作者原文：

V3 is here!

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: 512×768 or 768×512
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 ❤