<h1 id="heading-24">Model play recommendation</h1><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/e3df675e-d47a-480b-8fa9-543c5464d190/width=525/e3df675e-d47a-480b-8fa9-543c5464d190.jpeg" /><h2 id="heading-25">There are more pictures in the Gallery for reference</h2><ol><li>Recommended Sampling Method:(DPM 2M Karras)(DPM SDE Karras)(DPM2)(Euler a)</li><li>Iteration steps recommended: 30-60 according to the actual situation of the individual adjustment</li><li>HD repair redrawing amplitude recommendation: (default 7) can also be adjusted according to individual mold</li><li>Size recommendation: 1024 starting effect (good)</li><li>Recommendation of prompt words: 7-16 coefficient</li></ol><h3 id="heading-83">It is recommended to use it together with the LORA model for better results. (<a target="_blank" rel="ugc" href="https://civarchive.com/models/146627/xllora">万享XL_LORA - v1.0 | Stable Diffusion LoRA | Civitai</a>)</h3><h3 id="heading-84">Lora helps to generate different styles of pictures, adding more details, gloss, color, texture, light and shadow, better rendering effect.</h3><h2 id="heading-85">Please return more pictures when it is convenient for family members. Some pictures are convenient for everyone to have more inspiration and reference in the drawing.</h2><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/cbedf109-45e1-41e0-a5dc-6959bd610068/width=525/cbedf109-45e1-41e0-a5dc-6959bd610068.jpeg" />

wanxiangXL

Model play recommendationRecommended Sampling Method:(DPM 2M Karras)(DPM SDE Karras)(DPM2)(Euler a)Recommended number of iteration steps: 25-60 adjusted according to individual actual situationHD repair redrawing amplitude recommendation: (default 7) can also be adjusted according to individual moldSize recommendation: 1024 starting effect (good)Recommendation of prompt words: 7-16 coefficientPlease return more pictures when it is convenient for family members. Some pictures are convenient for everyone to have more inspiration and reference in the drawing.

wanxiangxl_v50.safetensors

Wanxiang XL (Collector's Edition V6.0)

Recommended sampling method for V3.0 model gameplay: (DPM++ 2M
 
Karras) (DPM++ SDE Karras) (DPM2) (Euler a) Recommended number of iteration steps: 30-60 adjusted according to individual circumstances
 
Recommended size for high-definition restoration and redrawing: (Default 7) You can also adjust the size according to personal modeling recommendations:
 
Recommended words for 1024 starting results (good): 7-16 coefficient combination (
 <a href="https://www.liblib.ai/modelinfo/c9cfba1b1e1a4c46b393206c483aa508?mine=1" target="_blank">(Wanxiang XL_LORA</a> ) 
The drawing effect is better, you can click to enter the page and trouble the family to return more pictures when it is convenient for everyone to have more inspiration and reference in drawing

Files with SHA256: c64da72d7a526cf8598de603fae4e32ac6493b0c5ac16d4a75ac543aa4a39cf8