*Example images' prompts in InvokeAI format, not A1111 format. If you don't use InvokeAI, don't copy/paste my prompts without first adjusting the syntax.Animated version is less heavily anime and thus more general-purpose. Anime version is more focused towards anime, and has some extra specialization in chaos and scenery, and much less tendency for uncanny valley.USAGE TIPS, BEST PRACTICES, AND SETTINGS (Anime-V2 version):<ul><li>After more practice with the model, the negative prompt I use most is <code>bad-artist, negative_hand, (low quality, worst quality:1.3)</code> in A1111 syntax, or <code>bad-artist, negative_hand, (low quality, worst quality)1.3</code> in InvokeAI syntax. Doesn't work perfect for everything, mind you, though it's a good start. Some prompts work best without negative embeddings and <code>low quality, worst quality</code> with 1.4 weight instead </li><li>The recommended negative embeddings are <a target="_blank" rel="ugc" href="https://civarchive.com/models/56519/negativehand-negative-embedding">negative_hand</a>, and then either a choice of <a target="_blank" rel="ugc" href="https://huggingface.co/nick-x-hacker/bad-artist">bad-artist</a> (the base version), <a target="_blank" rel="ugc" href="https://huggingface.co/dwringer/neg-anime">&lt;neg-anime&gt;</a>, or <a target="_blank" rel="ugc" href="https://huggingface.co/JPPhoto/neg-sketch-2">&lt;neg-sketch-2&gt;</a>. <code>negative_hand</code> doesn't interfere with the model and has an okay success rate. <code>bad-artist</code> has less effect on model imagination than <code>&lt;neg-anime&gt;</code> or <code>&lt;neg-sketch-2&gt;</code>, and provides brighter and more colorful results, though may not increase detail as much. <code>&lt;neg-anime&gt;</code> or <code>&lt;neg-sketch-2&gt;</code> are the opposite. More impact on imagination, yet more detailed and less change in composition. <code>&lt;neg-anime&gt;</code> seems to lean towards darker images in Anime-V2. <a target="_blank" rel="ugc" href="https://huggingface.co/SweetLuna/Aurora/tree/main/AuroraEmbeddings">Luna's KHFB and AuroraNegative</a> are also safe to use, though I don't use them personally.</li><li>Other negative embeddings (e.g. bad-artist-anime, EasyNegative, bad_prompt_version2) are generally not recommended, as they impact art style and model expressiveness and have little, if any, actual benefit.</li><li>With or without any negative embeddings, <code>negative_hand</code> aside, using <code>(low quality, worst quality)</code> with a 1.3 or 1.4 weight does the job for most prompts if you get any subpar definition or color.</li><li>Does not respond very well to LoRAs trained mainly 2.5d, 3d, or photorealistic-style images, such as dogu_cat's it<a target="_blank" rel="ugc" href="https://civarchive.com/models/56877/its-skyler-white-yolora">'s Skyler White Yo</a> guy LoRA.</li><li>Upscaling via img2img / High-Res Optimization in InvokeAI is ideal, especially at a strength like 0.47-0.55.</li><li>Example images were generated without CLIP skip. CLIP skip 2 has interesting effect, though does reduce stylization.</li><li>This model uses the Waifu Diffusion 1.4 VAE with the pixel layer modified for -6% contrast. img2img at low strength may reduce quality unless you swap the VAE.</li></ul>USAGE TIPS, BEST PRACTICES, AND SETTINGS (Animated version):<ul><li><code>negative_hand</code> and <code>bad-artist</code> are the only negative embeddings I can comfortably recommend using for this model, and not even that is a requirement. <code>&lt;neg-anime&gt;</code> or <code>&lt;neg-sketch-2&gt;</code> are also great, but tend towards a semi-realistic style in this model, so be wary of the uncanny valley if you use them.</li><li>To liven up color and lighting (when not using a negative embedding), I suggest putting <code>desaturated</code> and <code>pixelated</code> in your negative prompt with 2 or 3 units of down-weighting (that means <code>[[[desaturated]]], [[[pixelated]]]</code> in A1111 UI, or <code>desaturated---, pixelated---</code> in InvokeAI).</li><li>To lean output more towards an anime style rather than semi-realistic, include <code>anime</code> in your prompt. Put <code>realistic</code> in your negative prompt to further lean towards 2D, or by the front of your positive prompt to lean more 3D.</li></ul>Example images were generated in InvokeAI, so you'll have to use your UI's weighting syntax (which means the + and - in my prompts likely won't do anything for you unless you're using InvokeAI).This model will be great for:<ul><li>People who want an anime aesthetic that is different from other SD 1.5 models</li><li>People who are more distant, casual enjoyers of anime, who might find this model more welcoming than one that's heavily leaned to modern anime art only</li><li>People who like more classic anime styles, ala Voltron and Ghost in the Shell</li><li>People who like generating in 2D and semi-real styles and liked 526Mix, who will probably enjoy the better lighting and touch of wackiness in this version</li></ul>The "Animated" model is a straightforward mix of 526Mix-V1.3.5, and Nerfgun3's <a target="_blank" rel="ugc" href="https://civarchive.com/models/11069/macaron-mix">Macaron Mix</a>, the latter having had the noise offset added at 0.70 multiplier. This is done with a weighted sum at a 0.3 multiplier with Macaron Mix. I always like Nerfgun3's art and embeddings, so I felt I could trust that model to be fairly in line with my own creative desires and expectations.As always, I suggest going to the source models for the full experience, and Nerfgun3's Macaron Mix and Newartmodel4 aren't exceptions here.Example images were generated in Invoke AI with the model converted to Diffusers format, hires fix on (0.45 strength, works like img2img), and the sampler DDIM (unless listed otherwise). This means unless you use Invoke AI, you likely won't be able to recreate my images exactly. Just learn from the prompts and modify the weighting in prompts as needed for the UI you use (if you use the A1111 UI, any (plus sign)+ is equal to one set of parentheses).

526Mix-Anime+Animated

New - Anime-V2 (still SD 1.5 because I can't run 2.1 768x models lol): New version with a bit of a style change. Reduction in the giant/titan issue that appeared in some prompts, and the model is less overbaked and cleaner at default settings with a tradeoff of being a little more needy for good negative prompting. Has a slight leaning towards generating women, but still won't fight you if you want dudes because that's annoying as hell and I wouldn't allow that. Also, anime is more entrenched and doesn't need to be explicitly prompted anymore.

Files with SHA256: 5ddf7e5cf335fcdd72e3f8a940b586aacc3b4d57a386b4bddb491af74ec86e2b