Model
Trends
.ai
Model
Trends
.ai
die besten Open-Source-KI-Modelle
Lokal ausführen
epicrealism_naturalSinRC1VAE.safetensors
1.99 GB · SafeTensor · fp16 · pruned
Downloads werden von Civitai bereitgestellt. Manche Ersteller verlangen zuerst eine Anmeldung bei Civitai.
AD
Auf Graydient installieren / ausführen
Mitgliedschaft erforderlich
<natural-sin>
Über dieses Modell
STABLE DIFFUSION 1.5 · Basismodelle
Erstellt von
epinikion
auf Civitai
VAE Natural Sin Final and last of epiCRealism by epinikion, a realistic base model. Notes from the creator: add "asian, chinese" to negative if you're looking for ethnicities other than Asian Light, shadows, and details are excellent without extra keywords If you're looking for a natural effect, avoid "cinematic, masterpiece, best quality, 8k, intricate, high detail" avoid using "1girl" since it pushes things to render/anime style to much description of the face will turn out bad mostly 512x768 or 768x512 recommended, then try upscaling with /more /size:1400x1400 /images:3 /strength:0.4 and then /facelift /photo
Notizen des Erstellers
Natural Sin Final and last of epiCRealism Since SDXL is right around the corner, let's say it is the final version for now since I put a lot effort into it and probably cannot do much more. I tried to refine the understanding of the Prompts, Hands and of course the Realism. Let's see what you guys can do with it. Thanks to for the in-depth , so i'd like to give some advices to use this model. [expand to see Advices] Advices - use simple prompts - no need to use keywords like "masterpiece, best quality, 8k, intricate, high detail" or "(extremely detailed face), (extremely detailed hands), (extremely detailed hair)" since it doesn't produce appreciable change - use simple negatives or small negative embeddings. gives most realistic look (check samples to get an idea of negatives i used) - add "asian, chinese" to negative if you're looking for ethnicities other than Asian - Light, shadows, and details are excellent without extra keywords - If you're looking for a natural effect, avoid "cinematic" - avoid using "1girl" since it pushes things to render/anime style - to much description of the face will turn out bad mostly - for a more fantasy like output use 2M Karras Sampler - no extra noise-offset needed, but u can if you like to 😉 How to use? Prompt: simple explanation of the image (try first without extra keywords) Negative: "cartoon, painting, illustration, (worst quality, low quality, normal quality:2)" Steps: >20 (if image has errors or artefacts use higher Steps) CFG Scale: 5 (higher config scale can lose realism, depends on prompt, sampler and Steps) Sampler: Any Sampler (SDE, DPM-Sampler will result in more realism) Size: 512x768 or 768x512 Hires upscaler: (Denoising: 0.35, Upscale: 2x) Useful Extensions | | | ⁉ No VAE needed but it is better to use one for more vibrant colors ⭐ Feel free to leave Reviews and Samples - and always have fun creating ❤
521,191 Downloads · 8,787 Likes auf Civitai
SHA256
84D76A0328EE5A1A2A1D466BA7478AB59183E3FEA385441528AA4C5D567FD43E
ModelTrends.ai-Modell-ID
#7689
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
DPM++ 2M
Schritte
20
Guidance
7
Seed
2911837756
Größe
512x512
Prompt
<lora:k_lora:.7 > A highly detailed, photorealistic close-up portrait of a woman with neutral expression, looking directly at the camera. She has smooth, fair skin with soft natural texture, light freckles across her cheeks and nose, deep brown almond-shaped eyes with long natural lashes, and subtly arched, dark eyebrows. Her lips are full with a natural pink tone, gently closed, and slightly relaxed. She wears a small silver hoop nose ring in her left nostril. Her medium-length dark brown hair is parted to the side, framing her face, with soft waves and a subtle auburn tint under indoor lighting. Her left hand rests on her cheek, showing a wedding ring with a large central stone and detailed silver band. Captured indoors under diffused soft light, with shallow depth of field and warm tones. Natural lighting, DSLR portrait style, 85mm lens, f/1.8 aperture, high-resolution, realistic facial proportions, no makeup, clean and unfiltered look, soft shadows and smooth bokeh in the background.
