If you want to use more my checkpoint online generation, please visit here.<a target="_blank" rel="ugc" href="https://tensor.art/u/762555264535746522">https://tensor.art/u/762555264535746522</a><h3 id="v3-fmqrzo01r">V3</h3><h3 id="the-overall-quality-has-improved-and-some-camera-training-has-been-added.-9hfda9hw0">The overall quality has improved, and some camera training has been added.</h3><h2 id="v2-wg6yqmuda">v2</h2><h3 id="the-quality-has-been-further-improved-with-enhanced-cinematographic-composition.-rgz9weupt">The quality has been further improved, with enhanced cinematographic composition.</h3><h3 id="-diuyb7drl"></h3>Recommended Setting<ul><li>Steps: 30-50</li><li>CFG scale: 7</li><li>Sampler: Euler a</li><li>ADetailer face_yolov8n/<a target="_blank" rel="ugc" href="http://s.pt">s.pt</a> use more better</li></ul>Positive Prompt<pre><code>score_9, score_8_up, score_7_up,source_real,rating_explicit,BREAK</code></pre>Negative Prompt<pre><code>Not particularly necessary</code></pre>

WAI-SemiReal

waiSemireal_v20.safetensors

v2.0

v3.0

v1.0

I am the model author mainly active on civitai. I came here to share my models due to an opportunity, mainly creating content related to ponies.My homepage is<a href="https://civitai.com/user/WAI0731" target="_blank">https://civitai.com/user/WAI0731</a> , hoping everyone can come and support.About this modelThis version starts updating from 2.0This model is a big model of a pony, Lora only recommends basic ponies, SDXL may not have good effects.Due to the special nature of the model, please be sure to abide by relevant national laws,the content generated based on this model is to be maintained by yourself and used after independent judgment, you are responsible for the generated content, I am not responsible for any losses caused by this. Basic Usage Method<ul><li style="text-align: start;">Number of steps: 30</li><li style="text-align: start;">CFG: 7</li><li style="text-align: start;">Sampling: Euler a/DPM++ 2M Karras</li><li style="text-align: start;">If there are facial issues in the mid-range, use ADetailer</li><li style="text-align: start;">For direct output, please use resolution greater than 1024x1024</li></ul>P.S. When setting prompts, do not rush to add weight to the prompts. Only add if necessary, excessive weight will result in ghost images. Positive prompts: score_9, score_8_up, score_7_up, source_real, rating_explicit, BREAK (must be included)Negative prompts: None required Disclaimer:The text content generated based on this model is to be maintained and used by yourself after independent judgment. You are required to use it in compliance with applicable laws and regulations. Any intellectual property issues arising from the content generated based on this model are to be handled by you. You are responsible for the generated content, and I am not liable for any losses incurred as a result.

Files with SHA256: f18c2ac8c74ae6a07ead55bf7a5a9800080983e77ecc45bc3ac47e05895012fb