it is not a normal ceckpoint-model, its for fine tuning your pics !not new trained only a merge of pix2pix and realv30<h3 id="heading-83">my first try of a new PIX2PIX model with better quality and may NSFW content</h3>Please tell me what you do with such a model?save it in default model folderuse it like:<a target="_blank" rel="ugc" href="https://stable-diffusion-art.com/instruct-pix2pix/">https://stable-diffusion-art.com/instruct-pix2pix/</a>main idea is to work with img2img you can write a prompt like: change A into B, and play with CFG Scale and Image CFG Scale careful.works also with inpaint little better than normal inpaint models but only with change colors etc. If you have a png image with areas erased (remove background) and mask it, everything will always be changed no matter what the settings, in my model more the masked areas would be changed.<ul><li>dont use BadDream, UnrealisticDream.</li></ul>-&gt; if inpaint use only (original) and you will see an extra button<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/8a7bdf52-badb-47eb-84cf-878649b28673/width=525/8a7bdf52-badb-47eb-84cf-878649b28673.jpeg" />

img2img + pix2pix - realv30

smaller size, no change in accuracy

Files with SHA256: 3ced8b300f38e458c180753e53bee7268f8977b5b5c7b2727ec4bc1f364c8ea7