Model
Trends
.ai
Model
Trends
.ai
die besten Open-Source-KI-Modelle
Lokal ausführen
anima-base-1-light-concepts-v31.safetensors
142 MB · SafeTensor
Downloads werden von Civitai bereitgestellt. Manche Ersteller verlangen zuerst eine Anmeldung bei Civitai.
AD
Auf Graydient installieren / ausführen
Mitgliedschaft erforderlich
<light-concepts-anima>
Über dieses Modell
ANIMA · LoRAs
Erstellt von
motimalu
auf Civitai
By motimalu - Used to enhance the lighting of generations or give interesting effects. Works best in combination with NL if you name a character, describe their basic appearance, and finish with descriptions of light sources and their effects on the scene
Notizen des Erstellers
Light Concepts Training data is a collection of various light concepts I enjoy using that are not overly represented in large datasets, trained as a single lora. ℹ️ LoRA work best when applied to the base models on which they are trained. Please read the About This Version on the appropriate base models and workflow/training information. I've trained many of these concepts before, generally they are nice to use to enhance the lighting of generations or give interesting effects. Trained on a large mixed NL and tags dataset, at mixed [1024, 1536] resolutions. Previews are mostly generated at 1024x1536 with a combination of tags and NL prompts. Concept tags Not limited to, but collected by works containing: dispersion hue shifting refraction subsurface scattering translucent bioluminescence caustics dappled moonlight glowing hot ultraviolet light Works best in combination with NL if you name a character, describe their basic appearance, and finish with descriptions of light sources and their effects on the scene: A vibrant and dynamic illustration of Hoshimachi Suisei from Hololive, featuring her squatting in front of a glowing triangular prism. A beam of white light enters the prism from the left and refracts into a vibrant rainbow on the right. The background is a solid dark grey to emphasize the lighting effects.
Triggerwörter
dispersion
hue shifting
refraction
subsurface scattering
translucent
bioluminescence
caustics
ultraviolet light
6,545 Downloads · 510 Likes auf Civitai
SHA256
98AFA7627640814006B5B1CC1C2EE024DEBA411E2810BBB9620F076D6282DB41
ModelTrends.ai-Modell-ID
#25466
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
er_sde
Schritte
32
Guidance
4.5
Seed
982586925
Größe
832x1216
Verwendetes Gewicht
0.75
Prompt
masterpiece, best quality, score_7, The image is a digital illustration rendered in a detailed, high-contrast style, with a strong emphasis on silhouette and reflection. The subject is a young woman with long, flowing blonde hair and a slender, smooth face, viewed from the side. She is wearing reflective sunglasses that magnify the cityscape behind her, creating a striking visual effect. The cityscape, visible through the sunglasses, shows a bustling urban environment at sunset, with tall skyscrapers and buildings in various shades of blue and gold, reflecting the warm hues of the setting sun. The woman's face is depicted in stark black silhouette, with her hair and sunglasses the only elements in color, creating a dramatic contrast against the dark background. The sunglasses have a sleek, oval shape with thin frames and a reflective surface that mirrors the cityscape perfectly. Her hair is styled in loose, flowing waves, with bangs framing her face. The background is a deep, almost black, creating a strong contrast that highlights the vibrant colors and detailed textures of the cityscape reflection. The overall style combines elements of digital art with a manga-inspired aesthetic, typical of high-quality anime illustrations. The image captures a sense of cool, urban sophistication.
Negativer Prompt
worst quality, low quality, score_1, score_2, score_3, artist name, (bad quality, worst quality, low quality), jpeg artifacts, poorly drawn, simple background, patreon, twiter, onlyfan, instagram, lowres, error, missing fingers, signature, watermark, username, out of focus, blurry, bad proportions, bad anatomy, bad hand, bad face, out of frame, cut off, censored, duplicate, deformed, glitch, low contrast, noisy, ugly, worst aesthetic, scan artifacts
Einstellungen
Sampler
ER SDE
Schritte
40
Guidance
4
Seed
993140916
Größe
1168x2048
Clip skip
2
Prompt
masterpiece, best quality,highres, score_7, score_8, score_9,year 2023, year 2024, year 2025,@YujinHare, cinematic composition, painterly texture, atmospheric depth, fantasy illustration, semi-realistic anime painting, elegant brushwork, dreamy cinematic atmosphere, soft painterly rendering, delicate color transitions, expressive cloud painting, poetic visual storytelling two graceful young women standing on a flower-covered hillside, vast summer sky filled with gigantic towering cumulus clouds, rolling meadow with red wildflowers and tall grass, wind blowing through hair and clothing, one woman in flowing blue traditional-inspired dress with open arms, another woman in pale green long dress holding flowers, distant perspective, low-angle composition, enormous sky dominating the scene, tiny human figures against majestic nature, emotional and nostalgic mood, dynamic grass movement, flowing ribbons and fabric, natural environment, open landscape, serene fantasy atmosphere golden hour sunlight, warm sunset glow on clouds, soft rim lighting, diffused ambient light, dramatic cloud shadows, subtle volumetric lighting, luminous cloud edges, soft haze, rich sky contrast, gentle warm highlights, cinematic color grading, airy atmosphere, peaceful summer lighting <lora:Yujin Hare v1:1> <lora:anima-base-1-light-concepts-v31:1>
