Diffus
Inicio
Afiliado
Precios
SD3
API
Modelos
Galería
Empezar
modelos/epiCRealism - pure Evolution V5

epiCRealism - pure Evolution V5

Kate Thompson
|
7/1/2024
|
9:50:55 PM
| Discussion
Digital illustration of a black vintage sports car on a checkered floor against a blue and orange retro futuristic background with an orange sun and trees.
Blonde model with retro hairstyle wearing red high-waisted shorts and a white crop top posing outdoors.
Full body portrait of a Japanese model styled in 1960s fashion wearing cream bell pants, a cozy white shrug sweater, and white heels, posing against a plain beige background.
Full body view of a Hawaiian model wearing a floral skirt and white top, adorned with a flower necklace and crown, standing in tropical garden
Two slender pale-skinned ginger girls share a kiss on a sidewalk near a building, styled with muted tones and symmetrical composition reminiscent of Wes Anderson.
Pale Scandinavian ginger woman wearing an oversized fuzzy white sweater standing outdoors in snowy field with dark storm clouds overhead.
Portrait of a pale blond woman with a subtle smug expression, dressed in a white blouse, set against an abstract watercolor background inspired by Zao Wou-Ki.
A serene image of a woman in a dark dress, sitting with her legs crossed in a garden surrounded by blooming cherry blossoms, created using stable diffusion AI.
Samurai standing in a dimly lit alley at night, generated by AI using Stable Diffusion.
A woman stands on a dimly lit Japanese street at night, rendered by AI using stable diffusion. She wears a light-colored top and looks towards the camera with a calm expression. Traditional Japanese lanterns and wooden buildings create an atmospheric background.
A female samurai warrior in traditional attire, holding a katana, standing in a dimly lit alley with traditional buildings.
A shirtless man with dreadlocks standing on a traditional Japanese street. AI generated image using Stable Diffusion.

Prompts Recomendados

simple explanation of the image,without extra keywords

Prompts Negativos Recomendados

cartoon, painting, illustration

(worst quality, low quality, normal quality:2)

asian,chinese,(epicnegative:0.9)

Parámetros Recomendados

samplers

DPM++ 2M Karras, DPM++ SDE Karras, DPM++ SDE

steps

20 - 30

cfg

5 - 6

resolution

512x768

other models

epiCRealism-pureEvolutionV5 (76be5be1b2)

Parámetros Recomendados de Alta Resolución

upscaler

4x_NMKD-Superscale-SP_178000_G

upscale

2

steps

14

denoising strength

0.35

Consejos

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)'

Use simple negatives or small negative embeddings for the most realistic look

Add 'asian, chinese' to negative if you're looking for ethnicities other than Asian

Light, shadows, and details are excellent without extra keywords

Avoid 'cinematic' for a natural effect

Avoid using '1girl' as it pushes the render towards an anime style

Too 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 you can use it if you like

Aspectos Destacados de la Versión

again quality improve
now better eyes (really!) 😄

Patrocinadores del Creador

Thanks to @drawaline for the in-depth review.

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 @drawaline for the in-depth review, 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: 4x_NMKD-Superscale-SP_178000_G (Denoising: 0.35, Upscale: 2x)

Useful Extensions

!After Detailer | ControlNet | Agent Scheduler | Ultimate SD Upscale

⁉ 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 ❤

Anterior
EasyNegative - EasyNegative
Siguiente
Styles for Pony Diffusion V6 XL Not Artists styles - Smooth Anime
Usar este modelo

Detalles del Modelo

Tipo de modelo

Checkpoint

Modelo base

SD 1.5

Versión del modelo

pure Evolution V5

Hash del modelo

76be5be1b2

Creador

epinikion's avatar
epinikion

Discusión

Por favor log in para dejar un comentario.

Imágenes por epiCRealism - pure Evolution V5

Digital illustration of a black vintage sports car on a checkered floor against a blue and orange retro futuristic background with an orange sun and trees.
Pale Scandinavian ginger woman wearing an oversized fuzzy white sweater standing outdoors in snowy field with dark storm clouds overhead.
A female samurai warrior in traditional attire, holding a katana, standing in a dimly lit alley with traditional buildings.
Aerial view of a city nestled in mountains during sunset, created with AI using stable diffusion
Blonde model with retro hairstyle wearing red high-waisted shorts and a white crop top posing outdoors.
Portrait of a pale blond woman with a subtle smug expression, dressed in a white blouse, set against an abstract watercolor background inspired by Zao Wou-Ki.
A shirtless man with dreadlocks standing on a traditional Japanese street. AI generated image using Stable Diffusion.
A Gothic woman with black lipstick, dark hair, and luminous eyes, in an AI generated image using Stable Diffusion.
Full body portrait of a Japanese model styled in 1960s fashion wearing cream bell pants, a cozy white shrug sweater, and white heels, posing against a plain beige background.
A serene image of a woman in a dark dress, sitting with her legs crossed in a garden surrounded by blooming cherry blossoms, created using stable diffusion AI.
AI generated image using Stable Diffusion showing a woman with red hair smiling and dressed in a blue dress, standing in a night city with bright lights in the background.
A woman with green hair lying in the sand in a desert garden, created with AI using Stable Diffusion.
Full body view of a Hawaiian model wearing a floral skirt and white top, adorned with a flower necklace and crown, standing in tropical garden
Samurai standing in a dimly lit alley at night, generated by AI using Stable Diffusion.
Close-up portrait of a beautiful woman with a serene expression created using Stable Diffusion, an AI image generation tool.
An AI-generated image of a young woman underwater, with a serene and ethereal expression, created using Stable Diffusion.
Two slender pale-skinned ginger girls share a kiss on a sidewalk near a building, styled with muted tones and symmetrical composition reminiscent of Wes Anderson.
A woman stands on a dimly lit Japanese street at night, rendered by AI using stable diffusion. She wears a light-colored top and looks towards the camera with a calm expression. Traditional Japanese lanterns and wooden buildings create an atmospheric background.
A samurai dressed in traditional red and black kimono, standing outdoors with trees in the background, AI generated image using Stable Diffusion.
A vibrant, AI-generated image using Stable Diffusion of a bright and colorful lizard standing on a reflective surface in a tropical forest setting.