Empfohlene Prompts

simple explanation of the image,without extra keywords

Empfohlene Negative Prompts

cartoon, painting, illustration

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

asian,chinese,(epicnegative:0.9)

Empfohlene Parameter

samplers

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

steps

20 - 30

cfg

5 - 6

resolution

512x768

other models

epiCRealism-pureEvolutionV5 (76be5be1b2)

Empfohlene Hires (Hochauflösungs-) Parameter

upscaler

4x_NMKD-Superscale-SP_178000_G

upscale

2

steps

14

denoising strength

0.35

Tipps

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

Versions-Highlights

again quality improve
now better eyes (really!) 😄

Ersteller-Sponsoren

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 ❤

Zurück
EasyNegative - EasyNegative
Weiter
Styles for Pony Diffusion V6 XL Not Artists styles - Smooth Anime

Modell-Details

Modelltyp

Checkpoint

Basismodell

SD 1.5

Modellversion

pure Evolution V5

Modell-Hash

76be5be1b2

Ersteller

Diskussion

Bitte log in um einen Kommentar zu hinterlassen.