Negativer Prompt
worst quality, low quality, score_1, score_2, score_3, artist name
Einstellungen
Sampler
DPM++ SDE
Schritte
45
Guidance
5
Größe
1920x2400
Prompt
unknown
Einstellungen
Sampler
ER SDE
Schritte
26
Guidance
4
Seed
2995932649
Größe
768x1152
Prompt
masterpiece, best quality, very aesthetic masterpiece, best quality, absurdres, very aesthetic, score_7, nazgul, the lord of the rings, solo, upper body, glowing red eyes, black robe, hood, gauntlets, holding sword, shaded face, blurry foreground, perspective,<lora:anima-base-1-masterpiece-v51_2961717:1> <lora:anima-base-1-light-concepts-v31_2952873:1> dispersion, bioluminescence,
Negativer Prompt
worst quality, low quality, jpeg artifacts, blurry, bad anatomy, distorted anatomy, bad hands, missing fingers, extra digits, fused fingers, deformed eyes, cross-eyed, text, watermark, signature, username, web address, 1girl, nose, mouth, mask,
Einstellungen
Sampler
Euler a_simple
Schritte
15
Guidance
4
Seed
1095374065066068
Größe
1248x1824
Clip skip
1
Prompt
@goosing, masterpiece, best quality, amazing quality, very aesthetic, extremely detailed, absurdres, highres, score_9, score_8, newest, 1girl, adult, catgirl, cat ears, cat tail, short hair, mint hair, pink eyes, pleated skirt, standing, adjusting a pleat, rooftop, morning, painterly anime. Mint-haired catgirl on a rooftop water tank, fussing one pleat back into line, pink eyes on her own knee. The pleated skirt hangs to mid-thigh and behaves. Tail as counterweight. Morning concrete. Adult, off-work, not a student. Wind tries and fails. She smooths the knife-folds until they look expensive again. <lora:anima-base-1-masterpiece-v51:1.0> <lora:anima-base-1-light-concepts-v31:1.0> <lora:Goosing:1.0>
Negativer Prompt
score_1, score_2, score_3, bad anatomy, bad proportions, deformed anatomy, deformed face, deformed eyes, multiple fingers, shiny skin, loli, young, censored
Einstellungen
Sampler
er_sde beta
Schritte
50
Guidance
4
Seed
924302602899888
Größe
2640x4688
Prompt
, @a5h1ma, 1girl, solo, long brown hair, hair tucked behind ear, loose hair, brown eyes, looking at viewer, calm expression, soft smile, slight blush, resting chin on hand, leaning on window, white turtleneck, oversized beige cardigan, upper body, sitting, train interior, passenger cabin, train seat, window, window frame, train window, scenery outside, outdoors, afternoon, sunlight, window light, warm lighting, sunbeams, rim light, depth of field, blurry foreground, (blurred train handle:1.2), bokeh, film grain, lens flare, soft focus, cinematic composition, nostalgic atmosphere, peaceful, A quiet girl sits in a sunlit train cabin, leaning softly against the large window and resting her chin on her hand while looking at the viewer. Warm afternoon sunlight pours through the glass, illuminating her white turtleneck and casting gentle rim light on her brown hair. The passing city scenery outside the window melts into beautiful bokeh, while a heavily blurred train handle in the foreground adds a strong sense of depth. The scene is filled with a nostalgic and peaceful atmosphere, enhanced by soft film grain and subtle lens flares., , masterpiece, best quality, amazing quality, highres, absurdres, newest, very awa <lora:ashima_v4:1.0> <lora:anima-base-1-masterpiece-v51:1.0> <lora:anima-base-1-light-concepts-v31:1.0> <lora:anima-base-1-photo-background-v4:0.8>
Negativer Prompt
lowres, bad anatomy, bad hands, error, missing finger, extra digits, fewer digits, ear tag, cropped, worst quality, low quality, low score, bad score, average score, signature, watermark, username, normal quality, bad anatomy, low resolution, score_3, score_2, score_1, bad perspective, bad proportions, censored, mosaic censoring, bar censor, artist name, footprints
Badges for creators
Made this model? Put its standing on your Civitai page, your Hugging Face card, your README or your site. Each badge is a small picture that shows the standing on the day you copy it and never changes afterwards, however the rankings move later. The date is part of the badge.
light concepts on ModelTrends.ai: #293 of 16,523 AI models
light concepts on ModelTrends.ai: #5 of 365 Anima models
light concepts on ModelTrends.ai: #5 of 353 Anima LoRAs
KI-Modelle für Bild-, Video- und Texterzeugung
light concepts anima ist ein LoRA für die Familie Anima und wird auf ModelTrends.ai gelistet, einem reinen Lesekatalog für Open-Source-KI-Modelle für Bild, Video und Text. Vergleiche es mit anderen Anima-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