Blue sportscar racing on a track at night with headlights on, spectators behind safety barriers, and track lights illuminating the scene.
Fashion portrait of a woman with long blonde hair, wearing a white long-sleeve top and denim jeans. AI generated image using stable diffusion.

推薦提示詞

simple explanation of the image

推薦反向提示詞

cartoon,painting,illustration,(worst quality, low quality, normal quality:2),asian,chinese

推薦參數

samplers

SDE, DPM-Sampler, 2M Karras, DPM++ SDE Karras, DPM++ 2M Karras, DPM++ SDE, Restart, DPM++ 2M SDE Karras

steps

20 - 30

cfg

2 - 7

resolution

512x768, 768x512, 512x768, 640x960, 768x512

vae

vae-ft-mse-840000-ema-pruned.safetensors (1006afe4e2)

推薦高解析度參數

upscaler

4x_NMKD-Superscale-SP_178000_G

upscale

1.5 - 2

steps

10 - 15

denoising strength

0.3 - 0.35

提示

Use simple prompts without extra keywords for best results.

Avoid keywords like 'masterpiece, best quality, 8k, intricate, high detail' as they don't improve output.

Use simple negatives or small negative embeddings for more realism.

Add 'asian, chinese' to negative prompts if avoiding Asian ethnicities.

Avoid using 'cinematic' for natural effects.

Avoid '1girl' keyword as it tends to push output toward anime style.

Using too much facial description often worsens the quality.

For a fantasy-like output, use 2M Karras Sampler.

No extra noise-offset is needed but can be used optionally.

版本亮點

Natural Sin Final Photo Realism refined

same generation data as RC1 for comparsion

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 ❤

貢獻者

上一個
Alien Abduction Style (FLUX) - More Detail - Best Version
下一個
Midjourney Luneva Cinematic Lora - LORA: R128-5000step

模型詳情

模型類型

Checkpoint

基礎模型

SD 1.5

模型版本

Natural Sin

模型雜湊值

bff4610d23

創作者

討論

log in以發表評論。