Nickel Saffron

详情

下载文件 (1)

模型描述

Nickel Saffron

Clean realism, flexible polish.

Built off the same Illustrious SDXL base as Copper Thyme, Nickel Saffron trades the stylized strokes and sketch-driven grit for a cleaner, more grounded visual style. This merge focuses on natural lighting, smoother skin rendering, and believable textures across fabric, hair, and materials.

Where Copper Thyme leaned into illustrative flair — line work, stylized shading, and more aggressive silhouettes — this one softens the edges. You’ll get better balance in anatomy, more lifelike lighting, and cleaner contrast without losing creative flexibility. It’s tuned for portraits, fashion, fantasy, and semi-erotic renders that want polish without overbaked effects.

If you liked the structure and prompt control of Copper Thyme but wanted something more realistic — this is it.

🔧 Recommended Settings:

A well-rounded setup for general SDXL prompting.

Steps: 30

Sampler: euler_ancestral

Scheduler: karras

CFG (Guidance): 4

Some of the quality tags I use are:

🏷️ Recommended Quality Tags

masterpiece, cinematic lighting, anime_screencap, high detail, depth of field, (blurred background), (dramatic lighting), best quality, very aesthetic, soft reflections,

((painting)), (masterpiece, best quality, amazing quality), very aesthetic, ultra-detailed, highly detailed, intricate details, absurdres, (volumetric lighting, HDR, backlighting, blurry foreground),

Image-to-Image Tips

For upscaling workflows, I've found that a denoise range of 0.4 to 0.5 works best. This preserves structure while still enhancing detail without overbaking the image.


📋 ADetailer Settings

Here are the current ADetailer/YOLO settings shown:

steps: 10

cfg: 5.0

sampler_name: dpmpp_2m

scheduler: karras

denoise: 0.45

feather: 10

noise_mask: enabled

force_inpaint: disabled

bbox_threshold: 0.65

bbox_dilation: 1

bbox_crop_factor: 1.5

sam_detection_hint: mask-area

sam_dilation: 4

sam_threshold: 0.93

sam_bbox_expansion: 0

sam_mask_hint_threshold: 0.70

sam_mask_hint_use_negative: False

drop_size: 5

Maybe I have my settings wrong and if you know a fix let me know. I only pretend to know what I'm doing.

此模型生成的图像