Pași
12
Seed
777673855
Mărime
832x1216
Pondere folosită
0.6
Prompt
A cinematic retro-futuristic illustration of a lone bounty hunter seated in the open doorway of a hovering helicopter above a vast neon-lit metropolis at night. The city below glows with dense grids of magenta, cyan, and violet lights reflecting through drifting mist and rain. The hunter sits at the edge of the open door, preparing for a dangerous mission, holding a heavy futuristic revolver across her lap, its chamber faintly glowing with energy rounds. She has long white hair moving in the wind, sharp blue eyes, and worn leather gloves gripping the weapon with calm focus. Slightly ahead inside the cockpit, the back silhouette of the helicopter pilot is visible against glowing instrument panels. Far below, a massive corporate skyscraper rises above the surrounding skyline — the crime boss’s fortress and her target, subtle red police lights flicker through streets. The perspective is slightly off to the side with a Dutch angle, emphasizing tension and motion. Retro synthwave cyberpunk atmosphere, vibrant neon contrasts, cinematic lighting, dramatic storytelling, graphic novel style illustration. The image is both epic and dramatic. best quality, high resolution, hyper-detailed, cinematic, centered, very aesthetic, accurate, award-winning composition, soft grain, evocative, artistic, immersive storytelling. 4ft3rd4rk, aidmamj6.1, ArsMovieStill, 80s Fantasy Movie Still
Prompt negativ
low quality, worst quality, casual, boring
Setări
Sampler
res_multistep
Pași
8
Guidance
1
Seed
432262096974488
Mărime
832x1248
Prompt
A portrait of a beautiful young woman with fiery red hair and freckles. She has a deep red lip and is wearing a sparkling teal top. Her skin is dusted with what appears to be snow or glitter. She's wearing a red bow in her hair. The lighting is soft and moody, with a teal and green color palette, creating a vintage or film-like aesthetic. The focus is on her face, and she's looking at the viewer with a sensual expression. The image has a dreamlike quality. 4ft3rd4rk
Setări
Sampler
res_multistep
Pași
8
Guidance
1
Seed
432262096974488
Mărime
832x1248
Prompt
Close-up portrait of a pale redheaded woman at golden hour, warm sunlight glowing through her curly auburn hair, soft freckles, natural makeup, bokeh background, cinematic look, 4ft3rd4rk
Setări
Sampler
er_sde
Pași
8
Guidance
1
Seed
732878166506245
Mărime
832x1248
Prompt
4ft3rd4rk A low-angle cinematic medium-full shot of a confident adult European woman, approx age 28, with glowing fair skin and long flowing auburn hair. She is wearing denim shorts, high heels, and a stylish sheer black top, fully clothed. She stands powerfully beside a weathered, rusted 1970s Dodge Charger R/T with faded paint and a license plate reading "BADGIRL". She holds a black 9mm pistol pointed safely upward, gazing intensely at the viewer. The setting is a gritty, atmospheric old gas station at night. The lighting is high-contrast and stylized, dominated by harsh fluorescent green overhead lights illuminating the dust motes and heavy shadows, with a distinct orange light leak streak cutting across the frame. Robert Rodriguez neo-noir grindhouse style, shot on Nikon F2 50mm, visible film grain, photorealistic texture, sharp focus. No nudity, no blurry details, no watermarks, no logos other than license plate, correct anatomy, realistic proportions.
Setări
Sampler
res_multistep
Pași
8
Guidance
1
Seed
432262096974488
Mărime
832x1248
Prompt
a woman in her late 30s, embodying a moment of quiet introspection at a vintage train station, captured in dramatic, low-key lighting cast from a single, overhead platform lamp that creates strong chiaroscuro effects. The photograph is taken with a Leica M11 camera and a Summilux-M 50mm f/1.4 ASPH lens. Set the aperture to f/2.0 for a shallow depth of field, rendering the woman and the worn leather of the suitcase she sits on in sharp detail, while the background train and billowing steam melt into a soft, romantic blur. The composition should be asymmetrical, placing the woman on the right third of the frame, using the wet railway lines as leading lines that disappear into the misty background. Adjust the shutter speed to 1/125s to ensure sharpness while capturing the ambient light. Set the white balance to produce rich, sepia tones, heavily emphasizing the rust-colored dress and earthy palette, while keeping shadows deep and blacks profound. Intricate interplay of light and shadow carves out the woman's features and the classic, pin-up style waves of her dark hair. The voluminous steam catches the lamplight, creating a volumetric, dreamlike haze that adds to the nostalgic, romantic feel. The texture of the worn suitcase leather and the wet sheen on the gray brick platform are rendered with hyper-realistic detail, evoking a powerful sense of time and place. The time of day is twilight. 4ft3rd4rk
Setări
Sampler
LCM
Pași
8
Guidance
1
Seed
210406765728508
Mărime
832x1248
Prompt
4ft3rd4rk An extreme close-up high-fashion photograph of an adult woman with a seductive look wearing an intricate black metal filigree masquerade mask adorned with small sparkling crystals. She has pale skin and is wearing glossy dark burgundy lipstick with her lips slightly parted. A hand with matching dark red fingernails is gently touching her face near the mouth.The lighting is dramatic and high-contrast chiaroscuro, with a strong, focused spotlight originating from the upper left casting shadows falling across the neck and side of the face. Realistic texture, 85mm macro lens, sharp focus on the lips and mask, plain dark muted background.