Negativer Prompt
cartoon, anime, digital art, unrealistic skin, blemishes, exaggerated facial features, wrong nose ring, wrong eye color, makeup, lipstick, heavy shadows, glasses, bangs, exaggerated lighting, overexposed, underexposed, low-res, distorted hands, wrong ring, fantasy elements, filters, smiling, frowning, head tilt, artistic style
Einstellungen
Sampler
DPM++ 2M Karras
Schritte
36
Guidance
10
Seed
1178266353
Größe
512x768
Clip skip
2
Prompt
Colossal Jaeger-style mecha with realistic metallic textures and glowing blue reactor on its chest, wielding a massive energy sword, standing in the ocean as waves crash at its feet. Two giant mechas battle against a towering kaiju monster amidst detailed city destruction, neon lights glowing through heavy rain, futuristic skyline backdrop, cinematic perspective, ultra-detailed, anime-mecha art style.
Negativer Prompt
blurry, low quality, watermark, text
Einstellungen
Sampler
DPM++ 2M Karras
Schritte
22
Guidance
6
Seed
1492004694
Größe
512x768
Prompt
(retouched:1.6), fitness woman, sneakers, studio
Negativer Prompt
asian, chinese, cartoon, painting, illustration, (worst quality, low quality, normal quality:2)
Einstellungen
Sampler
DPM++ SDE Karras
Schritte
25
Guidance
7
Seed
144278541
Größe
640x960
Prompt
polaroid photo, night photo, photo of 24 y.o beautiful woman, pale skin, bokeh, motion blur
Negativer Prompt
(deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime, mutated hands and fingers:1.4), (deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, amputation
Einstellungen
Sampler
DPM++ 2M Karras
Schritte
36
Guidance
10
Seed
1178266353
Größe
512x768
Clip skip
2
Prompt
Colossal Jaeger-style mecha with realistic metallic textures and glowing blue reactor on its chest, wielding a massive energy sword, standing in the ocean as waves crash at its feet. Two giant mechas battle against a towering kaiju monster amidst detailed city destruction, neon lights glowing through heavy rain, futuristic skyline backdrop, cinematic perspective, ultra-detailed, anime-mecha art style.
Negativer Prompt
blurry, low quality, watermark, text
Einstellungen
Sampler
ddpm
Schritte
30
Guidance
7
Seed
607902164977911
Größe
1024x1016
Prompt
old, sad, talking, open mouth, Nordic man on wagon, wooden cart, blue worn leather armor, chainmail, fur, snowy winter forest, eyeliner, scared, battleworn,
Negativer Prompt
worst quality, wembedding:bBy bad artist -neg, embedding:BadDream, embedding:badhandv4, embedding:bad_prompt_version2-,
Einstellungen
Sampler
DPM++ 2M Karras
Schritte
36
Guidance
10
Seed
1178266353
Größe
512x768
Clip skip
2
Prompt
Colossal Jaeger-style mecha with realistic metallic textures and glowing blue reactor on its chest, wielding a massive energy sword, standing in the ocean as waves crash at its feet. Two giant mechas battle against a towering kaiju monster amidst detailed city destruction, neon lights glowing through heavy rain, futuristic skyline backdrop, cinematic perspective, ultra-detailed, anime-mecha art style.
Negativer Prompt
blurry, low quality, watermark, text
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.
natural sin on ModelTrends.ai: #20 of 16,523 AI models
natural sin on ModelTrends.ai: #6 of 4,540 Stable Diffusion 1.5 models
natural sin on ModelTrends.ai: #6 of 396 Stable Diffusion 1.5 base models
KI-Modelle für Bild-, Video- und Texterzeugung
natural sin ist ein Basismodell für die Familie Stable Diffusion 1.5 und wird auf ModelTrends.ai gelistet, einem reinen Lesekatalog für Open-Source-KI-Modelle für Bild, Video und Text. Vergleiche es mit anderen Stable Diffusion 1.5-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