Since the Pony model and the SDXL model are very different, I trained the Pony version of DeepNegative<h3 id="how-to-use-it-7exts8cw7">How to use it?</h3>put it in negative prompt.another deep-negative:<ul><li>1.5 version: <a target="_blank" rel="ugc" href="https://civarchive.com/models/4629/deep-negative-v1x">https://civarchive.com/models/4629</a></li><li>SDXL version: <a target="_blank" rel="ugc" href="https://civarchive.com/models/407448">https://civarchive.com/models/407448</a></li></ul><h3 id="what-does-it-do-r12ku0zdx">What does it do?</h3>DeepNegative is a negative embedding. it contain unsightly compositions and color patterns, such as inaccurate human anatomy, distasteful color combinations, disoriented spatial structures, and more. By put it in negative prompt, we can significantly reduce the occurrence of these elements.<h3 id="suggestion-qhfyj5kio">Suggestion</h3>Because this embedding is learning how to create disgusting concepts, it cannot improve the picture quality accurately, so it is best used with (worst quality, low quality, logo, text, watermark, username:1) these negative prompts.Of course, it is completely fine to use with other similar negative embeddings.<a target="_blank" rel="ugc" href="https://huggingface.co/lenML/Deep-Negative-Pony">backup on huggingface</a>

Files with SHA256: 4dd0e783ca77fba115aabc96e0e61413657b0512a035de6c5f483c49fa6a1488