Model
Trends
.ai
Model
Trends
.ai
die besten Open-Source-KI-Modelle
Start
/
KREA2
/
fantasy real refiner krea2
fantasy real refiner krea2
Vergleichen
8308°
Lokal ausführen
zjourneykreav1.safetensors
218 MB · SafeTensor · bf16
Downloads werden von Civitai bereitgestellt. Manche Ersteller verlangen zuerst eine Anmeldung bei Civitai.
AD
Auf Graydient installieren / ausführen
Mitgliedschaft erforderlich
<fantasy-real-refiner-krea2>
Über dieses Modell
KREA2 · LoRAs
Erstellt von
tsolful
auf Civitai
by tsolful - zjourney - Fantasy Realism Refiner
Notizen des Erstellers
zjourney - Fantasy Realism Refiner | Qwen 2.1 Update Focused on further grounding Fantasy outputs in photographic output. Trained on 44 film stills. Usage: Recommended strength: 0.5-0.6 Examples were generated with er_sde/beta. one with turbo lora at 6 steps 1cfg, other without 50 steps 2cfg zjourney - Fantasy Realism Refiner | Krea 2 Update Focused on further grounding Fantasy outputs in photographic "realism". Trained on 44 film stills. Usage: - Recommended strength: 0.8-1.4 Examples generated with filter bypass + zjourneykrea LoRA A lightweight LoRA trained on 44 curated images generated with the LoRA, built to refine Ideogram 4 fantasy outputs toward a more realism aesthetic. Why I made this: Ideogram 4 produces stunning fantasy art, but that's often the problem. No matter how I prompted it (photographic, photorealism, cinematic realism, etc.), fantasy subject matter almost always defaults to an illustrated or painterly art style. zjourney was built to push past that and ground those outputs in something that feels genuinely photographic. What it does: Refines Ideogram 4 outputs with richer photorealism, improving surface texturing, cinematic lighting, environmental depth, and material detail across fantasy and action subjects. It also works well as a general realism refiner beyond pure fantasy content. zjourney - Fantasy Realism Refiner | v2 Update V2 expands the training dataset, focusing on further grounding outputs in photographic realism. Trained on 44 film stills alongside 6 LoRA generations. Usage: - Standalone recommended strength: 0.55 0.35-0.6 - For best results, stack with v1: - v1 @ 0.35 + v2 @ 0.45 - First 2 example images generated standalone with v2 - Final 5 example images generated with v1 + v2 combined Key improvements over base Ideogram 4: - More detailed and grounded environments (ruins, foliage, wet stone) - Richer skin, fur, and fabric textures - Stronger cinematic color grading and atmospheric depth - More convincing crowd and secondary figure detail Known limitations: - Close-up shots with heavy focus on skin texture can see a slight degradation in quality, works best at mid-range and wider compositions Usage: - Recommended strength: 0.4–0.7 - Sample images generated at 0.5 - Works best alongside detailed fantasy or action prompts; can also be applied to general realism scenes - Works with and without trigger word, the trigger word was trained in the aesthetics placement in the json prompt structure
1,124 Downloads · 89 Likes auf Civitai
SHA256
5685942A68782E4A77BD4B28911E98E71B5D4F8B9CEE5291F71B1F4F4DCD803A
ModelTrends.ai-Modell-ID
#27141
Inhalt melden
Beispielbilder
Prompts und Einstellungen, geteilt von den Leuten, die diese Bilder auf Civitai erstellt haben. Wähle ein Bild, um zu sehen, wie es entstanden ist.
Einstellungen
Sampler
Euler
Schritte
10
Guidance
1
Seed
376511076208377
Größe
1248x1680
Prompt
zjourney, candid photo of a fiercely independent female dragon rider with messy, windblown ginger hair sharing an intimate, unstaged moment of rest with her colossal dragon on a windswept alpine crag. Her pale skin alight with a half-formed smile, the rider presses her forehead tenderly to the dragon's imposing, armored snout. She wears a heavily distressed, shearling-lined aviator jacket crafted from thick, dark-brown boiled leather, secured across her chest with tarnished brass buckles over a mud-splattered forest-green wool tunic. Filling the right side of the frame, the dragon features incredibly textured, overlapping scales that transition from deep, oxidized bronze to vibrant verdigris teal. Its giant, golden slitted eye is half-closed in peaceful contentment, while a faint, pulsing amber bioluminescence radiates from deep within its throat, casting a warm, fiery subsurface glow directly onto the rider's cheek and illuminating the stray strands of her bright copper hair. Thick curls of white steam hiss softly from the beast's jagged, carbon-scored nostrils, rolling over the rider's shoulders and mingling with the freezing, damp mountain mist. The tight medium close-up composition is framed at eye level and captured on 35mm vintage film stock with an 85mm portrait lens at f/2.0. This extremely shallow depth of field locks razor-sharp focus on the rider's joyful expression and the intricate, micro-cracked texture of the dragon's cheek scales, while the beast's sweeping, obsidian horns and the distant, jagged peaks of the cloudy mountain range dissolve into a smooth, cool-toned cinematic bokeh. The atmospheric lighting relies on soft, diffused cyan ambient daylight from a heavy overcast sky, beautifully contrasting with the localized, radiating internal heat of the drake. Masterful photorealistic detailing emphasizes the tiny droplets of condensation trapped in the rider's ginger hair, the frayed, dirty wool of her jacket collar, the microscopic ridges of the dragon's reptilian skin, and heavy optical film grain, delivering a deeply grounded, documentary-style slice of high-fantasy companionship.