Setări
Pași
12
Seed
718576259
Mărime
832x1216
Pondere folosită
0.6
Prompt
A dystopian surreal landscape rendered in a painterly, textured illustration style with heavy brushwork, soft grain, and layered atmospheric depth. From a slightly elevated, almost observational angle, two female figures stand at the threshold of an immense labyrinth that stretches endlessly toward the horizon. The labyrinth is designed in a decayed Art Deco style—tall geometric walls, repeating arches, sharp symmetry softened by erosion, intricate patterns partially consumed by time.
The elf mage is slender and elegant, with pale luminous skin and long white hair flowing down her back, wearing layered arcane robes with subtle gold ornamentation and faint glowing sigils. Her posture is calm and focused, one hand slightly raised as if sensing the labyrinth’s energy. Beside her stands a human warrior, athletic and grounded, wearing worn but refined armor with engraved details, a cloak hanging behind her, one hand resting on the hilt of a sword, her expression alert and protective.
The environment dominates the composition: towering structures rise like monoliths in the distance, partially obscured by dense greenish fog. The sky is surreal and fractured, with visible gaps in space revealing strange light and void-like depths beyond reality. A strange large eye looks at them from a gap in space, observing. The ground near the foreground is saturated with intense color—deep crimson vegetation or mineral-like textures contrasting against cold teal and desaturated stone.
Soft volumetric light filters from above, creating glowing highlights along edges and subtle golden reflections within architectural details. The atmosphere is ominous yet mesmerizing, blending beauty and decay. Painterly gothic surrealism, vibrant but controlled color palette (emerald green, oxidized teal, muted gold, deep red accents), cinematic scale, dramatic depth, no CGI, traditional painting aesthetic, rich texture, epic dark fantasy storytelling, best quality. 4ft3rd4rk, aidmamj6.1, ArsMJStyle, Etherial Gothic
Prompt negativ
low quality, worst quality, casual, boring
Setări
Sampler
res_multistep
Pași
8
Guidance
1
Seed
271321947275669
Mărime
832x1248
Prompt
4ft3rd4rk Cinematic medium shot of an adult woman leaning against a door frame, one arm raised resting on her head, creating a dramatic silhouette. She appears to be a young adult with curly hair styled in a messy updo. She is wearing a fitted sleeveless crop top and denim jeans, fully clothed. The setting is a dark interior room looking through a doorway. The scene is defined by intense, warm volumetric lighting and god rays beaming through the opening, creating a golden orange haze and strong backlighting that puts the subject in shadow while highlighting her outline with rim light. Moody, atmospheric, introspective, and emotional. Realistic photography, grainy film aesthetic, high contrast, 35mm lens. High resolution, sharp focus. No text, no watermark, no logos, no blurry details, correct anatomy, no extra limbs.
Modele similare
Modele AI pentru generare de imagini, video și text
afterdark flux2 este un LoRA pentru familia Flux 2 / Klein, listat pe ModelTrends.ai, un catalog doar pentru citire al modelelor AI open source pentru imagini, video și text. Compară-l cu alte modele Flux 2 / Klein, verifică-i scorul de căldură pentru a vedea cât este de popular și deschide-l pe PirateDiffusion sau BitVector pentru a-l încerca.
Mai multe modele Flux 2 / KleinMai multe LoRA Flux 2 / Kleinlightingphotographyrealistickrea2filmz-imagelomodetail
Răsfoiește după familia de modele
Modele Text / LLM
411
Modele Anima
509
Modele Chroma
14
Modele Flux
1,071
Modele Flux 2 / Klein
1,237
Modele MiniMax H3
331
Modele Hunyuan
197
Modele Ideogram
20
Modele Krea2
674
Modele Qwen
17
Modele Qwen2
36
Modele Ltx2
150
Modele Stable Diffusion 1.5
6,465
Modele Stable Diffusion XL 1.0
15,432
Modele Zimage
804
Modele Wan
919

Model
Trends
.ai
© ModelTrends.ai
|
Realizat în Japonia
|
© 2026