Einstellungen
Sampler
Euler a
Schritte
8
Guidance
1
Seed
122522075217304
Größe
1584x1992
Verwendetes Gewicht
0.35
Prompt
Detailed Emotions and Expressions,
Einstellungen
Sampler
Euler
Schritte
8
Guidance
1
Seed
945105295372114
Größe
2048x3072
Prompt
A close-up portrait photo of a female elf in a dynamic pose, aiming a bow directly toward the viewer with one eye closed and the bowstring stretched across the middle of her face — she is not looking at the knocked arrow, her gaze fixed forward with intense focus — she has a cute, expressive face with soft features and perfectly straight, flowing hair that frames her face; she wears detailed armor decorated with natural leaf motifs, and a quiver rests on her back, subtly visible over her shoulder; the background is a lush, dense forest with dappled sunlight filtering through the canopy, creating depth and atmosphere; captured in highly detailed documentary photography using a 35mm lens on a professional full-frame camera, the image exhibits natural and vibrant lighting, realistic exposure, deep contrast, and rich, saturated colors, rendered in an authentic photojournalistic style with sharp focus on the subject’s face and bow while the background remains softly blurred to emphasize her presence. zy_cinematic, dndstyle.
Einstellungen
Sampler
Euler
Schritte
10
Guidance
1
Seed
252924719160792
Größe
1408x1872
Prompt
zjourney, candid photo of a wide tracking shot taken from a chase camera flying alongside a colossal white and gold dragon in high-speed flight. The horizontal composition captures the massive scale of the beast relative to its rider. In the foreground, the dragon's giant head is fully visible, covered in matte, calcified ivory scales with visible dirt in the crevices, and weathered, bone-like gold horns with tiny chips. Its intelligent, watery gold eye is squinted against the wind. Seated in a heavy, weathered saddle on the dragon's muscular shoulders, the helmetless female knight has messy, tangled ginger hair whipping across her wind-reddened face, eyes focused ahead. Her unpolished steel plate armor is scuffed and coated in high-altitude frost, her leather-gloved hands gripping thick, coarse reins. Below them, a dizzying, distant expanse of snowy mountain ridges and pine forests slides past, partially obscured by rushing cloud banks. The camera lens has tiny water droplets and dust on the glass from the clouds. Shot on 70mm film with an anamorphic wide-angle lens, featuring natural optical imperfections, slight motion blur from the speed, chromatic aberration near the frame edges, and heavy, organic film grain that gives the image a gritty, tactile, archival documentary quality.
Einstellungen
Sampler
Euler
Schritte
10
Guidance
1
Seed
376511076208377
Größe
1248x1680
Prompt
zjourney, candid photo of a frantic, multi-character fantasy ambush erupting in a narrow, rain-slicked red sandstone slot canyon. In the right foreground, a heavily scarred dwarven paladin is caught in a desperate mid-brace, aggressively angling a massive, dented steel kite shield upward to deflect a plunging aerial attack. He wears mud-caked, overlapping brass plate armor over a soaked chainmail hauberk, his thick auburn beard heavy with rainwater. Directly above him, violently frozen mid-leap off the canyon wall, a feral goblin assassin strikes downward with dual jagged, rusted iron daggers that spark brilliantly against the paladin's steel shield. The goblin wears tightly wrapped, waterlogged black leather bandages, its yellow slitted eyes wide with manic aggression. In the left midground, a fiercely focused tiefling warlock with sweeping obsidian horns and glowing magenta eyes pivots sharply to counterattack. She is clad in torn, heavy indigo velvet robes clinging wetly to her dark crimson skin, her outstretched palm erupting with a crackling, blinding blast of electric-blue magical lightning. The kinetic, low-angle composition is shot on high-speed 35mm film with a wide 24mm lens at f/4, utilizing an ultra-fast 1/4000s shutter speed to perfectly freeze the torrential, sideways rain, flying droplets of brown mud, and the explosive shower of hot orange sparks. The lighting is fiercely dramatic and dual-toned: the searing, cool cyan illumination from the warlock’s lightning bolt aggressively cross-lights the wet red canyon walls and casts sharp, jagged shadows across the paladin’s face, fiercely contrasting with the warm, localized amber glow of the striking metal. Masterful photorealistic detailing highlights the microscopic water droplets exploding off the dwarf's polished brass pauldrons, the deeply oxidized pitting on the goblin's crude blades, and the heavy, saturated weave of the tiefling's ruined velvet coat, delivering a raw, visceral documentary snapshot of deadly, high-stakes fantasy combat.
KI-Modelle für Bild-, Video- und Texterzeugung
fantasy real refiner krea2 ist ein LoRA für die Familie Krea2 und wird auf ModelTrends.ai gelistet, einem reinen Lesekatalog für Open-Source-KI-Modelle für Bild, Video und Text. Vergleiche es mit anderen Krea2-Modellen, prüfe den Hitzewert, um den Trend zu sehen, und öffne es auf PirateDiffusion oder BitVector, um es auszuprobieren.
Nach Modellfamilie stöbern
Alle Modelle ansehen